github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-07 00:22:43 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #13739] v0.14.1 fails to start on Windows #34765

New Issue
Closed
opened 2026-04-22 18:35:48 -05:00 by GiteaMirror · 2 comments
GiteaMirror commented 2026-04-22 18:35:48 -05:00
Owner
Copy Link

Originally created by @kyleweishaupt on GitHub (Jan 16, 2026).
Original GitHub issue: https://github.com/ollama/ollama/issues/13739

What is the issue?

I'm unable to get Ollama for Windows to start. It appears to hang, even though some endpoints like /api/tags work.

When I try to run ollama list I get: Error: Head "http://0.0.0.0:11434/": read tcp 127.0.0.1:63869->127.0.0.1:11434: wsarecv: An existing connection was forcibly closed by the remote host.

I have all the latest updates on Windows 11. Nvidia RTX 3060 GPU with latest 591.74 drivers. Intel I9-13900K CPU.

Relevant log output

time=2026-01-15T19:28:53.031-05:00 level=INFO source=app_windows.go:270 msg="starting Ollama" app=C:\Users\kylew\AppData\Local\Programs\Ollama version=0.14.1 OS=Windows/10.0.26200
time=2026-01-15T19:28:53.032-05:00 level=INFO source=app.go:237 msg="initialized tools registry" tool_count=0
time=2026-01-15T19:28:53.043-05:00 level=INFO source=app.go:252 msg="starting ollama server"
time=2026-01-15T19:28:53.043-05:00 level=INFO source=app.go:277 msg="starting ui server" port=62999
time=2026-01-15T19:28:53.044-05:00 level=DEBUG source=app.go:279 msg="starting ui server on port" port=62999
time=2026-01-15T19:28:53.050-05:00 level=DEBUG source=app.go:316 msg="no URL scheme request to handle"
time=2026-01-15T19:28:53.050-05:00 level=DEBUG source=app.go:320 msg="waiting for ollama server to be ready"
time=2026-01-15T19:28:53.216-05:00 level=DEBUG source=webview.go:446 msg="starting webview event loop"
time=2026-01-15T19:28:53.223-05:00 level=DEBUG source=eventloop.go:22 msg="starting event handling loop"
time=2026-01-15T19:28:53.335-05:00 level=INFO source=ui.go:236 msg=site.serveHTTP http.method=GET http.path=/api/v1/settings http.pattern="GET /api/v1/settings" http.status=200 http.d=0s request_id=1768523333335148900 version=0.14.1
time=2026-01-15T19:28:53.336-05:00 level=INFO source=ui.go:236 msg=site.serveHTTP http.method=GET http.path=/api/v1/chats http.pattern="GET /api/v1/chats" http.status=200 http.d=0s request_id=1768523333336336800 version=0.14.1
time=2026-01-15T19:28:53.838-05:00 level=ERROR source=ui.go:1468 msg="failed to get inference compute" error="timeout scanning server log for inference compute details"
time=2026-01-15T19:28:53.838-05:00 level=ERROR source=ui.go:236 msg=site.serveHTTP error="failed to get inference compute: timeout scanning server log for inference compute details" http.method=GET http.path=/api/v1/inference-compute http.pattern="GET /api/v1/inference-compute" http.status=500 http.d=502.9255ms request_id=1768523333335148900 version=0.14.1
time=2026-01-15T19:28:53.839-05:00 level=INFO source=ui.go:236 msg=site.serveHTTP http.method=GET http.path=/api/v1/chats http.pattern="GET /api/v1/chats" http.status=200 http.d=0s request_id=1768523333839226400 version=0.14.1
time=2026-01-15T19:28:54.869-05:00 level=INFO source=server.go:344 msg=Matched "inference compute"="{Library:CUDA Variant: Compute:8.6 Driver:13.1 Name:CUDA0 VRAM:8.0 GiB}"
time=2026-01-15T19:28:54.869-05:00 level=INFO source=ui.go:236 msg=site.serveHTTP http.method=GET http.path=/api/v1/inference-compute http.pattern="GET /api/v1/inference-compute" http.status=200 http.d=12.84ms request_id=1768523334856327700 version=0.14.1
time=2026-01-15T19:28:56.044-05:00 level=INFO source=updater.go:254 msg="beginning update checker" interval=1h0m0s
time=2026-01-15T19:28:56.045-05:00 level=DEBUG source=updater.go:100 msg="checking for available update" requestURL="https://ollama.com/api/update?arch=amd64&nonce=vAVM3rq24CUUNKdBtrRFaw&os=windows&ts=1768523336&version=0.14.1" User-Agent="ollama/0.14.1 amd64 Go/go1.24.1 Windows/10.0.26200"
time=2026-01-15T19:28:56.266-05:00 level=DEBUG source=updater.go:109 msg="check update response 204 (current version is up to date)"
time=2026-01-15T19:29:14.112-05:00 level=WARN source=app.go:322 msg="ollama server not ready, continuing anyway" error="timeout waiting for Ollama server to be ready"
time=2026-01-15T19:29:14.348-05:00 level=WARN source=ui.go:136 msg="ollama server not ready, retrying" attempt=2
time=2026-01-15T19:29:20.550-05:00 level=INFO source=ui.go:236 msg=site.serveHTTP http.method=GET http.path=/api/v1/settings http.pattern="GET /api/v1/settings" http.status=200 http.d=0s request_id=1768523360550840600 version=0.14.1
time=2026-01-15T19:29:22.317-05:00 level=INFO source=ui.go:236 msg=site.serveHTTP http.method=GET http.path=/api/v1/chats http.pattern="GET /api/v1/chats" http.status=200 http.d=0s request_id=1768523362317712800 version=0.14.1
time=2026-01-15T19:29:22.318-05:00 level=INFO source=ui.go:236 msg=site.serveHTTP http.method=GET http.path=/api/v1/settings http.pattern="GET /api/v1/settings" http.status=200 http.d=0s request_id=1768523362318383600 version=0.14.1
time=2026-01-15T19:29:36.392-05:00 level=ERROR source=ui.go:148 msg="ollama server not ready after retries" error="timeout waiting for Ollama server to be ready"
time=2026-01-15T19:29:38.876-05:00 level=INFO source=ui.go:236 msg=site.serveHTTP http.method=GET http.path=/api/v1/settings http.pattern="GET /api/v1/settings" http.status=200 http.d=0s request_id=1768523378876417000 version=0.14.1
time=2026-01-15T19:29:57.449-05:00 level=WARN source=ui.go:136 msg="ollama server not ready, retrying" attempt=2
time=2026-01-15T19:30:19.488-05:00 level=ERROR source=ui.go:148 msg="ollama server not ready after retries" error="timeout waiting for Ollama server to be ready"
time=2026-01-15T19:30:40.541-05:00 level=WARN source=ui.go:136 msg="ollama server not ready, retrying" attempt=2
time=2026-01-15T19:31:02.580-05:00 level=ERROR source=ui.go:148 msg="ollama server not ready after retries" error="timeout waiting for Ollama server to be ready"
time=2026-01-15T19:31:23.612-05:00 level=WARN source=ui.go:136 msg="ollama server not ready, retrying" attempt=2
time=2026-01-15T19:31:45.662-05:00 level=ERROR source=ui.go:148 msg="ollama server not ready after retries" error="timeout waiting for Ollama server to be ready"
time=2026-01-15T19:32:06.722-05:00 level=WARN source=ui.go:136 msg="ollama server not ready, retrying" attempt=2
time=2026-01-15T19:32:28.769-05:00 level=ERROR source=ui.go:148 msg="ollama server not ready after retries" error="timeout waiting for Ollama server to be ready"
time=2026-01-15T19:32:43.067-05:00 level=INFO source=ui.go:236 msg=site.serveHTTP http.method=GET http.path=/api/v1/chats http.pattern="GET /api/v1/chats" http.status=200 http.d=0s request_id=1768523563067849700 version=0.14.1
time=2026-01-15T19:32:43.081-05:00 level=INFO source=ui.go:236 msg=site.serveHTTP http.method=GET http.path=/api/v1/settings http.pattern="GET /api/v1/settings" http.status=200 http.d=13.3685ms request_id=1768523563067849700 version=0.14.1
time=2026-01-15T19:32:49.820-05:00 level=WARN source=ui.go:136 msg="ollama server not ready, retrying" attempt=2

OS

Windows

GPU

Nvidia

CPU

Intel

Ollama version

0.14.1

Originally created by @kyleweishaupt on GitHub (Jan 16, 2026). Original GitHub issue: https://github.com/ollama/ollama/issues/13739 ### What is the issue? I'm unable to get Ollama for Windows to start. It appears to hang, even though some endpoints like `/api/tags` work. When I try to run `ollama list` I get: `Error: Head "http://0.0.0.0:11434/": read tcp 127.0.0.1:63869->127.0.0.1:11434: wsarecv: An existing connection was forcibly closed by the remote host.` I have all the latest updates on Windows 11. Nvidia RTX 3060 GPU with latest 591.74 drivers. Intel I9-13900K CPU. ### Relevant log output ```shell time=2026-01-15T19:28:53.031-05:00 level=INFO source=app_windows.go:270 msg="starting Ollama" app=C:\Users\kylew\AppData\Local\Programs\Ollama version=0.14.1 OS=Windows/10.0.26200 time=2026-01-15T19:28:53.032-05:00 level=INFO source=app.go:237 msg="initialized tools registry" tool_count=0 time=2026-01-15T19:28:53.043-05:00 level=INFO source=app.go:252 msg="starting ollama server" time=2026-01-15T19:28:53.043-05:00 level=INFO source=app.go:277 msg="starting ui server" port=62999 time=2026-01-15T19:28:53.044-05:00 level=DEBUG source=app.go:279 msg="starting ui server on port" port=62999 time=2026-01-15T19:28:53.050-05:00 level=DEBUG source=app.go:316 msg="no URL scheme request to handle" time=2026-01-15T19:28:53.050-05:00 level=DEBUG source=app.go:320 msg="waiting for ollama server to be ready" time=2026-01-15T19:28:53.216-05:00 level=DEBUG source=webview.go:446 msg="starting webview event loop" time=2026-01-15T19:28:53.223-05:00 level=DEBUG source=eventloop.go:22 msg="starting event handling loop" time=2026-01-15T19:28:53.335-05:00 level=INFO source=ui.go:236 msg=site.serveHTTP http.method=GET http.path=/api/v1/settings http.pattern="GET /api/v1/settings" http.status=200 http.d=0s request_id=1768523333335148900 version=0.14.1 time=2026-01-15T19:28:53.336-05:00 level=INFO source=ui.go:236 msg=site.serveHTTP http.method=GET http.path=/api/v1/chats http.pattern="GET /api/v1/chats" http.status=200 http.d=0s request_id=1768523333336336800 version=0.14.1 time=2026-01-15T19:28:53.838-05:00 level=ERROR source=ui.go:1468 msg="failed to get inference compute" error="timeout scanning server log for inference compute details" time=2026-01-15T19:28:53.838-05:00 level=ERROR source=ui.go:236 msg=site.serveHTTP error="failed to get inference compute: timeout scanning server log for inference compute details" http.method=GET http.path=/api/v1/inference-compute http.pattern="GET /api/v1/inference-compute" http.status=500 http.d=502.9255ms request_id=1768523333335148900 version=0.14.1 time=2026-01-15T19:28:53.839-05:00 level=INFO source=ui.go:236 msg=site.serveHTTP http.method=GET http.path=/api/v1/chats http.pattern="GET /api/v1/chats" http.status=200 http.d=0s request_id=1768523333839226400 version=0.14.1 time=2026-01-15T19:28:54.869-05:00 level=INFO source=server.go:344 msg=Matched "inference compute"="{Library:CUDA Variant: Compute:8.6 Driver:13.1 Name:CUDA0 VRAM:8.0 GiB}" time=2026-01-15T19:28:54.869-05:00 level=INFO source=ui.go:236 msg=site.serveHTTP http.method=GET http.path=/api/v1/inference-compute http.pattern="GET /api/v1/inference-compute" http.status=200 http.d=12.84ms request_id=1768523334856327700 version=0.14.1 time=2026-01-15T19:28:56.044-05:00 level=INFO source=updater.go:254 msg="beginning update checker" interval=1h0m0s time=2026-01-15T19:28:56.045-05:00 level=DEBUG source=updater.go:100 msg="checking for available update" requestURL="https://ollama.com/api/update?arch=amd64&nonce=vAVM3rq24CUUNKdBtrRFaw&os=windows&ts=1768523336&version=0.14.1" User-Agent="ollama/0.14.1 amd64 Go/go1.24.1 Windows/10.0.26200" time=2026-01-15T19:28:56.266-05:00 level=DEBUG source=updater.go:109 msg="check update response 204 (current version is up to date)" time=2026-01-15T19:29:14.112-05:00 level=WARN source=app.go:322 msg="ollama server not ready, continuing anyway" error="timeout waiting for Ollama server to be ready" time=2026-01-15T19:29:14.348-05:00 level=WARN source=ui.go:136 msg="ollama server not ready, retrying" attempt=2 time=2026-01-15T19:29:20.550-05:00 level=INFO source=ui.go:236 msg=site.serveHTTP http.method=GET http.path=/api/v1/settings http.pattern="GET /api/v1/settings" http.status=200 http.d=0s request_id=1768523360550840600 version=0.14.1 time=2026-01-15T19:29:22.317-05:00 level=INFO source=ui.go:236 msg=site.serveHTTP http.method=GET http.path=/api/v1/chats http.pattern="GET /api/v1/chats" http.status=200 http.d=0s request_id=1768523362317712800 version=0.14.1 time=2026-01-15T19:29:22.318-05:00 level=INFO source=ui.go:236 msg=site.serveHTTP http.method=GET http.path=/api/v1/settings http.pattern="GET /api/v1/settings" http.status=200 http.d=0s request_id=1768523362318383600 version=0.14.1 time=2026-01-15T19:29:36.392-05:00 level=ERROR source=ui.go:148 msg="ollama server not ready after retries" error="timeout waiting for Ollama server to be ready" time=2026-01-15T19:29:38.876-05:00 level=INFO source=ui.go:236 msg=site.serveHTTP http.method=GET http.path=/api/v1/settings http.pattern="GET /api/v1/settings" http.status=200 http.d=0s request_id=1768523378876417000 version=0.14.1 time=2026-01-15T19:29:57.449-05:00 level=WARN source=ui.go:136 msg="ollama server not ready, retrying" attempt=2 time=2026-01-15T19:30:19.488-05:00 level=ERROR source=ui.go:148 msg="ollama server not ready after retries" error="timeout waiting for Ollama server to be ready" time=2026-01-15T19:30:40.541-05:00 level=WARN source=ui.go:136 msg="ollama server not ready, retrying" attempt=2 time=2026-01-15T19:31:02.580-05:00 level=ERROR source=ui.go:148 msg="ollama server not ready after retries" error="timeout waiting for Ollama server to be ready" time=2026-01-15T19:31:23.612-05:00 level=WARN source=ui.go:136 msg="ollama server not ready, retrying" attempt=2 time=2026-01-15T19:31:45.662-05:00 level=ERROR source=ui.go:148 msg="ollama server not ready after retries" error="timeout waiting for Ollama server to be ready" time=2026-01-15T19:32:06.722-05:00 level=WARN source=ui.go:136 msg="ollama server not ready, retrying" attempt=2 time=2026-01-15T19:32:28.769-05:00 level=ERROR source=ui.go:148 msg="ollama server not ready after retries" error="timeout waiting for Ollama server to be ready" time=2026-01-15T19:32:43.067-05:00 level=INFO source=ui.go:236 msg=site.serveHTTP http.method=GET http.path=/api/v1/chats http.pattern="GET /api/v1/chats" http.status=200 http.d=0s request_id=1768523563067849700 version=0.14.1 time=2026-01-15T19:32:43.081-05:00 level=INFO source=ui.go:236 msg=site.serveHTTP http.method=GET http.path=/api/v1/settings http.pattern="GET /api/v1/settings" http.status=200 http.d=13.3685ms request_id=1768523563067849700 version=0.14.1 time=2026-01-15T19:32:49.820-05:00 level=WARN source=ui.go:136 msg="ollama server not ready, retrying" attempt=2 ``` ### OS Windows ### GPU Nvidia ### CPU Intel ### Ollama version 0.14.1
GiteaMirror added the bugwindows labels 2026-04-22 18:35:48 -05:00
GiteaMirror commented 2026-04-22 18:35:52 -05:00
Author
Owner
Copy Link

@kyleweishaupt commented on GitHub (Jan 16, 2026):

Here is from my app.log with OLLAMA_DEBUG=2:

time=2026-01-15T19:59:35.031-05:00 level=INFO source=app_windows.go:270 msg="starting Ollama" app=C:\Users\kylew\AppData\Local\Programs\Ollama version=0.14.1 OS=Windows/10.0.26200
time=2026-01-15T19:59:35.032-05:00 level=INFO source=app.go:237 msg="initialized tools registry" tool_count=0
time=2026-01-15T19:59:35.043-05:00 level=INFO source=app.go:252 msg="starting ollama server"
time=2026-01-15T19:59:35.043-05:00 level=INFO source=app.go:277 msg="starting ui server" port=64727
time=2026-01-15T19:59:35.392-05:00 level=INFO source=ui.go:236 msg=site.serveHTTP http.method=GET http.path=/api/v1/settings http.pattern="GET /api/v1/settings" http.status=200 http.d=0s request_id=1768525175392174900 version=0.14.1
time=2026-01-15T19:59:35.393-05:00 level=INFO source=ui.go:236 msg=site.serveHTTP http.method=GET http.path=/api/v1/chats http.pattern="GET /api/v1/chats" http.status=200 http.d=0s request_id=1768525175393167600 version=0.14.1
time=2026-01-15T19:59:35.503-05:00 level=INFO source=ui.go:236 msg=site.serveHTTP http.method=GET http.path=/api/v1/chats http.pattern="GET /api/v1/chats" http.status=200 http.d=0s request_id=1768525175503469400 version=0.14.1
time=2026-01-15T19:59:35.893-05:00 level=ERROR source=ui.go:1468 msg="failed to get inference compute" error="timeout scanning server log for inference compute details"
time=2026-01-15T19:59:35.893-05:00 level=ERROR source=ui.go:236 msg=site.serveHTTP error="failed to get inference compute: timeout scanning server log for inference compute details" http.method=GET http.path=/api/v1/inference-compute http.pattern="GET /api/v1/inference-compute" http.status=500 http.d=501.3099ms request_id=1768525175392174900 version=0.14.1
time=2026-01-15T19:59:37.410-05:00 level=ERROR source=ui.go:1468 msg="failed to get inference compute" error="timeout scanning server log for inference compute details"
time=2026-01-15T19:59:37.410-05:00 level=ERROR source=ui.go:236 msg=site.serveHTTP error="failed to get inference compute: timeout scanning server log for inference compute details" http.method=GET http.path=/api/v1/inference-compute http.pattern="GET /api/v1/inference-compute" http.status=500 http.d=509.8674ms request_id=1768525176900767000 version=0.14.1
time=2026-01-15T19:59:38.044-05:00 level=INFO source=updater.go:254 msg="beginning update checker" interval=1h0m0s
time=2026-01-15T19:59:39.958-05:00 level=ERROR source=ui.go:1468 msg="failed to get inference compute" error="timeout scanning server log for inference compute details"
time=2026-01-15T19:59:39.958-05:00 level=ERROR source=ui.go:236 msg=site.serveHTTP error="failed to get inference compute: timeout scanning server log for inference compute details" http.method=GET http.path=/api/v1/inference-compute http.pattern="GET /api/v1/inference-compute" http.status=500 http.d=542.7972ms request_id=1768525179416002300 version=0.14.1
time=2026-01-15T19:59:43.963-05:00 level=INFO source=server.go:344 msg=Matched "inference compute"="{Library:CUDA Variant: Compute:8.6 Driver:13.1 Name:CUDA0 VRAM:8.0 GiB}"
time=2026-01-15T19:59:43.963-05:00 level=INFO source=ui.go:236 msg=site.serveHTTP http.method=GET http.path=/api/v1/inference-compute http.pattern="GET /api/v1/inference-compute" http.status=200 http.d=1.0209ms request_id=1768525183962881500 version=0.14.1
time=2026-01-15T19:59:48.949-05:00 level=INFO source=app_windows.go:270 msg="starting Ollama" app=C:\Users\kylew\AppData\Local\Programs\Ollama version=0.14.1 OS=Windows/10.0.26200
time=2026-01-15T19:59:48.951-05:00 level=INFO source=eventloop.go:328 msg="sent focus request to existing instance"
time=2026-01-15T19:59:48.951-05:00 level=INFO source=app_windows.go:79 msg="existing instance found, exiting"
time=2026-01-15T19:59:56.100-05:00 level=WARN source=app.go:322 msg="ollama server not ready, continuing anyway" error="timeout waiting for Ollama server to be ready"
time=2026-01-15T19:59:56.413-05:00 level=WARN source=ui.go:136 msg="ollama server not ready, retrying" attempt=2
time=2026-01-15T20:00:05.802-05:00 level=INFO source=ui.go:236 msg=site.serveHTTP http.method=GET http.path=/api/v1/settings http.pattern="GET /api/v1/settings" http.status=200 http.d=0s request_id=1768525205802786600 version=0.14.1
time=2026-01-15T20:00:05.803-05:00 level=INFO source=ui.go:236 msg=site.serveHTTP http.method=GET http.path=/api/v1/chats http.pattern="GET /api/v1/chats" http.status=200 http.d=0s request_id=1768525205803289100 version=0.14.1
time=2026-01-15T20:00:06.977-05:00 level=INFO source=ui.go:236 msg=site.serveHTTP http.method=GET http.path=/api/v1/settings http.pattern="GET /api/v1/settings" http.status=200 http.d=373.3µs request_id=1768525206977038600 version=0.14.1
time=2026-01-15T20:00:09.352-05:00 level=INFO source=ui.go:236 msg=site.serveHTTP http.method=GET http.path=/api/v1/chats http.pattern="GET /api/v1/chats" http.status=200 http.d=539.6µs request_id=1768525209351680400 version=0.14.1
time=2026-01-15T20:00:09.352-05:00 level=INFO source=ui.go:236 msg=site.serveHTTP http.method=GET http.path=/api/v1/settings http.pattern="GET /api/v1/settings" http.status=200 http.d=515.5µs request_id=1768525209352220000 version=0.14.1
time=2026-01-15T20:00:18.457-05:00 level=ERROR source=ui.go:148 msg="ollama server not ready after retries" error="timeout waiting for Ollama server to be ready"
time=2026-01-15T20:00:32.255-05:00 level=INFO source=ui.go:236 msg=site.serveHTTP http.method=GET http.path=/api/v1/settings http.pattern="GET /api/v1/settings" http.status=200 http.d=0s request_id=1768525232255477100 version=0.14.1
time=2026-01-15T20:00:39.503-05:00 level=WARN source=ui.go:136 msg="ollama server not ready, retrying" attempt=2
time=2026-01-15T20:00:53.868-05:00 level=INFO source=ui.go:236 msg=site.serveHTTP http.method=GET http.path=/api/v1/settings http.pattern="GET /api/v1/settings" http.status=200 http.d=0s request_id=1768525253868462700 version=0.14.1
time=2026-01-15T20:00:55.572-05:00 level=INFO source=ui.go:236 msg=site.serveHTTP http.method=GET http.path=/api/v1/chats http.pattern="GET /api/v1/chats" http.status=200 http.d=0s request_id=1768525255572808700 version=0.14.1
time=2026-01-15T20:00:55.583-05:00 level=INFO source=ui.go:236 msg=site.serveHTTP http.method=GET http.path=/api/v1/settings http.pattern="GET /api/v1/settings" http.status=200 http.d=11.1907ms request_id=1768525255572808700 version=0.14.1

Here is the contents of my server.log:

time=2026-01-15T19:59:36.131-05:00 level=INFO source=routes.go:1614 msg="server config" env="map[CUDA_VISIBLE_DEVICES: GGML_VK_VISIBLE_DEVICES: GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: HTTPS_PROXY: HTTP_PROXY: NO_PROXY: OLLAMA_CONTEXT_LENGTH:4096 OLLAMA_DEBUG:DEBUG-4 OLLAMA_FLASH_ATTENTION:false OLLAMA_GPU_OVERHEAD:0 OLLAMA_HOST:http://0.0.0.0:11434 OLLAMA_KEEP_ALIVE:5m0s OLLAMA_KV_CACHE_TYPE: OLLAMA_LLM_LIBRARY: OLLAMA_LOAD_TIMEOUT:5m0s OLLAMA_MAX_LOADED_MODELS:0 OLLAMA_MAX_QUEUE:512 OLLAMA_MODELS:C:\\Users\\kylew\\.ollama\\models OLLAMA_MULTIUSER_CACHE:false OLLAMA_NEW_ENGINE:false OLLAMA_NOHISTORY:false OLLAMA_NOPRUNE:false OLLAMA_NUM_PARALLEL:1 OLLAMA_ORIGINS:[http://localhost https://localhost http://localhost:* https://localhost:* http://127.0.0.1 https://127.0.0.1 http://127.0.0.1:* https://127.0.0.1:* http://0.0.0.0 https://0.0.0.0 http://0.0.0.0:* https://0.0.0.0:* app://* file://* tauri://* vscode-webview://* vscode-file://*] OLLAMA_REMOTES:[ollama.com] OLLAMA_SCHED_SPREAD:false OLLAMA_VULKAN:false ROCR_VISIBLE_DEVICES:]"
time=2026-01-15T19:59:36.132-05:00 level=INFO source=images.go:499 msg="total blobs: 0"
time=2026-01-15T19:59:36.132-05:00 level=INFO source=images.go:506 msg="total unused blobs removed: 0"
time=2026-01-15T19:59:36.133-05:00 level=INFO source=routes.go:1667 msg="Listening on [::]:11434 (version 0.14.1)"
time=2026-01-15T19:59:36.133-05:00 level=DEBUG source=sched.go:121 msg="starting llm scheduler"
time=2026-01-15T19:59:36.134-05:00 level=INFO source=runner.go:67 msg="discovering available GPUs..."
time=2026-01-15T19:59:36.147-05:00 level=TRACE source=runner.go:440 msg="starting runner for device discovery" libDirs="[C:\\Users\\kylew\\AppData\\Local\\Programs\\Ollama\\lib\\ollama C:\\Users\\kylew\\AppData\\Local\\Programs\\Ollama\\lib\\ollama\\cuda_v12]" extraEnvs=map[]
time=2026-01-15T19:59:36.152-05:00 level=INFO source=server.go:429 msg="starting runner" cmd="C:\\Users\\kylew\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 65131"
time=2026-01-15T19:59:36.152-05:00 level=DEBUG source=server.go:430 msg=subprocess OLLAMA_HOST=0.0.0.0 PATH="C:\\Users\\kylew\\AppData\\Local\\Programs\\Ollama\\lib\\ollama;C:\\Users\\kylew\\AppData\\Local\\Programs\\Ollama\\lib\\ollama\\cuda_v12;C:\\Python314\\Scripts\\;C:\\Python314\\;C:\\Windows\\system32;C:\\Windows;C:\\Windows\\System32\\Wbem;C:\\Windows\\System32\\WindowsPowerShell\\v1.0\\;C:\\Windows\\System32\\OpenSSH\\;C:\\Program Files\\Git\\cmd;C:\\Program Files\\PuTTY\\;C:\\Users\\kylew\\AppData\\Roaming\\npm;C:\\Users\\kylew\\AppData\\Local\\PowerToys\\DSCModules\\;C:\\Users\\kylew\\.local\\bin;;C:\\Users\\kylew\\AppData\\Local\\Programs\\Ollama" OLLAMA_DEBUG=2 OLLAMA_CONTEXT_LENGTH=4096 OLLAMA_MODELS=C:\Users\kylew\.ollama\models OLLAMA_LIBRARY_PATH=C:\Users\kylew\AppData\Local\Programs\Ollama\lib\ollama;C:\Users\kylew\AppData\Local\Programs\Ollama\lib\ollama\cuda_v12
time=2026-01-15T19:59:36.182-05:00 level=INFO source=runner.go:1405 msg="starting ollama engine"
time=2026-01-15T19:59:36.184-05:00 level=INFO source=runner.go:1440 msg="Server listening on 127.0.0.1:65131"
time=2026-01-15T19:59:36.190-05:00 level=DEBUG source=gguf.go:589 msg=general.architecture type=string
time=2026-01-15T19:59:36.191-05:00 level=DEBUG source=gguf.go:589 msg=tokenizer.ggml.model type=string
time=2026-01-15T19:59:36.191-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=general.alignment default=32
time=2026-01-15T19:59:36.196-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=general.alignment default=32
time=2026-01-15T19:59:36.196-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=general.file_type default=0
time=2026-01-15T19:59:36.197-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=general.name default=""
time=2026-01-15T19:59:36.197-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=general.description default=""
time=2026-01-15T19:59:36.197-05:00 level=INFO source=ggml.go:136 msg="" architecture=llama file_type=unknown name="" description="" num_tensors=0 num_key_values=3
time=2026-01-15T19:59:36.197-05:00 level=DEBUG source=ggml.go:94 msg="ggml backend load all from path" path=C:\Users\kylew\AppData\Local\Programs\Ollama\lib\ollama
load_backend: loaded CPU backend from C:\Users\kylew\AppData\Local\Programs\Ollama\lib\ollama\ggml-cpu-alderlake.dll
time=2026-01-15T19:59:36.398-05:00 level=DEBUG source=ggml.go:94 msg="ggml backend load all from path" path=C:\Users\kylew\AppData\Local\Programs\Ollama\lib\ollama\cuda_v12
ggml_cuda_init: GGML_CUDA_FORCE_MMQ:    no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 CUDA devices:
  Device 0: NVIDIA GeForce RTX 3060 Ti, compute capability 8.6, VMM: yes, ID: GPU-2e029dff-70bc-bc67-d675-b378a7fa494a
load_backend: loaded CUDA backend from C:\Users\kylew\AppData\Local\Programs\Ollama\lib\ollama\cuda_v12\ggml-cuda.dll
time=2026-01-15T19:59:38.761-05:00 level=INFO source=ggml.go:104 msg=system CPU.0.SSE3=1 CPU.0.SSSE3=1 CPU.0.AVX=1 CPU.0.AVX_VNNI=1 CPU.0.AVX2=1 CPU.0.F16C=1 CPU.0.FMA=1 CPU.0.BMI2=1 CPU.0.LLAMAFILE=1 CPU.1.LLAMAFILE=1 CUDA.0.ARCHS=500,520,600,610,700,750,800,860,890,900,1200 CUDA.0.USE_GRAPHS=1 CUDA.0.PEER_MAX_BATCH_SIZE=128 compiler=cgo(clang)
time=2026-01-15T19:59:38.762-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=llama.block_count default=0
time=2026-01-15T19:59:38.762-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=llama.pooling_type default=0
time=2026-01-15T19:59:38.763-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=llama.expert_count default=0
time=2026-01-15T19:59:38.763-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=tokenizer.ggml.tokens default="&{size:0 values:[]}"
time=2026-01-15T19:59:38.763-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=tokenizer.ggml.scores default="&{size:0 values:[]}"
time=2026-01-15T19:59:38.763-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=tokenizer.ggml.token_type default="&{size:0 values:[]}"
time=2026-01-15T19:59:38.763-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=tokenizer.ggml.merges default="&{size:0 values:[]}"
time=2026-01-15T19:59:38.763-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=tokenizer.ggml.add_bos_token default=true
time=2026-01-15T19:59:38.763-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=tokenizer.ggml.bos_token_id default=0
time=2026-01-15T19:59:38.763-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=tokenizer.ggml.add_eos_token default=false
time=2026-01-15T19:59:38.763-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=tokenizer.ggml.eos_token_id default=0
time=2026-01-15T19:59:38.763-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=tokenizer.ggml.eos_token_ids default="&{size:0 values:[]}"
time=2026-01-15T19:59:38.763-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=tokenizer.ggml.pre default=""
time=2026-01-15T19:59:38.764-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=llama.block_count default=0
time=2026-01-15T19:59:38.764-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=llama.embedding_length default=0
time=2026-01-15T19:59:38.764-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=llama.attention.head_count default=0
time=2026-01-15T19:59:38.764-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=llama.attention.head_count_kv default=0
time=2026-01-15T19:59:38.764-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=llama.attention.key_length default=0
time=2026-01-15T19:59:38.764-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=llama.rope.dimension_count default=0
time=2026-01-15T19:59:38.764-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=llama.attention.layer_norm_rms_epsilon default=0
time=2026-01-15T19:59:38.764-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=llama.rope.freq_base default=100000
time=2026-01-15T19:59:38.764-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=llama.rope.scaling.factor default=1
time=2026-01-15T19:59:38.764-05:00 level=DEBUG source=runner.go:1380 msg="dummy model load took" duration=2.5753385s
ggml_backend_cuda_device_get_memory device GPU-2e029dff-70bc-bc67-d675-b378a7fa494a utilizing NVML memory reporting free: 7727259648 total: 8589934592
time=2026-01-15T19:59:38.802-05:00 level=DEBUG source=runner.go:1385 msg="gathering device infos took" duration=37.6757ms
time=2026-01-15T19:59:38.803-05:00 level=TRACE source=runner.go:467 msg="runner enumerated devices" OLLAMA_LIBRARY_PATH="[C:\\Users\\kylew\\AppData\\Local\\Programs\\Ollama\\lib\\ollama C:\\Users\\kylew\\AppData\\Local\\Programs\\Ollama\\lib\\ollama\\cuda_v12]" devices="[{DeviceID:{ID:GPU-2e029dff-70bc-bc67-d675-b378a7fa494a Library:CUDA} Name:CUDA0 Description:NVIDIA GeForce RTX 3060 Ti FilterID: Integrated:false PCIID:0000:01:00.0 TotalMemory:8589934592 FreeMemory:7727259648 ComputeMajor:8 ComputeMinor:6 DriverMajor:13 DriverMinor:1 LibraryPath:[C:\\Users\\kylew\\AppData\\Local\\Programs\\Ollama\\lib\\ollama C:\\Users\\kylew\\AppData\\Local\\Programs\\Ollama\\lib\\ollama\\cuda_v12]}]"
time=2026-01-15T19:59:38.803-05:00 level=DEBUG source=runner.go:437 msg="bootstrap discovery took" duration=2.6564672s OLLAMA_LIBRARY_PATH="[C:\\Users\\kylew\\AppData\\Local\\Programs\\Ollama\\lib\\ollama C:\\Users\\kylew\\AppData\\Local\\Programs\\Ollama\\lib\\ollama\\cuda_v12]" extra_envs=map[]
time=2026-01-15T19:59:38.803-05:00 level=TRACE source=runner.go:440 msg="starting runner for device discovery" libDirs="[C:\\Users\\kylew\\AppData\\Local\\Programs\\Ollama\\lib\\ollama C:\\Users\\kylew\\AppData\\Local\\Programs\\Ollama\\lib\\ollama\\cuda_v13]" extraEnvs=map[]
time=2026-01-15T19:59:38.804-05:00 level=INFO source=server.go:429 msg="starting runner" cmd="C:\\Users\\kylew\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 65137"
time=2026-01-15T19:59:38.804-05:00 level=DEBUG source=server.go:430 msg=subprocess OLLAMA_HOST=0.0.0.0 PATH="C:\\Users\\kylew\\AppData\\Local\\Programs\\Ollama\\lib\\ollama;C:\\Users\\kylew\\AppData\\Local\\Programs\\Ollama\\lib\\ollama\\cuda_v13;C:\\Python314\\Scripts\\;C:\\Python314\\;C:\\Windows\\system32;C:\\Windows;C:\\Windows\\System32\\Wbem;C:\\Windows\\System32\\WindowsPowerShell\\v1.0\\;C:\\Windows\\System32\\OpenSSH\\;C:\\Program Files\\Git\\cmd;C:\\Program Files\\PuTTY\\;C:\\Users\\kylew\\AppData\\Roaming\\npm;C:\\Users\\kylew\\AppData\\Local\\PowerToys\\DSCModules\\;C:\\Users\\kylew\\.local\\bin;;C:\\Users\\kylew\\AppData\\Local\\Programs\\Ollama" OLLAMA_DEBUG=2 OLLAMA_CONTEXT_LENGTH=4096 OLLAMA_MODELS=C:\Users\kylew\.ollama\models OLLAMA_LIBRARY_PATH=C:\Users\kylew\AppData\Local\Programs\Ollama\lib\ollama;C:\Users\kylew\AppData\Local\Programs\Ollama\lib\ollama\cuda_v13
time=2026-01-15T19:59:38.829-05:00 level=INFO source=runner.go:1405 msg="starting ollama engine"
time=2026-01-15T19:59:38.830-05:00 level=INFO source=runner.go:1440 msg="Server listening on 127.0.0.1:65137"
time=2026-01-15T19:59:38.837-05:00 level=DEBUG source=gguf.go:589 msg=general.architecture type=string
time=2026-01-15T19:59:38.837-05:00 level=DEBUG source=gguf.go:589 msg=tokenizer.ggml.model type=string
time=2026-01-15T19:59:38.837-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=general.alignment default=32
time=2026-01-15T19:59:38.838-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=general.alignment default=32
time=2026-01-15T19:59:38.838-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=general.file_type default=0
time=2026-01-15T19:59:38.838-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=general.name default=""
time=2026-01-15T19:59:38.838-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=general.description default=""
time=2026-01-15T19:59:38.838-05:00 level=INFO source=ggml.go:136 msg="" architecture=llama file_type=unknown name="" description="" num_tensors=0 num_key_values=3
time=2026-01-15T19:59:38.838-05:00 level=DEBUG source=ggml.go:94 msg="ggml backend load all from path" path=C:\Users\kylew\AppData\Local\Programs\Ollama\lib\ollama
load_backend: loaded CPU backend from C:\Users\kylew\AppData\Local\Programs\Ollama\lib\ollama\ggml-cpu-alderlake.dll
time=2026-01-15T19:59:38.847-05:00 level=DEBUG source=ggml.go:94 msg="ggml backend load all from path" path=C:\Users\kylew\AppData\Local\Programs\Ollama\lib\ollama\cuda_v13
ggml_cuda_init: GGML_CUDA_FORCE_MMQ:    no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 CUDA devices:
  Device 0: NVIDIA GeForce RTX 3060 Ti, compute capability 8.6, VMM: yes, ID: GPU-2e029dff-70bc-bc67-d675-b378a7fa494a
load_backend: loaded CUDA backend from C:\Users\kylew\AppData\Local\Programs\Ollama\lib\ollama\cuda_v13\ggml-cuda.dll
time=2026-01-15T19:59:39.484-05:00 level=INFO source=ggml.go:104 msg=system CPU.0.SSE3=1 CPU.0.SSSE3=1 CPU.0.AVX=1 CPU.0.AVX_VNNI=1 CPU.0.AVX2=1 CPU.0.F16C=1 CPU.0.FMA=1 CPU.0.BMI2=1 CPU.0.LLAMAFILE=1 CPU.1.LLAMAFILE=1 CUDA.0.ARCHS=750,800,860,870,890,900,1000,1030,1100,1200,1210 CUDA.0.USE_GRAPHS=1 CUDA.0.PEER_MAX_BATCH_SIZE=128 compiler=cgo(clang)
time=2026-01-15T19:59:39.484-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=llama.block_count default=0
time=2026-01-15T19:59:39.485-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=llama.pooling_type default=0
time=2026-01-15T19:59:39.485-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=llama.expert_count default=0
time=2026-01-15T19:59:39.485-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=tokenizer.ggml.tokens default="&{size:0 values:[]}"
time=2026-01-15T19:59:39.485-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=tokenizer.ggml.scores default="&{size:0 values:[]}"
time=2026-01-15T19:59:39.485-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=tokenizer.ggml.token_type default="&{size:0 values:[]}"
time=2026-01-15T19:59:39.485-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=tokenizer.ggml.merges default="&{size:0 values:[]}"
time=2026-01-15T19:59:39.485-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=tokenizer.ggml.add_bos_token default=true
time=2026-01-15T19:59:39.485-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=tokenizer.ggml.bos_token_id default=0
time=2026-01-15T19:59:39.485-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=tokenizer.ggml.add_eos_token default=false
time=2026-01-15T19:59:39.485-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=tokenizer.ggml.eos_token_id default=0
time=2026-01-15T19:59:39.485-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=tokenizer.ggml.eos_token_ids default="&{size:0 values:[]}"
time=2026-01-15T19:59:39.485-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=tokenizer.ggml.pre default=""
time=2026-01-15T19:59:39.485-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=llama.block_count default=0
time=2026-01-15T19:59:39.485-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=llama.embedding_length default=0
time=2026-01-15T19:59:39.485-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=llama.attention.head_count default=0
time=2026-01-15T19:59:39.485-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=llama.attention.head_count_kv default=0
time=2026-01-15T19:59:39.485-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=llama.attention.key_length default=0
time=2026-01-15T19:59:39.485-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=llama.rope.dimension_count default=0
time=2026-01-15T19:59:39.485-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=llama.attention.layer_norm_rms_epsilon default=0
time=2026-01-15T19:59:39.485-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=llama.rope.freq_base default=100000
time=2026-01-15T19:59:39.485-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=llama.rope.scaling.factor default=1
time=2026-01-15T19:59:39.485-05:00 level=DEBUG source=runner.go:1380 msg="dummy model load took" duration=648.4647ms
ggml_backend_cuda_device_get_memory device GPU-2e029dff-70bc-bc67-d675-b378a7fa494a utilizing NVML memory reporting free: 7716462592 total: 8589934592
time=2026-01-15T19:59:39.512-05:00 level=DEBUG source=runner.go:1385 msg="gathering device infos took" duration=26.7054ms
time=2026-01-15T19:59:39.512-05:00 level=TRACE source=runner.go:467 msg="runner enumerated devices" OLLAMA_LIBRARY_PATH="[C:\\Users\\kylew\\AppData\\Local\\Programs\\Ollama\\lib\\ollama C:\\Users\\kylew\\AppData\\Local\\Programs\\Ollama\\lib\\ollama\\cuda_v13]" devices="[{DeviceID:{ID:GPU-2e029dff-70bc-bc67-d675-b378a7fa494a Library:CUDA} Name:CUDA0 Description:NVIDIA GeForce RTX 3060 Ti FilterID: Integrated:false PCIID:0000:01:00.0 TotalMemory:8589934592 FreeMemory:7716462592 ComputeMajor:8 ComputeMinor:6 DriverMajor:13 DriverMinor:1 LibraryPath:[C:\\Users\\kylew\\AppData\\Local\\Programs\\Ollama\\lib\\ollama C:\\Users\\kylew\\AppData\\Local\\Programs\\Ollama\\lib\\ollama\\cuda_v13]}]"
time=2026-01-15T19:59:39.512-05:00 level=DEBUG source=runner.go:437 msg="bootstrap discovery took" duration=709.0754ms OLLAMA_LIBRARY_PATH="[C:\\Users\\kylew\\AppData\\Local\\Programs\\Ollama\\lib\\ollama C:\\Users\\kylew\\AppData\\Local\\Programs\\Ollama\\lib\\ollama\\cuda_v13]" extra_envs=map[]
time=2026-01-15T19:59:39.513-05:00 level=TRACE source=runner.go:440 msg="starting runner for device discovery" libDirs="[C:\\Users\\kylew\\AppData\\Local\\Programs\\Ollama\\lib\\ollama C:\\Users\\kylew\\AppData\\Local\\Programs\\Ollama\\lib\\ollama\\rocm]" extraEnvs=map[]
time=2026-01-15T19:59:39.513-05:00 level=INFO source=server.go:429 msg="starting runner" cmd="C:\\Users\\kylew\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 65146"
time=2026-01-15T19:59:39.513-05:00 level=DEBUG source=server.go:430 msg=subprocess OLLAMA_HOST=0.0.0.0 PATH="C:\\Users\\kylew\\AppData\\Local\\Programs\\Ollama\\lib\\ollama;C:\\Users\\kylew\\AppData\\Local\\Programs\\Ollama\\lib\\ollama\\rocm;C:\\Python314\\Scripts\\;C:\\Python314\\;C:\\Windows\\system32;C:\\Windows;C:\\Windows\\System32\\Wbem;C:\\Windows\\System32\\WindowsPowerShell\\v1.0\\;C:\\Windows\\System32\\OpenSSH\\;C:\\Program Files\\Git\\cmd;C:\\Program Files\\PuTTY\\;C:\\Users\\kylew\\AppData\\Roaming\\npm;C:\\Users\\kylew\\AppData\\Local\\PowerToys\\DSCModules\\;C:\\Users\\kylew\\.local\\bin;;C:\\Users\\kylew\\AppData\\Local\\Programs\\Ollama" OLLAMA_DEBUG=2 OLLAMA_CONTEXT_LENGTH=4096 OLLAMA_MODELS=C:\Users\kylew\.ollama\models OLLAMA_LIBRARY_PATH=C:\Users\kylew\AppData\Local\Programs\Ollama\lib\ollama;C:\Users\kylew\AppData\Local\Programs\Ollama\lib\ollama\rocm
time=2026-01-15T19:59:39.540-05:00 level=INFO source=runner.go:1405 msg="starting ollama engine"
time=2026-01-15T19:59:39.541-05:00 level=INFO source=runner.go:1440 msg="Server listening on 127.0.0.1:65146"
time=2026-01-15T19:59:39.547-05:00 level=DEBUG source=gguf.go:589 msg=general.architecture type=string
time=2026-01-15T19:59:39.547-05:00 level=DEBUG source=gguf.go:589 msg=tokenizer.ggml.model type=string
time=2026-01-15T19:59:39.548-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=general.alignment default=32
time=2026-01-15T19:59:39.548-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=general.alignment default=32
time=2026-01-15T19:59:39.548-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=general.file_type default=0
time=2026-01-15T19:59:39.548-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=general.name default=""
time=2026-01-15T19:59:39.548-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=general.description default=""
time=2026-01-15T19:59:39.548-05:00 level=INFO source=ggml.go:136 msg="" architecture=llama file_type=unknown name="" description="" num_tensors=0 num_key_values=3
time=2026-01-15T19:59:39.548-05:00 level=DEBUG source=ggml.go:94 msg="ggml backend load all from path" path=C:\Users\kylew\AppData\Local\Programs\Ollama\lib\ollama
load_backend: loaded CPU backend from C:\Users\kylew\AppData\Local\Programs\Ollama\lib\ollama\ggml-cpu-alderlake.dll
time=2026-01-15T19:59:39.558-05:00 level=DEBUG source=ggml.go:94 msg="ggml backend load all from path" path=C:\Users\kylew\AppData\Local\Programs\Ollama\lib\ollama\rocm
ggml_cuda_init: failed to initialize ROCm: no ROCm-capable device is detected
load_backend: loaded ROCm backend from C:\Users\kylew\AppData\Local\Programs\Ollama\lib\ollama\rocm\ggml-hip.dll
time=2026-01-15T19:59:39.753-05:00 level=INFO source=ggml.go:104 msg=system CPU.0.SSE3=1 CPU.0.SSSE3=1 CPU.0.AVX=1 CPU.0.AVX_VNNI=1 CPU.0.AVX2=1 CPU.0.F16C=1 CPU.0.FMA=1 CPU.0.BMI2=1 CPU.0.LLAMAFILE=1 CPU.1.LLAMAFILE=1 compiler=cgo(clang)
time=2026-01-15T19:59:39.753-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=llama.block_count default=0
time=2026-01-15T19:59:39.753-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=llama.pooling_type default=0
time=2026-01-15T19:59:39.753-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=llama.expert_count default=0
time=2026-01-15T19:59:39.753-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=tokenizer.ggml.tokens default="&{size:0 values:[]}"
time=2026-01-15T19:59:39.753-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=tokenizer.ggml.scores default="&{size:0 values:[]}"
time=2026-01-15T19:59:39.753-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=tokenizer.ggml.token_type default="&{size:0 values:[]}"
time=2026-01-15T19:59:39.753-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=tokenizer.ggml.merges default="&{size:0 values:[]}"
time=2026-01-15T19:59:39.753-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=tokenizer.ggml.add_bos_token default=true
time=2026-01-15T19:59:39.753-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=tokenizer.ggml.bos_token_id default=0
time=2026-01-15T19:59:39.753-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=tokenizer.ggml.add_eos_token default=false
time=2026-01-15T19:59:39.753-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=tokenizer.ggml.eos_token_id default=0
time=2026-01-15T19:59:39.753-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=tokenizer.ggml.eos_token_ids default="&{size:0 values:[]}"
time=2026-01-15T19:59:39.753-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=tokenizer.ggml.pre default=""
time=2026-01-15T19:59:39.754-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=llama.block_count default=0
time=2026-01-15T19:59:39.754-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=llama.embedding_length default=0
time=2026-01-15T19:59:39.754-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=llama.attention.head_count default=0
time=2026-01-15T19:59:39.754-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=llama.attention.head_count_kv default=0
time=2026-01-15T19:59:39.754-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=llama.attention.key_length default=0
time=2026-01-15T19:59:39.754-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=llama.rope.dimension_count default=0
time=2026-01-15T19:59:39.754-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=llama.attention.layer_norm_rms_epsilon default=0
time=2026-01-15T19:59:39.754-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=llama.rope.freq_base default=100000
time=2026-01-15T19:59:39.754-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=llama.rope.scaling.factor default=1
time=2026-01-15T19:59:39.754-05:00 level=DEBUG source=runner.go:1380 msg="dummy model load took" duration=206.2151ms
time=2026-01-15T19:59:39.754-05:00 level=DEBUG source=runner.go:1385 msg="gathering device infos took" duration=0s
time=2026-01-15T19:59:39.754-05:00 level=TRACE source=runner.go:467 msg="runner enumerated devices" OLLAMA_LIBRARY_PATH="[C:\\Users\\kylew\\AppData\\Local\\Programs\\Ollama\\lib\\ollama C:\\Users\\kylew\\AppData\\Local\\Programs\\Ollama\\lib\\ollama\\rocm]" devices=[]
time=2026-01-15T19:59:39.754-05:00 level=DEBUG source=runner.go:437 msg="bootstrap discovery took" duration=241.4085ms OLLAMA_LIBRARY_PATH="[C:\\Users\\kylew\\AppData\\Local\\Programs\\Ollama\\lib\\ollama C:\\Users\\kylew\\AppData\\Local\\Programs\\Ollama\\lib\\ollama\\rocm]" extra_envs=map[]
time=2026-01-15T19:59:39.754-05:00 level=INFO source=runner.go:106 msg="experimental Vulkan support disabled.  To enable, set OLLAMA_VULKAN=1"
time=2026-01-15T19:59:39.754-05:00 level=DEBUG source=runner.go:124 msg="evaluating which, if any, devices to filter out" initial_count=2
time=2026-01-15T19:59:39.754-05:00 level=DEBUG source=runner.go:146 msg="verifying if device is supported" library=C:\Users\kylew\AppData\Local\Programs\Ollama\lib\ollama\cuda_v12 description="NVIDIA GeForce RTX 3060 Ti" compute=8.6 id=GPU-2e029dff-70bc-bc67-d675-b378a7fa494a pci_id=0000:01:00.0
time=2026-01-15T19:59:39.754-05:00 level=DEBUG source=runner.go:146 msg="verifying if device is supported" library=C:\Users\kylew\AppData\Local\Programs\Ollama\lib\ollama\cuda_v13 description="NVIDIA GeForce RTX 3060 Ti" compute=8.6 id=GPU-2e029dff-70bc-bc67-d675-b378a7fa494a pci_id=0000:01:00.0
time=2026-01-15T19:59:39.754-05:00 level=TRACE source=runner.go:440 msg="starting runner for device discovery" libDirs="[C:\\Users\\kylew\\AppData\\Local\\Programs\\Ollama\\lib\\ollama C:\\Users\\kylew\\AppData\\Local\\Programs\\Ollama\\lib\\ollama\\cuda_v13]" extraEnvs="map[CUDA_VISIBLE_DEVICES:GPU-2e029dff-70bc-bc67-d675-b378a7fa494a GGML_CUDA_INIT:1]"
time=2026-01-15T19:59:39.754-05:00 level=TRACE source=runner.go:440 msg="starting runner for device discovery" libDirs="[C:\\Users\\kylew\\AppData\\Local\\Programs\\Ollama\\lib\\ollama C:\\Users\\kylew\\AppData\\Local\\Programs\\Ollama\\lib\\ollama\\cuda_v12]" extraEnvs="map[CUDA_VISIBLE_DEVICES:GPU-2e029dff-70bc-bc67-d675-b378a7fa494a GGML_CUDA_INIT:1]"
time=2026-01-15T19:59:39.755-05:00 level=INFO source=server.go:429 msg="starting runner" cmd="C:\\Users\\kylew\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 65152"
time=2026-01-15T19:59:39.755-05:00 level=DEBUG source=server.go:430 msg=subprocess OLLAMA_HOST=0.0.0.0 PATH="C:\\Users\\kylew\\AppData\\Local\\Programs\\Ollama\\lib\\ollama;C:\\Users\\kylew\\AppData\\Local\\Programs\\Ollama\\lib\\ollama\\cuda_v13;C:\\Python314\\Scripts\\;C:\\Python314\\;C:\\Windows\\system32;C:\\Windows;C:\\Windows\\System32\\Wbem;C:\\Windows\\System32\\WindowsPowerShell\\v1.0\\;C:\\Windows\\System32\\OpenSSH\\;C:\\Program Files\\Git\\cmd;C:\\Program Files\\PuTTY\\;C:\\Users\\kylew\\AppData\\Roaming\\npm;C:\\Users\\kylew\\AppData\\Local\\PowerToys\\DSCModules\\;C:\\Users\\kylew\\.local\\bin;;C:\\Users\\kylew\\AppData\\Local\\Programs\\Ollama" OLLAMA_DEBUG=2 OLLAMA_CONTEXT_LENGTH=4096 OLLAMA_MODELS=C:\Users\kylew\.ollama\models OLLAMA_LIBRARY_PATH=C:\Users\kylew\AppData\Local\Programs\Ollama\lib\ollama;C:\Users\kylew\AppData\Local\Programs\Ollama\lib\ollama\cuda_v13 CUDA_VISIBLE_DEVICES=GPU-2e029dff-70bc-bc67-d675-b378a7fa494a GGML_CUDA_INIT=1
time=2026-01-15T19:59:39.755-05:00 level=INFO source=server.go:429 msg="starting runner" cmd="C:\\Users\\kylew\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 65153"
time=2026-01-15T19:59:39.755-05:00 level=DEBUG source=server.go:430 msg=subprocess OLLAMA_HOST=0.0.0.0 PATH="C:\\Users\\kylew\\AppData\\Local\\Programs\\Ollama\\lib\\ollama;C:\\Users\\kylew\\AppData\\Local\\Programs\\Ollama\\lib\\ollama\\cuda_v12;C:\\Python314\\Scripts\\;C:\\Python314\\;C:\\Windows\\system32;C:\\Windows;C:\\Windows\\System32\\Wbem;C:\\Windows\\System32\\WindowsPowerShell\\v1.0\\;C:\\Windows\\System32\\OpenSSH\\;C:\\Program Files\\Git\\cmd;C:\\Program Files\\PuTTY\\;C:\\Users\\kylew\\AppData\\Roaming\\npm;C:\\Users\\kylew\\AppData\\Local\\PowerToys\\DSCModules\\;C:\\Users\\kylew\\.local\\bin;;C:\\Users\\kylew\\AppData\\Local\\Programs\\Ollama" OLLAMA_DEBUG=2 OLLAMA_CONTEXT_LENGTH=4096 OLLAMA_MODELS=C:\Users\kylew\.ollama\models OLLAMA_LIBRARY_PATH=C:\Users\kylew\AppData\Local\Programs\Ollama\lib\ollama;C:\Users\kylew\AppData\Local\Programs\Ollama\lib\ollama\cuda_v12 GGML_CUDA_INIT=1 CUDA_VISIBLE_DEVICES=GPU-2e029dff-70bc-bc67-d675-b378a7fa494a
time=2026-01-15T19:59:39.785-05:00 level=INFO source=runner.go:1405 msg="starting ollama engine"
time=2026-01-15T19:59:39.785-05:00 level=INFO source=runner.go:1405 msg="starting ollama engine"
time=2026-01-15T19:59:39.786-05:00 level=INFO source=runner.go:1440 msg="Server listening on 127.0.0.1:65153"
time=2026-01-15T19:59:39.786-05:00 level=INFO source=runner.go:1440 msg="Server listening on 127.0.0.1:65152"
time=2026-01-15T19:59:39.789-05:00 level=DEBUG source=gguf.go:589 msg=general.architecture type=string
time=2026-01-15T19:59:39.789-05:00 level=DEBUG source=gguf.go:589 msg=general.architecture type=string
time=2026-01-15T19:59:39.789-05:00 level=DEBUG source=gguf.go:589 msg=tokenizer.ggml.model type=string
time=2026-01-15T19:59:39.789-05:00 level=DEBUG source=gguf.go:589 msg=tokenizer.ggml.model type=string
time=2026-01-15T19:59:39.789-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=general.alignment default=32
time=2026-01-15T19:59:39.789-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=general.alignment default=32
time=2026-01-15T19:59:39.790-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=general.alignment default=32
time=2026-01-15T19:59:39.790-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=general.file_type default=0
time=2026-01-15T19:59:39.790-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=general.name default=""
time=2026-01-15T19:59:39.790-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=general.description default=""
time=2026-01-15T19:59:39.790-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=general.alignment default=32
time=2026-01-15T19:59:39.790-05:00 level=INFO source=ggml.go:136 msg="" architecture=llama file_type=unknown name="" description="" num_tensors=0 num_key_values=3
time=2026-01-15T19:59:39.790-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=general.file_type default=0
time=2026-01-15T19:59:39.790-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=general.name default=""
time=2026-01-15T19:59:39.790-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=general.description default=""
time=2026-01-15T19:59:39.790-05:00 level=INFO source=ggml.go:136 msg="" architecture=llama file_type=unknown name="" description="" num_tensors=0 num_key_values=3
time=2026-01-15T19:59:39.790-05:00 level=DEBUG source=ggml.go:94 msg="ggml backend load all from path" path=C:\Users\kylew\AppData\Local\Programs\Ollama\lib\ollama
time=2026-01-15T19:59:39.790-05:00 level=DEBUG source=ggml.go:94 msg="ggml backend load all from path" path=C:\Users\kylew\AppData\Local\Programs\Ollama\lib\ollama
load_backend: loaded CPU backend from C:\Users\kylew\AppData\Local\Programs\Ollama\lib\ollama\ggml-cpu-alderlake.dll
time=2026-01-15T19:59:39.800-05:00 level=DEBUG source=ggml.go:94 msg="ggml backend load all from path" path=C:\Users\kylew\AppData\Local\Programs\Ollama\lib\ollama\cuda_v12
load_backend: loaded CPU backend from C:\Users\kylew\AppData\Local\Programs\Ollama\lib\ollama\ggml-cpu-alderlake.dll
time=2026-01-15T19:59:39.800-05:00 level=DEBUG source=ggml.go:94 msg="ggml backend load all from path" path=C:\Users\kylew\AppData\Local\Programs\Ollama\lib\ollama\cuda_v13
ggml_cuda_init: GGML_CUDA_FORCE_MMQ:    no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 CUDA devices:
  Device 0: NVIDIA GeForce RTX 3060 Ti, compute capability 8.6, VMM: yes, ID: GPU-2e029dff-70bc-bc67-d675-b378a7fa494a
load_backend: loaded CUDA backend from C:\Users\kylew\AppData\Local\Programs\Ollama\lib\ollama\cuda_v13\ggml-cuda.dll
time=2026-01-15T19:59:39.869-05:00 level=INFO source=ggml.go:104 msg=system CPU.0.SSE3=1 CPU.0.SSSE3=1 CPU.0.AVX=1 CPU.0.AVX_VNNI=1 CPU.0.AVX2=1 CPU.0.F16C=1 CPU.0.FMA=1 CPU.0.BMI2=1 CPU.0.LLAMAFILE=1 CPU.1.LLAMAFILE=1 CUDA.0.ARCHS=750,800,860,870,890,900,1000,1030,1100,1200,1210 CUDA.0.USE_GRAPHS=1 CUDA.0.PEER_MAX_BATCH_SIZE=128 compiler=cgo(clang)
time=2026-01-15T19:59:39.869-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=llama.block_count default=0
time=2026-01-15T19:59:39.869-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=llama.pooling_type default=0
time=2026-01-15T19:59:39.870-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=llama.expert_count default=0
time=2026-01-15T19:59:39.870-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=tokenizer.ggml.tokens default="&{size:0 values:[]}"
time=2026-01-15T19:59:39.870-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=tokenizer.ggml.scores default="&{size:0 values:[]}"
time=2026-01-15T19:59:39.870-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=tokenizer.ggml.token_type default="&{size:0 values:[]}"
time=2026-01-15T19:59:39.870-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=tokenizer.ggml.merges default="&{size:0 values:[]}"
time=2026-01-15T19:59:39.870-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=tokenizer.ggml.add_bos_token default=true
time=2026-01-15T19:59:39.870-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=tokenizer.ggml.bos_token_id default=0
time=2026-01-15T19:59:39.870-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=tokenizer.ggml.add_eos_token default=false
time=2026-01-15T19:59:39.870-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=tokenizer.ggml.eos_token_id default=0
time=2026-01-15T19:59:39.870-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=tokenizer.ggml.eos_token_ids default="&{size:0 values:[]}"
time=2026-01-15T19:59:39.870-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=tokenizer.ggml.pre default=""
time=2026-01-15T19:59:39.870-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=llama.block_count default=0
time=2026-01-15T19:59:39.870-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=llama.embedding_length default=0
time=2026-01-15T19:59:39.870-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=llama.attention.head_count default=0
time=2026-01-15T19:59:39.870-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=llama.attention.head_count_kv default=0
time=2026-01-15T19:59:39.870-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=llama.attention.key_length default=0
time=2026-01-15T19:59:39.870-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=llama.rope.dimension_count default=0
time=2026-01-15T19:59:39.870-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=llama.attention.layer_norm_rms_epsilon default=0
time=2026-01-15T19:59:39.870-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=llama.rope.freq_base default=100000
time=2026-01-15T19:59:39.870-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=llama.rope.scaling.factor default=1
time=2026-01-15T19:59:39.870-05:00 level=DEBUG source=runner.go:1380 msg="dummy model load took" duration=80.7727ms
ggml_cuda_init: GGML_CUDA_FORCE_MMQ:    no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 CUDA devices:
  Device 0: NVIDIA GeForce RTX 3060 Ti, compute capability 8.6, VMM: yes, ID: GPU-2e029dff-70bc-bc67-d675-b378a7fa494a
load_backend: loaded CUDA backend from C:\Users\kylew\AppData\Local\Programs\Ollama\lib\ollama\cuda_v12\ggml-cuda.dll
time=2026-01-15T19:59:39.880-05:00 level=INFO source=ggml.go:104 msg=system CPU.0.SSE3=1 CPU.0.SSSE3=1 CPU.0.AVX=1 CPU.0.AVX_VNNI=1 CPU.0.AVX2=1 CPU.0.F16C=1 CPU.0.FMA=1 CPU.0.BMI2=1 CPU.0.LLAMAFILE=1 CPU.1.LLAMAFILE=1 CUDA.0.ARCHS=500,520,600,610,700,750,800,860,890,900,1200 CUDA.0.USE_GRAPHS=1 CUDA.0.PEER_MAX_BATCH_SIZE=128 compiler=cgo(clang)
time=2026-01-15T19:59:39.880-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=llama.block_count default=0
time=2026-01-15T19:59:39.880-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=llama.pooling_type default=0
time=2026-01-15T19:59:39.880-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=llama.expert_count default=0
time=2026-01-15T19:59:39.880-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=tokenizer.ggml.tokens default="&{size:0 values:[]}"
time=2026-01-15T19:59:39.880-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=tokenizer.ggml.scores default="&{size:0 values:[]}"
time=2026-01-15T19:59:39.880-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=tokenizer.ggml.token_type default="&{size:0 values:[]}"
time=2026-01-15T19:59:39.880-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=tokenizer.ggml.merges default="&{size:0 values:[]}"
time=2026-01-15T19:59:39.880-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=tokenizer.ggml.add_bos_token default=true
time=2026-01-15T19:59:39.880-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=tokenizer.ggml.bos_token_id default=0
time=2026-01-15T19:59:39.880-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=tokenizer.ggml.add_eos_token default=false
time=2026-01-15T19:59:39.880-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=tokenizer.ggml.eos_token_id default=0
time=2026-01-15T19:59:39.880-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=tokenizer.ggml.eos_token_ids default="&{size:0 values:[]}"
time=2026-01-15T19:59:39.880-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=tokenizer.ggml.pre default=""
time=2026-01-15T19:59:39.880-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=llama.block_count default=0
time=2026-01-15T19:59:39.880-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=llama.embedding_length default=0
time=2026-01-15T19:59:39.880-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=llama.attention.head_count default=0
time=2026-01-15T19:59:39.880-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=llama.attention.head_count_kv default=0
time=2026-01-15T19:59:39.880-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=llama.attention.key_length default=0
time=2026-01-15T19:59:39.880-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=llama.rope.dimension_count default=0
time=2026-01-15T19:59:39.880-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=llama.attention.layer_norm_rms_epsilon default=0
time=2026-01-15T19:59:39.880-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=llama.rope.freq_base default=100000
time=2026-01-15T19:59:39.880-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=llama.rope.scaling.factor default=1
time=2026-01-15T19:59:39.880-05:00 level=DEBUG source=runner.go:1380 msg="dummy model load took" duration=91.613ms
ggml_backend_cuda_device_get_memory device GPU-2e029dff-70bc-bc67-d675-b378a7fa494a utilizing NVML memory reporting free: 7703863296 total: 8589934592
time=2026-01-15T19:59:39.888-05:00 level=DEBUG source=runner.go:1385 msg="gathering device infos took" duration=18.0196ms
time=2026-01-15T19:59:39.888-05:00 level=TRACE source=runner.go:467 msg="runner enumerated devices" OLLAMA_LIBRARY_PATH="[C:\\Users\\kylew\\AppData\\Local\\Programs\\Ollama\\lib\\ollama C:\\Users\\kylew\\AppData\\Local\\Programs\\Ollama\\lib\\ollama\\cuda_v13]" devices="[{DeviceID:{ID:GPU-2e029dff-70bc-bc67-d675-b378a7fa494a Library:CUDA} Name:CUDA0 Description:NVIDIA GeForce RTX 3060 Ti FilterID: Integrated:false PCIID:0000:01:00.0 TotalMemory:8589934592 FreeMemory:7703863296 ComputeMajor:8 ComputeMinor:6 DriverMajor:13 DriverMinor:1 LibraryPath:[C:\\Users\\kylew\\AppData\\Local\\Programs\\Ollama\\lib\\ollama C:\\Users\\kylew\\AppData\\Local\\Programs\\Ollama\\lib\\ollama\\cuda_v13]}]"
time=2026-01-15T19:59:39.888-05:00 level=DEBUG source=runner.go:437 msg="bootstrap discovery took" duration=133.9558ms OLLAMA_LIBRARY_PATH="[C:\\Users\\kylew\\AppData\\Local\\Programs\\Ollama\\lib\\ollama C:\\Users\\kylew\\AppData\\Local\\Programs\\Ollama\\lib\\ollama\\cuda_v13]" extra_envs="map[CUDA_VISIBLE_DEVICES:GPU-2e029dff-70bc-bc67-d675-b378a7fa494a GGML_CUDA_INIT:1]"
ggml_backend_cuda_device_get_memory device GPU-2e029dff-70bc-bc67-d675-b378a7fa494a utilizing NVML memory reporting free: 7703863296 total: 8589934592
time=2026-01-15T19:59:39.903-05:00 level=DEBUG source=runner.go:1385 msg="gathering device infos took" duration=22.6888ms
time=2026-01-15T19:59:39.904-05:00 level=TRACE source=runner.go:467 msg="runner enumerated devices" OLLAMA_LIBRARY_PATH="[C:\\Users\\kylew\\AppData\\Local\\Programs\\Ollama\\lib\\ollama C:\\Users\\kylew\\AppData\\Local\\Programs\\Ollama\\lib\\ollama\\cuda_v12]" devices="[{DeviceID:{ID:GPU-2e029dff-70bc-bc67-d675-b378a7fa494a Library:CUDA} Name:CUDA0 Description:NVIDIA GeForce RTX 3060 Ti FilterID: Integrated:false PCIID:0000:01:00.0 TotalMemory:8589934592 FreeMemory:7703863296 ComputeMajor:8 ComputeMinor:6 DriverMajor:13 DriverMinor:1 LibraryPath:[C:\\Users\\kylew\\AppData\\Local\\Programs\\Ollama\\lib\\ollama C:\\Users\\kylew\\AppData\\Local\\Programs\\Ollama\\lib\\ollama\\cuda_v12]}]"
time=2026-01-15T19:59:39.904-05:00 level=DEBUG source=runner.go:437 msg="bootstrap discovery took" duration=149.4678ms OLLAMA_LIBRARY_PATH="[C:\\Users\\kylew\\AppData\\Local\\Programs\\Ollama\\lib\\ollama C:\\Users\\kylew\\AppData\\Local\\Programs\\Ollama\\lib\\ollama\\cuda_v12]" extra_envs="map[CUDA_VISIBLE_DEVICES:GPU-2e029dff-70bc-bc67-d675-b378a7fa494a GGML_CUDA_INIT:1]"
time=2026-01-15T19:59:39.904-05:00 level=TRACE source=runner.go:174 msg="supported GPU library combinations before filtering" supported="map[CUDA:map[C:\\Users\\kylew\\AppData\\Local\\Programs\\Ollama\\lib\\ollama\\cuda_v12:map[GPU-2e029dff-70bc-bc67-d675-b378a7fa494a:0] C:\\Users\\kylew\\AppData\\Local\\Programs\\Ollama\\lib\\ollama\\cuda_v13:map[GPU-2e029dff-70bc-bc67-d675-b378a7fa494a:1]]]"
time=2026-01-15T19:59:39.904-05:00 level=DEBUG source=runner.go:401 msg="filtering device with overlapping libraries" id=GPU-2e029dff-70bc-bc67-d675-b378a7fa494a library=C:\Users\kylew\AppData\Local\Programs\Ollama\lib\ollama\cuda_v12 delete_index=0 kept_library=C:\Users\kylew\AppData\Local\Programs\Ollama\lib\ollama\cuda_v13
time=2026-01-15T19:59:39.904-05:00 level=TRACE source=runner.go:183 msg="removing unsupported or overlapping GPU combination" libDir=C:\Users\kylew\AppData\Local\Programs\Ollama\lib\ollama\cuda_v12 description="NVIDIA GeForce RTX 3060 Ti" compute=8.6 pci_id=0000:01:00.0
time=2026-01-15T19:59:39.904-05:00 level=DEBUG source=runner.go:40 msg="GPU bootstrap discovery took" duration=3.7713077s
time=2026-01-15T19:59:39.905-05:00 level=INFO source=types.go:42 msg="inference compute" id=GPU-2e029dff-70bc-bc67-d675-b378a7fa494a filter_id="" library=CUDA compute=8.6 name=CUDA0 description="NVIDIA GeForce RTX 3060 Ti" libdirs=ollama,cuda_v13 driver=13.1 pci_id=0000:01:00.0 type=discrete total="8.0 GiB" available="7.2 GiB"
time=2026-01-15T19:59:39.905-05:00 level=INFO source=routes.go:1708 msg="entering low vram mode" "total vram"="8.0 GiB" threshold="20.0 GiB"
<!-- gh-comment-id:3757584629 --> @kyleweishaupt commented on GitHub (Jan 16, 2026): Here is from my app.log with `OLLAMA_DEBUG=2`: ``` time=2026-01-15T19:59:35.031-05:00 level=INFO source=app_windows.go:270 msg="starting Ollama" app=C:\Users\kylew\AppData\Local\Programs\Ollama version=0.14.1 OS=Windows/10.0.26200 time=2026-01-15T19:59:35.032-05:00 level=INFO source=app.go:237 msg="initialized tools registry" tool_count=0 time=2026-01-15T19:59:35.043-05:00 level=INFO source=app.go:252 msg="starting ollama server" time=2026-01-15T19:59:35.043-05:00 level=INFO source=app.go:277 msg="starting ui server" port=64727 time=2026-01-15T19:59:35.392-05:00 level=INFO source=ui.go:236 msg=site.serveHTTP http.method=GET http.path=/api/v1/settings http.pattern="GET /api/v1/settings" http.status=200 http.d=0s request_id=1768525175392174900 version=0.14.1 time=2026-01-15T19:59:35.393-05:00 level=INFO source=ui.go:236 msg=site.serveHTTP http.method=GET http.path=/api/v1/chats http.pattern="GET /api/v1/chats" http.status=200 http.d=0s request_id=1768525175393167600 version=0.14.1 time=2026-01-15T19:59:35.503-05:00 level=INFO source=ui.go:236 msg=site.serveHTTP http.method=GET http.path=/api/v1/chats http.pattern="GET /api/v1/chats" http.status=200 http.d=0s request_id=1768525175503469400 version=0.14.1 time=2026-01-15T19:59:35.893-05:00 level=ERROR source=ui.go:1468 msg="failed to get inference compute" error="timeout scanning server log for inference compute details" time=2026-01-15T19:59:35.893-05:00 level=ERROR source=ui.go:236 msg=site.serveHTTP error="failed to get inference compute: timeout scanning server log for inference compute details" http.method=GET http.path=/api/v1/inference-compute http.pattern="GET /api/v1/inference-compute" http.status=500 http.d=501.3099ms request_id=1768525175392174900 version=0.14.1 time=2026-01-15T19:59:37.410-05:00 level=ERROR source=ui.go:1468 msg="failed to get inference compute" error="timeout scanning server log for inference compute details" time=2026-01-15T19:59:37.410-05:00 level=ERROR source=ui.go:236 msg=site.serveHTTP error="failed to get inference compute: timeout scanning server log for inference compute details" http.method=GET http.path=/api/v1/inference-compute http.pattern="GET /api/v1/inference-compute" http.status=500 http.d=509.8674ms request_id=1768525176900767000 version=0.14.1 time=2026-01-15T19:59:38.044-05:00 level=INFO source=updater.go:254 msg="beginning update checker" interval=1h0m0s time=2026-01-15T19:59:39.958-05:00 level=ERROR source=ui.go:1468 msg="failed to get inference compute" error="timeout scanning server log for inference compute details" time=2026-01-15T19:59:39.958-05:00 level=ERROR source=ui.go:236 msg=site.serveHTTP error="failed to get inference compute: timeout scanning server log for inference compute details" http.method=GET http.path=/api/v1/inference-compute http.pattern="GET /api/v1/inference-compute" http.status=500 http.d=542.7972ms request_id=1768525179416002300 version=0.14.1 time=2026-01-15T19:59:43.963-05:00 level=INFO source=server.go:344 msg=Matched "inference compute"="{Library:CUDA Variant: Compute:8.6 Driver:13.1 Name:CUDA0 VRAM:8.0 GiB}" time=2026-01-15T19:59:43.963-05:00 level=INFO source=ui.go:236 msg=site.serveHTTP http.method=GET http.path=/api/v1/inference-compute http.pattern="GET /api/v1/inference-compute" http.status=200 http.d=1.0209ms request_id=1768525183962881500 version=0.14.1 time=2026-01-15T19:59:48.949-05:00 level=INFO source=app_windows.go:270 msg="starting Ollama" app=C:\Users\kylew\AppData\Local\Programs\Ollama version=0.14.1 OS=Windows/10.0.26200 time=2026-01-15T19:59:48.951-05:00 level=INFO source=eventloop.go:328 msg="sent focus request to existing instance" time=2026-01-15T19:59:48.951-05:00 level=INFO source=app_windows.go:79 msg="existing instance found, exiting" time=2026-01-15T19:59:56.100-05:00 level=WARN source=app.go:322 msg="ollama server not ready, continuing anyway" error="timeout waiting for Ollama server to be ready" time=2026-01-15T19:59:56.413-05:00 level=WARN source=ui.go:136 msg="ollama server not ready, retrying" attempt=2 time=2026-01-15T20:00:05.802-05:00 level=INFO source=ui.go:236 msg=site.serveHTTP http.method=GET http.path=/api/v1/settings http.pattern="GET /api/v1/settings" http.status=200 http.d=0s request_id=1768525205802786600 version=0.14.1 time=2026-01-15T20:00:05.803-05:00 level=INFO source=ui.go:236 msg=site.serveHTTP http.method=GET http.path=/api/v1/chats http.pattern="GET /api/v1/chats" http.status=200 http.d=0s request_id=1768525205803289100 version=0.14.1 time=2026-01-15T20:00:06.977-05:00 level=INFO source=ui.go:236 msg=site.serveHTTP http.method=GET http.path=/api/v1/settings http.pattern="GET /api/v1/settings" http.status=200 http.d=373.3µs request_id=1768525206977038600 version=0.14.1 time=2026-01-15T20:00:09.352-05:00 level=INFO source=ui.go:236 msg=site.serveHTTP http.method=GET http.path=/api/v1/chats http.pattern="GET /api/v1/chats" http.status=200 http.d=539.6µs request_id=1768525209351680400 version=0.14.1 time=2026-01-15T20:00:09.352-05:00 level=INFO source=ui.go:236 msg=site.serveHTTP http.method=GET http.path=/api/v1/settings http.pattern="GET /api/v1/settings" http.status=200 http.d=515.5µs request_id=1768525209352220000 version=0.14.1 time=2026-01-15T20:00:18.457-05:00 level=ERROR source=ui.go:148 msg="ollama server not ready after retries" error="timeout waiting for Ollama server to be ready" time=2026-01-15T20:00:32.255-05:00 level=INFO source=ui.go:236 msg=site.serveHTTP http.method=GET http.path=/api/v1/settings http.pattern="GET /api/v1/settings" http.status=200 http.d=0s request_id=1768525232255477100 version=0.14.1 time=2026-01-15T20:00:39.503-05:00 level=WARN source=ui.go:136 msg="ollama server not ready, retrying" attempt=2 time=2026-01-15T20:00:53.868-05:00 level=INFO source=ui.go:236 msg=site.serveHTTP http.method=GET http.path=/api/v1/settings http.pattern="GET /api/v1/settings" http.status=200 http.d=0s request_id=1768525253868462700 version=0.14.1 time=2026-01-15T20:00:55.572-05:00 level=INFO source=ui.go:236 msg=site.serveHTTP http.method=GET http.path=/api/v1/chats http.pattern="GET /api/v1/chats" http.status=200 http.d=0s request_id=1768525255572808700 version=0.14.1 time=2026-01-15T20:00:55.583-05:00 level=INFO source=ui.go:236 msg=site.serveHTTP http.method=GET http.path=/api/v1/settings http.pattern="GET /api/v1/settings" http.status=200 http.d=11.1907ms request_id=1768525255572808700 version=0.14.1 ``` Here is the contents of my server.log: ``` time=2026-01-15T19:59:36.131-05:00 level=INFO source=routes.go:1614 msg="server config" env="map[CUDA_VISIBLE_DEVICES: GGML_VK_VISIBLE_DEVICES: GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: HTTPS_PROXY: HTTP_PROXY: NO_PROXY: OLLAMA_CONTEXT_LENGTH:4096 OLLAMA_DEBUG:DEBUG-4 OLLAMA_FLASH_ATTENTION:false OLLAMA_GPU_OVERHEAD:0 OLLAMA_HOST:http://0.0.0.0:11434 OLLAMA_KEEP_ALIVE:5m0s OLLAMA_KV_CACHE_TYPE: OLLAMA_LLM_LIBRARY: OLLAMA_LOAD_TIMEOUT:5m0s OLLAMA_MAX_LOADED_MODELS:0 OLLAMA_MAX_QUEUE:512 OLLAMA_MODELS:C:\\Users\\kylew\\.ollama\\models OLLAMA_MULTIUSER_CACHE:false OLLAMA_NEW_ENGINE:false OLLAMA_NOHISTORY:false OLLAMA_NOPRUNE:false OLLAMA_NUM_PARALLEL:1 OLLAMA_ORIGINS:[http://localhost https://localhost http://localhost:* https://localhost:* http://127.0.0.1 https://127.0.0.1 http://127.0.0.1:* https://127.0.0.1:* http://0.0.0.0 https://0.0.0.0 http://0.0.0.0:* https://0.0.0.0:* app://* file://* tauri://* vscode-webview://* vscode-file://*] OLLAMA_REMOTES:[ollama.com] OLLAMA_SCHED_SPREAD:false OLLAMA_VULKAN:false ROCR_VISIBLE_DEVICES:]" time=2026-01-15T19:59:36.132-05:00 level=INFO source=images.go:499 msg="total blobs: 0" time=2026-01-15T19:59:36.132-05:00 level=INFO source=images.go:506 msg="total unused blobs removed: 0" time=2026-01-15T19:59:36.133-05:00 level=INFO source=routes.go:1667 msg="Listening on [::]:11434 (version 0.14.1)" time=2026-01-15T19:59:36.133-05:00 level=DEBUG source=sched.go:121 msg="starting llm scheduler" time=2026-01-15T19:59:36.134-05:00 level=INFO source=runner.go:67 msg="discovering available GPUs..." time=2026-01-15T19:59:36.147-05:00 level=TRACE source=runner.go:440 msg="starting runner for device discovery" libDirs="[C:\\Users\\kylew\\AppData\\Local\\Programs\\Ollama\\lib\\ollama C:\\Users\\kylew\\AppData\\Local\\Programs\\Ollama\\lib\\ollama\\cuda_v12]" extraEnvs=map[] time=2026-01-15T19:59:36.152-05:00 level=INFO source=server.go:429 msg="starting runner" cmd="C:\\Users\\kylew\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 65131" time=2026-01-15T19:59:36.152-05:00 level=DEBUG source=server.go:430 msg=subprocess OLLAMA_HOST=0.0.0.0 PATH="C:\\Users\\kylew\\AppData\\Local\\Programs\\Ollama\\lib\\ollama;C:\\Users\\kylew\\AppData\\Local\\Programs\\Ollama\\lib\\ollama\\cuda_v12;C:\\Python314\\Scripts\\;C:\\Python314\\;C:\\Windows\\system32;C:\\Windows;C:\\Windows\\System32\\Wbem;C:\\Windows\\System32\\WindowsPowerShell\\v1.0\\;C:\\Windows\\System32\\OpenSSH\\;C:\\Program Files\\Git\\cmd;C:\\Program Files\\PuTTY\\;C:\\Users\\kylew\\AppData\\Roaming\\npm;C:\\Users\\kylew\\AppData\\Local\\PowerToys\\DSCModules\\;C:\\Users\\kylew\\.local\\bin;;C:\\Users\\kylew\\AppData\\Local\\Programs\\Ollama" OLLAMA_DEBUG=2 OLLAMA_CONTEXT_LENGTH=4096 OLLAMA_MODELS=C:\Users\kylew\.ollama\models OLLAMA_LIBRARY_PATH=C:\Users\kylew\AppData\Local\Programs\Ollama\lib\ollama;C:\Users\kylew\AppData\Local\Programs\Ollama\lib\ollama\cuda_v12 time=2026-01-15T19:59:36.182-05:00 level=INFO source=runner.go:1405 msg="starting ollama engine" time=2026-01-15T19:59:36.184-05:00 level=INFO source=runner.go:1440 msg="Server listening on 127.0.0.1:65131" time=2026-01-15T19:59:36.190-05:00 level=DEBUG source=gguf.go:589 msg=general.architecture type=string time=2026-01-15T19:59:36.191-05:00 level=DEBUG source=gguf.go:589 msg=tokenizer.ggml.model type=string time=2026-01-15T19:59:36.191-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=general.alignment default=32 time=2026-01-15T19:59:36.196-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=general.alignment default=32 time=2026-01-15T19:59:36.196-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=general.file_type default=0 time=2026-01-15T19:59:36.197-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=general.name default="" time=2026-01-15T19:59:36.197-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=general.description default="" time=2026-01-15T19:59:36.197-05:00 level=INFO source=ggml.go:136 msg="" architecture=llama file_type=unknown name="" description="" num_tensors=0 num_key_values=3 time=2026-01-15T19:59:36.197-05:00 level=DEBUG source=ggml.go:94 msg="ggml backend load all from path" path=C:\Users\kylew\AppData\Local\Programs\Ollama\lib\ollama load_backend: loaded CPU backend from C:\Users\kylew\AppData\Local\Programs\Ollama\lib\ollama\ggml-cpu-alderlake.dll time=2026-01-15T19:59:36.398-05:00 level=DEBUG source=ggml.go:94 msg="ggml backend load all from path" path=C:\Users\kylew\AppData\Local\Programs\Ollama\lib\ollama\cuda_v12 ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no ggml_cuda_init: found 1 CUDA devices: Device 0: NVIDIA GeForce RTX 3060 Ti, compute capability 8.6, VMM: yes, ID: GPU-2e029dff-70bc-bc67-d675-b378a7fa494a load_backend: loaded CUDA backend from C:\Users\kylew\AppData\Local\Programs\Ollama\lib\ollama\cuda_v12\ggml-cuda.dll time=2026-01-15T19:59:38.761-05:00 level=INFO source=ggml.go:104 msg=system CPU.0.SSE3=1 CPU.0.SSSE3=1 CPU.0.AVX=1 CPU.0.AVX_VNNI=1 CPU.0.AVX2=1 CPU.0.F16C=1 CPU.0.FMA=1 CPU.0.BMI2=1 CPU.0.LLAMAFILE=1 CPU.1.LLAMAFILE=1 CUDA.0.ARCHS=500,520,600,610,700,750,800,860,890,900,1200 CUDA.0.USE_GRAPHS=1 CUDA.0.PEER_MAX_BATCH_SIZE=128 compiler=cgo(clang) time=2026-01-15T19:59:38.762-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=llama.block_count default=0 time=2026-01-15T19:59:38.762-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=llama.pooling_type default=0 time=2026-01-15T19:59:38.763-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=llama.expert_count default=0 time=2026-01-15T19:59:38.763-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=tokenizer.ggml.tokens default="&{size:0 values:[]}" time=2026-01-15T19:59:38.763-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=tokenizer.ggml.scores default="&{size:0 values:[]}" time=2026-01-15T19:59:38.763-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=tokenizer.ggml.token_type default="&{size:0 values:[]}" time=2026-01-15T19:59:38.763-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=tokenizer.ggml.merges default="&{size:0 values:[]}" time=2026-01-15T19:59:38.763-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=tokenizer.ggml.add_bos_token default=true time=2026-01-15T19:59:38.763-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=tokenizer.ggml.bos_token_id default=0 time=2026-01-15T19:59:38.763-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=tokenizer.ggml.add_eos_token default=false time=2026-01-15T19:59:38.763-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=tokenizer.ggml.eos_token_id default=0 time=2026-01-15T19:59:38.763-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=tokenizer.ggml.eos_token_ids default="&{size:0 values:[]}" time=2026-01-15T19:59:38.763-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=tokenizer.ggml.pre default="" time=2026-01-15T19:59:38.764-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=llama.block_count default=0 time=2026-01-15T19:59:38.764-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=llama.embedding_length default=0 time=2026-01-15T19:59:38.764-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=llama.attention.head_count default=0 time=2026-01-15T19:59:38.764-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=llama.attention.head_count_kv default=0 time=2026-01-15T19:59:38.764-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=llama.attention.key_length default=0 time=2026-01-15T19:59:38.764-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=llama.rope.dimension_count default=0 time=2026-01-15T19:59:38.764-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=llama.attention.layer_norm_rms_epsilon default=0 time=2026-01-15T19:59:38.764-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=llama.rope.freq_base default=100000 time=2026-01-15T19:59:38.764-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=llama.rope.scaling.factor default=1 time=2026-01-15T19:59:38.764-05:00 level=DEBUG source=runner.go:1380 msg="dummy model load took" duration=2.5753385s ggml_backend_cuda_device_get_memory device GPU-2e029dff-70bc-bc67-d675-b378a7fa494a utilizing NVML memory reporting free: 7727259648 total: 8589934592 time=2026-01-15T19:59:38.802-05:00 level=DEBUG source=runner.go:1385 msg="gathering device infos took" duration=37.6757ms time=2026-01-15T19:59:38.803-05:00 level=TRACE source=runner.go:467 msg="runner enumerated devices" OLLAMA_LIBRARY_PATH="[C:\\Users\\kylew\\AppData\\Local\\Programs\\Ollama\\lib\\ollama C:\\Users\\kylew\\AppData\\Local\\Programs\\Ollama\\lib\\ollama\\cuda_v12]" devices="[{DeviceID:{ID:GPU-2e029dff-70bc-bc67-d675-b378a7fa494a Library:CUDA} Name:CUDA0 Description:NVIDIA GeForce RTX 3060 Ti FilterID: Integrated:false PCIID:0000:01:00.0 TotalMemory:8589934592 FreeMemory:7727259648 ComputeMajor:8 ComputeMinor:6 DriverMajor:13 DriverMinor:1 LibraryPath:[C:\\Users\\kylew\\AppData\\Local\\Programs\\Ollama\\lib\\ollama C:\\Users\\kylew\\AppData\\Local\\Programs\\Ollama\\lib\\ollama\\cuda_v12]}]" time=2026-01-15T19:59:38.803-05:00 level=DEBUG source=runner.go:437 msg="bootstrap discovery took" duration=2.6564672s OLLAMA_LIBRARY_PATH="[C:\\Users\\kylew\\AppData\\Local\\Programs\\Ollama\\lib\\ollama C:\\Users\\kylew\\AppData\\Local\\Programs\\Ollama\\lib\\ollama\\cuda_v12]" extra_envs=map[] time=2026-01-15T19:59:38.803-05:00 level=TRACE source=runner.go:440 msg="starting runner for device discovery" libDirs="[C:\\Users\\kylew\\AppData\\Local\\Programs\\Ollama\\lib\\ollama C:\\Users\\kylew\\AppData\\Local\\Programs\\Ollama\\lib\\ollama\\cuda_v13]" extraEnvs=map[] time=2026-01-15T19:59:38.804-05:00 level=INFO source=server.go:429 msg="starting runner" cmd="C:\\Users\\kylew\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 65137" time=2026-01-15T19:59:38.804-05:00 level=DEBUG source=server.go:430 msg=subprocess OLLAMA_HOST=0.0.0.0 PATH="C:\\Users\\kylew\\AppData\\Local\\Programs\\Ollama\\lib\\ollama;C:\\Users\\kylew\\AppData\\Local\\Programs\\Ollama\\lib\\ollama\\cuda_v13;C:\\Python314\\Scripts\\;C:\\Python314\\;C:\\Windows\\system32;C:\\Windows;C:\\Windows\\System32\\Wbem;C:\\Windows\\System32\\WindowsPowerShell\\v1.0\\;C:\\Windows\\System32\\OpenSSH\\;C:\\Program Files\\Git\\cmd;C:\\Program Files\\PuTTY\\;C:\\Users\\kylew\\AppData\\Roaming\\npm;C:\\Users\\kylew\\AppData\\Local\\PowerToys\\DSCModules\\;C:\\Users\\kylew\\.local\\bin;;C:\\Users\\kylew\\AppData\\Local\\Programs\\Ollama" OLLAMA_DEBUG=2 OLLAMA_CONTEXT_LENGTH=4096 OLLAMA_MODELS=C:\Users\kylew\.ollama\models OLLAMA_LIBRARY_PATH=C:\Users\kylew\AppData\Local\Programs\Ollama\lib\ollama;C:\Users\kylew\AppData\Local\Programs\Ollama\lib\ollama\cuda_v13 time=2026-01-15T19:59:38.829-05:00 level=INFO source=runner.go:1405 msg="starting ollama engine" time=2026-01-15T19:59:38.830-05:00 level=INFO source=runner.go:1440 msg="Server listening on 127.0.0.1:65137" time=2026-01-15T19:59:38.837-05:00 level=DEBUG source=gguf.go:589 msg=general.architecture type=string time=2026-01-15T19:59:38.837-05:00 level=DEBUG source=gguf.go:589 msg=tokenizer.ggml.model type=string time=2026-01-15T19:59:38.837-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=general.alignment default=32 time=2026-01-15T19:59:38.838-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=general.alignment default=32 time=2026-01-15T19:59:38.838-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=general.file_type default=0 time=2026-01-15T19:59:38.838-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=general.name default="" time=2026-01-15T19:59:38.838-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=general.description default="" time=2026-01-15T19:59:38.838-05:00 level=INFO source=ggml.go:136 msg="" architecture=llama file_type=unknown name="" description="" num_tensors=0 num_key_values=3 time=2026-01-15T19:59:38.838-05:00 level=DEBUG source=ggml.go:94 msg="ggml backend load all from path" path=C:\Users\kylew\AppData\Local\Programs\Ollama\lib\ollama load_backend: loaded CPU backend from C:\Users\kylew\AppData\Local\Programs\Ollama\lib\ollama\ggml-cpu-alderlake.dll time=2026-01-15T19:59:38.847-05:00 level=DEBUG source=ggml.go:94 msg="ggml backend load all from path" path=C:\Users\kylew\AppData\Local\Programs\Ollama\lib\ollama\cuda_v13 ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no ggml_cuda_init: found 1 CUDA devices: Device 0: NVIDIA GeForce RTX 3060 Ti, compute capability 8.6, VMM: yes, ID: GPU-2e029dff-70bc-bc67-d675-b378a7fa494a load_backend: loaded CUDA backend from C:\Users\kylew\AppData\Local\Programs\Ollama\lib\ollama\cuda_v13\ggml-cuda.dll time=2026-01-15T19:59:39.484-05:00 level=INFO source=ggml.go:104 msg=system CPU.0.SSE3=1 CPU.0.SSSE3=1 CPU.0.AVX=1 CPU.0.AVX_VNNI=1 CPU.0.AVX2=1 CPU.0.F16C=1 CPU.0.FMA=1 CPU.0.BMI2=1 CPU.0.LLAMAFILE=1 CPU.1.LLAMAFILE=1 CUDA.0.ARCHS=750,800,860,870,890,900,1000,1030,1100,1200,1210 CUDA.0.USE_GRAPHS=1 CUDA.0.PEER_MAX_BATCH_SIZE=128 compiler=cgo(clang) time=2026-01-15T19:59:39.484-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=llama.block_count default=0 time=2026-01-15T19:59:39.485-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=llama.pooling_type default=0 time=2026-01-15T19:59:39.485-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=llama.expert_count default=0 time=2026-01-15T19:59:39.485-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=tokenizer.ggml.tokens default="&{size:0 values:[]}" time=2026-01-15T19:59:39.485-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=tokenizer.ggml.scores default="&{size:0 values:[]}" time=2026-01-15T19:59:39.485-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=tokenizer.ggml.token_type default="&{size:0 values:[]}" time=2026-01-15T19:59:39.485-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=tokenizer.ggml.merges default="&{size:0 values:[]}" time=2026-01-15T19:59:39.485-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=tokenizer.ggml.add_bos_token default=true time=2026-01-15T19:59:39.485-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=tokenizer.ggml.bos_token_id default=0 time=2026-01-15T19:59:39.485-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=tokenizer.ggml.add_eos_token default=false time=2026-01-15T19:59:39.485-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=tokenizer.ggml.eos_token_id default=0 time=2026-01-15T19:59:39.485-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=tokenizer.ggml.eos_token_ids default="&{size:0 values:[]}" time=2026-01-15T19:59:39.485-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=tokenizer.ggml.pre default="" time=2026-01-15T19:59:39.485-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=llama.block_count default=0 time=2026-01-15T19:59:39.485-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=llama.embedding_length default=0 time=2026-01-15T19:59:39.485-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=llama.attention.head_count default=0 time=2026-01-15T19:59:39.485-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=llama.attention.head_count_kv default=0 time=2026-01-15T19:59:39.485-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=llama.attention.key_length default=0 time=2026-01-15T19:59:39.485-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=llama.rope.dimension_count default=0 time=2026-01-15T19:59:39.485-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=llama.attention.layer_norm_rms_epsilon default=0 time=2026-01-15T19:59:39.485-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=llama.rope.freq_base default=100000 time=2026-01-15T19:59:39.485-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=llama.rope.scaling.factor default=1 time=2026-01-15T19:59:39.485-05:00 level=DEBUG source=runner.go:1380 msg="dummy model load took" duration=648.4647ms ggml_backend_cuda_device_get_memory device GPU-2e029dff-70bc-bc67-d675-b378a7fa494a utilizing NVML memory reporting free: 7716462592 total: 8589934592 time=2026-01-15T19:59:39.512-05:00 level=DEBUG source=runner.go:1385 msg="gathering device infos took" duration=26.7054ms time=2026-01-15T19:59:39.512-05:00 level=TRACE source=runner.go:467 msg="runner enumerated devices" OLLAMA_LIBRARY_PATH="[C:\\Users\\kylew\\AppData\\Local\\Programs\\Ollama\\lib\\ollama C:\\Users\\kylew\\AppData\\Local\\Programs\\Ollama\\lib\\ollama\\cuda_v13]" devices="[{DeviceID:{ID:GPU-2e029dff-70bc-bc67-d675-b378a7fa494a Library:CUDA} Name:CUDA0 Description:NVIDIA GeForce RTX 3060 Ti FilterID: Integrated:false PCIID:0000:01:00.0 TotalMemory:8589934592 FreeMemory:7716462592 ComputeMajor:8 ComputeMinor:6 DriverMajor:13 DriverMinor:1 LibraryPath:[C:\\Users\\kylew\\AppData\\Local\\Programs\\Ollama\\lib\\ollama C:\\Users\\kylew\\AppData\\Local\\Programs\\Ollama\\lib\\ollama\\cuda_v13]}]" time=2026-01-15T19:59:39.512-05:00 level=DEBUG source=runner.go:437 msg="bootstrap discovery took" duration=709.0754ms OLLAMA_LIBRARY_PATH="[C:\\Users\\kylew\\AppData\\Local\\Programs\\Ollama\\lib\\ollama C:\\Users\\kylew\\AppData\\Local\\Programs\\Ollama\\lib\\ollama\\cuda_v13]" extra_envs=map[] time=2026-01-15T19:59:39.513-05:00 level=TRACE source=runner.go:440 msg="starting runner for device discovery" libDirs="[C:\\Users\\kylew\\AppData\\Local\\Programs\\Ollama\\lib\\ollama C:\\Users\\kylew\\AppData\\Local\\Programs\\Ollama\\lib\\ollama\\rocm]" extraEnvs=map[] time=2026-01-15T19:59:39.513-05:00 level=INFO source=server.go:429 msg="starting runner" cmd="C:\\Users\\kylew\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 65146" time=2026-01-15T19:59:39.513-05:00 level=DEBUG source=server.go:430 msg=subprocess OLLAMA_HOST=0.0.0.0 PATH="C:\\Users\\kylew\\AppData\\Local\\Programs\\Ollama\\lib\\ollama;C:\\Users\\kylew\\AppData\\Local\\Programs\\Ollama\\lib\\ollama\\rocm;C:\\Python314\\Scripts\\;C:\\Python314\\;C:\\Windows\\system32;C:\\Windows;C:\\Windows\\System32\\Wbem;C:\\Windows\\System32\\WindowsPowerShell\\v1.0\\;C:\\Windows\\System32\\OpenSSH\\;C:\\Program Files\\Git\\cmd;C:\\Program Files\\PuTTY\\;C:\\Users\\kylew\\AppData\\Roaming\\npm;C:\\Users\\kylew\\AppData\\Local\\PowerToys\\DSCModules\\;C:\\Users\\kylew\\.local\\bin;;C:\\Users\\kylew\\AppData\\Local\\Programs\\Ollama" OLLAMA_DEBUG=2 OLLAMA_CONTEXT_LENGTH=4096 OLLAMA_MODELS=C:\Users\kylew\.ollama\models OLLAMA_LIBRARY_PATH=C:\Users\kylew\AppData\Local\Programs\Ollama\lib\ollama;C:\Users\kylew\AppData\Local\Programs\Ollama\lib\ollama\rocm time=2026-01-15T19:59:39.540-05:00 level=INFO source=runner.go:1405 msg="starting ollama engine" time=2026-01-15T19:59:39.541-05:00 level=INFO source=runner.go:1440 msg="Server listening on 127.0.0.1:65146" time=2026-01-15T19:59:39.547-05:00 level=DEBUG source=gguf.go:589 msg=general.architecture type=string time=2026-01-15T19:59:39.547-05:00 level=DEBUG source=gguf.go:589 msg=tokenizer.ggml.model type=string time=2026-01-15T19:59:39.548-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=general.alignment default=32 time=2026-01-15T19:59:39.548-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=general.alignment default=32 time=2026-01-15T19:59:39.548-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=general.file_type default=0 time=2026-01-15T19:59:39.548-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=general.name default="" time=2026-01-15T19:59:39.548-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=general.description default="" time=2026-01-15T19:59:39.548-05:00 level=INFO source=ggml.go:136 msg="" architecture=llama file_type=unknown name="" description="" num_tensors=0 num_key_values=3 time=2026-01-15T19:59:39.548-05:00 level=DEBUG source=ggml.go:94 msg="ggml backend load all from path" path=C:\Users\kylew\AppData\Local\Programs\Ollama\lib\ollama load_backend: loaded CPU backend from C:\Users\kylew\AppData\Local\Programs\Ollama\lib\ollama\ggml-cpu-alderlake.dll time=2026-01-15T19:59:39.558-05:00 level=DEBUG source=ggml.go:94 msg="ggml backend load all from path" path=C:\Users\kylew\AppData\Local\Programs\Ollama\lib\ollama\rocm ggml_cuda_init: failed to initialize ROCm: no ROCm-capable device is detected load_backend: loaded ROCm backend from C:\Users\kylew\AppData\Local\Programs\Ollama\lib\ollama\rocm\ggml-hip.dll time=2026-01-15T19:59:39.753-05:00 level=INFO source=ggml.go:104 msg=system CPU.0.SSE3=1 CPU.0.SSSE3=1 CPU.0.AVX=1 CPU.0.AVX_VNNI=1 CPU.0.AVX2=1 CPU.0.F16C=1 CPU.0.FMA=1 CPU.0.BMI2=1 CPU.0.LLAMAFILE=1 CPU.1.LLAMAFILE=1 compiler=cgo(clang) time=2026-01-15T19:59:39.753-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=llama.block_count default=0 time=2026-01-15T19:59:39.753-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=llama.pooling_type default=0 time=2026-01-15T19:59:39.753-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=llama.expert_count default=0 time=2026-01-15T19:59:39.753-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=tokenizer.ggml.tokens default="&{size:0 values:[]}" time=2026-01-15T19:59:39.753-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=tokenizer.ggml.scores default="&{size:0 values:[]}" time=2026-01-15T19:59:39.753-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=tokenizer.ggml.token_type default="&{size:0 values:[]}" time=2026-01-15T19:59:39.753-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=tokenizer.ggml.merges default="&{size:0 values:[]}" time=2026-01-15T19:59:39.753-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=tokenizer.ggml.add_bos_token default=true time=2026-01-15T19:59:39.753-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=tokenizer.ggml.bos_token_id default=0 time=2026-01-15T19:59:39.753-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=tokenizer.ggml.add_eos_token default=false time=2026-01-15T19:59:39.753-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=tokenizer.ggml.eos_token_id default=0 time=2026-01-15T19:59:39.753-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=tokenizer.ggml.eos_token_ids default="&{size:0 values:[]}" time=2026-01-15T19:59:39.753-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=tokenizer.ggml.pre default="" time=2026-01-15T19:59:39.754-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=llama.block_count default=0 time=2026-01-15T19:59:39.754-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=llama.embedding_length default=0 time=2026-01-15T19:59:39.754-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=llama.attention.head_count default=0 time=2026-01-15T19:59:39.754-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=llama.attention.head_count_kv default=0 time=2026-01-15T19:59:39.754-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=llama.attention.key_length default=0 time=2026-01-15T19:59:39.754-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=llama.rope.dimension_count default=0 time=2026-01-15T19:59:39.754-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=llama.attention.layer_norm_rms_epsilon default=0 time=2026-01-15T19:59:39.754-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=llama.rope.freq_base default=100000 time=2026-01-15T19:59:39.754-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=llama.rope.scaling.factor default=1 time=2026-01-15T19:59:39.754-05:00 level=DEBUG source=runner.go:1380 msg="dummy model load took" duration=206.2151ms time=2026-01-15T19:59:39.754-05:00 level=DEBUG source=runner.go:1385 msg="gathering device infos took" duration=0s time=2026-01-15T19:59:39.754-05:00 level=TRACE source=runner.go:467 msg="runner enumerated devices" OLLAMA_LIBRARY_PATH="[C:\\Users\\kylew\\AppData\\Local\\Programs\\Ollama\\lib\\ollama C:\\Users\\kylew\\AppData\\Local\\Programs\\Ollama\\lib\\ollama\\rocm]" devices=[] time=2026-01-15T19:59:39.754-05:00 level=DEBUG source=runner.go:437 msg="bootstrap discovery took" duration=241.4085ms OLLAMA_LIBRARY_PATH="[C:\\Users\\kylew\\AppData\\Local\\Programs\\Ollama\\lib\\ollama C:\\Users\\kylew\\AppData\\Local\\Programs\\Ollama\\lib\\ollama\\rocm]" extra_envs=map[] time=2026-01-15T19:59:39.754-05:00 level=INFO source=runner.go:106 msg="experimental Vulkan support disabled. To enable, set OLLAMA_VULKAN=1" time=2026-01-15T19:59:39.754-05:00 level=DEBUG source=runner.go:124 msg="evaluating which, if any, devices to filter out" initial_count=2 time=2026-01-15T19:59:39.754-05:00 level=DEBUG source=runner.go:146 msg="verifying if device is supported" library=C:\Users\kylew\AppData\Local\Programs\Ollama\lib\ollama\cuda_v12 description="NVIDIA GeForce RTX 3060 Ti" compute=8.6 id=GPU-2e029dff-70bc-bc67-d675-b378a7fa494a pci_id=0000:01:00.0 time=2026-01-15T19:59:39.754-05:00 level=DEBUG source=runner.go:146 msg="verifying if device is supported" library=C:\Users\kylew\AppData\Local\Programs\Ollama\lib\ollama\cuda_v13 description="NVIDIA GeForce RTX 3060 Ti" compute=8.6 id=GPU-2e029dff-70bc-bc67-d675-b378a7fa494a pci_id=0000:01:00.0 time=2026-01-15T19:59:39.754-05:00 level=TRACE source=runner.go:440 msg="starting runner for device discovery" libDirs="[C:\\Users\\kylew\\AppData\\Local\\Programs\\Ollama\\lib\\ollama C:\\Users\\kylew\\AppData\\Local\\Programs\\Ollama\\lib\\ollama\\cuda_v13]" extraEnvs="map[CUDA_VISIBLE_DEVICES:GPU-2e029dff-70bc-bc67-d675-b378a7fa494a GGML_CUDA_INIT:1]" time=2026-01-15T19:59:39.754-05:00 level=TRACE source=runner.go:440 msg="starting runner for device discovery" libDirs="[C:\\Users\\kylew\\AppData\\Local\\Programs\\Ollama\\lib\\ollama C:\\Users\\kylew\\AppData\\Local\\Programs\\Ollama\\lib\\ollama\\cuda_v12]" extraEnvs="map[CUDA_VISIBLE_DEVICES:GPU-2e029dff-70bc-bc67-d675-b378a7fa494a GGML_CUDA_INIT:1]" time=2026-01-15T19:59:39.755-05:00 level=INFO source=server.go:429 msg="starting runner" cmd="C:\\Users\\kylew\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 65152" time=2026-01-15T19:59:39.755-05:00 level=DEBUG source=server.go:430 msg=subprocess OLLAMA_HOST=0.0.0.0 PATH="C:\\Users\\kylew\\AppData\\Local\\Programs\\Ollama\\lib\\ollama;C:\\Users\\kylew\\AppData\\Local\\Programs\\Ollama\\lib\\ollama\\cuda_v13;C:\\Python314\\Scripts\\;C:\\Python314\\;C:\\Windows\\system32;C:\\Windows;C:\\Windows\\System32\\Wbem;C:\\Windows\\System32\\WindowsPowerShell\\v1.0\\;C:\\Windows\\System32\\OpenSSH\\;C:\\Program Files\\Git\\cmd;C:\\Program Files\\PuTTY\\;C:\\Users\\kylew\\AppData\\Roaming\\npm;C:\\Users\\kylew\\AppData\\Local\\PowerToys\\DSCModules\\;C:\\Users\\kylew\\.local\\bin;;C:\\Users\\kylew\\AppData\\Local\\Programs\\Ollama" OLLAMA_DEBUG=2 OLLAMA_CONTEXT_LENGTH=4096 OLLAMA_MODELS=C:\Users\kylew\.ollama\models OLLAMA_LIBRARY_PATH=C:\Users\kylew\AppData\Local\Programs\Ollama\lib\ollama;C:\Users\kylew\AppData\Local\Programs\Ollama\lib\ollama\cuda_v13 CUDA_VISIBLE_DEVICES=GPU-2e029dff-70bc-bc67-d675-b378a7fa494a GGML_CUDA_INIT=1 time=2026-01-15T19:59:39.755-05:00 level=INFO source=server.go:429 msg="starting runner" cmd="C:\\Users\\kylew\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 65153" time=2026-01-15T19:59:39.755-05:00 level=DEBUG source=server.go:430 msg=subprocess OLLAMA_HOST=0.0.0.0 PATH="C:\\Users\\kylew\\AppData\\Local\\Programs\\Ollama\\lib\\ollama;C:\\Users\\kylew\\AppData\\Local\\Programs\\Ollama\\lib\\ollama\\cuda_v12;C:\\Python314\\Scripts\\;C:\\Python314\\;C:\\Windows\\system32;C:\\Windows;C:\\Windows\\System32\\Wbem;C:\\Windows\\System32\\WindowsPowerShell\\v1.0\\;C:\\Windows\\System32\\OpenSSH\\;C:\\Program Files\\Git\\cmd;C:\\Program Files\\PuTTY\\;C:\\Users\\kylew\\AppData\\Roaming\\npm;C:\\Users\\kylew\\AppData\\Local\\PowerToys\\DSCModules\\;C:\\Users\\kylew\\.local\\bin;;C:\\Users\\kylew\\AppData\\Local\\Programs\\Ollama" OLLAMA_DEBUG=2 OLLAMA_CONTEXT_LENGTH=4096 OLLAMA_MODELS=C:\Users\kylew\.ollama\models OLLAMA_LIBRARY_PATH=C:\Users\kylew\AppData\Local\Programs\Ollama\lib\ollama;C:\Users\kylew\AppData\Local\Programs\Ollama\lib\ollama\cuda_v12 GGML_CUDA_INIT=1 CUDA_VISIBLE_DEVICES=GPU-2e029dff-70bc-bc67-d675-b378a7fa494a time=2026-01-15T19:59:39.785-05:00 level=INFO source=runner.go:1405 msg="starting ollama engine" time=2026-01-15T19:59:39.785-05:00 level=INFO source=runner.go:1405 msg="starting ollama engine" time=2026-01-15T19:59:39.786-05:00 level=INFO source=runner.go:1440 msg="Server listening on 127.0.0.1:65153" time=2026-01-15T19:59:39.786-05:00 level=INFO source=runner.go:1440 msg="Server listening on 127.0.0.1:65152" time=2026-01-15T19:59:39.789-05:00 level=DEBUG source=gguf.go:589 msg=general.architecture type=string time=2026-01-15T19:59:39.789-05:00 level=DEBUG source=gguf.go:589 msg=general.architecture type=string time=2026-01-15T19:59:39.789-05:00 level=DEBUG source=gguf.go:589 msg=tokenizer.ggml.model type=string time=2026-01-15T19:59:39.789-05:00 level=DEBUG source=gguf.go:589 msg=tokenizer.ggml.model type=string time=2026-01-15T19:59:39.789-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=general.alignment default=32 time=2026-01-15T19:59:39.789-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=general.alignment default=32 time=2026-01-15T19:59:39.790-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=general.alignment default=32 time=2026-01-15T19:59:39.790-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=general.file_type default=0 time=2026-01-15T19:59:39.790-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=general.name default="" time=2026-01-15T19:59:39.790-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=general.description default="" time=2026-01-15T19:59:39.790-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=general.alignment default=32 time=2026-01-15T19:59:39.790-05:00 level=INFO source=ggml.go:136 msg="" architecture=llama file_type=unknown name="" description="" num_tensors=0 num_key_values=3 time=2026-01-15T19:59:39.790-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=general.file_type default=0 time=2026-01-15T19:59:39.790-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=general.name default="" time=2026-01-15T19:59:39.790-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=general.description default="" time=2026-01-15T19:59:39.790-05:00 level=INFO source=ggml.go:136 msg="" architecture=llama file_type=unknown name="" description="" num_tensors=0 num_key_values=3 time=2026-01-15T19:59:39.790-05:00 level=DEBUG source=ggml.go:94 msg="ggml backend load all from path" path=C:\Users\kylew\AppData\Local\Programs\Ollama\lib\ollama time=2026-01-15T19:59:39.790-05:00 level=DEBUG source=ggml.go:94 msg="ggml backend load all from path" path=C:\Users\kylew\AppData\Local\Programs\Ollama\lib\ollama load_backend: loaded CPU backend from C:\Users\kylew\AppData\Local\Programs\Ollama\lib\ollama\ggml-cpu-alderlake.dll time=2026-01-15T19:59:39.800-05:00 level=DEBUG source=ggml.go:94 msg="ggml backend load all from path" path=C:\Users\kylew\AppData\Local\Programs\Ollama\lib\ollama\cuda_v12 load_backend: loaded CPU backend from C:\Users\kylew\AppData\Local\Programs\Ollama\lib\ollama\ggml-cpu-alderlake.dll time=2026-01-15T19:59:39.800-05:00 level=DEBUG source=ggml.go:94 msg="ggml backend load all from path" path=C:\Users\kylew\AppData\Local\Programs\Ollama\lib\ollama\cuda_v13 ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no ggml_cuda_init: found 1 CUDA devices: Device 0: NVIDIA GeForce RTX 3060 Ti, compute capability 8.6, VMM: yes, ID: GPU-2e029dff-70bc-bc67-d675-b378a7fa494a load_backend: loaded CUDA backend from C:\Users\kylew\AppData\Local\Programs\Ollama\lib\ollama\cuda_v13\ggml-cuda.dll time=2026-01-15T19:59:39.869-05:00 level=INFO source=ggml.go:104 msg=system CPU.0.SSE3=1 CPU.0.SSSE3=1 CPU.0.AVX=1 CPU.0.AVX_VNNI=1 CPU.0.AVX2=1 CPU.0.F16C=1 CPU.0.FMA=1 CPU.0.BMI2=1 CPU.0.LLAMAFILE=1 CPU.1.LLAMAFILE=1 CUDA.0.ARCHS=750,800,860,870,890,900,1000,1030,1100,1200,1210 CUDA.0.USE_GRAPHS=1 CUDA.0.PEER_MAX_BATCH_SIZE=128 compiler=cgo(clang) time=2026-01-15T19:59:39.869-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=llama.block_count default=0 time=2026-01-15T19:59:39.869-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=llama.pooling_type default=0 time=2026-01-15T19:59:39.870-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=llama.expert_count default=0 time=2026-01-15T19:59:39.870-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=tokenizer.ggml.tokens default="&{size:0 values:[]}" time=2026-01-15T19:59:39.870-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=tokenizer.ggml.scores default="&{size:0 values:[]}" time=2026-01-15T19:59:39.870-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=tokenizer.ggml.token_type default="&{size:0 values:[]}" time=2026-01-15T19:59:39.870-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=tokenizer.ggml.merges default="&{size:0 values:[]}" time=2026-01-15T19:59:39.870-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=tokenizer.ggml.add_bos_token default=true time=2026-01-15T19:59:39.870-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=tokenizer.ggml.bos_token_id default=0 time=2026-01-15T19:59:39.870-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=tokenizer.ggml.add_eos_token default=false time=2026-01-15T19:59:39.870-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=tokenizer.ggml.eos_token_id default=0 time=2026-01-15T19:59:39.870-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=tokenizer.ggml.eos_token_ids default="&{size:0 values:[]}" time=2026-01-15T19:59:39.870-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=tokenizer.ggml.pre default="" time=2026-01-15T19:59:39.870-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=llama.block_count default=0 time=2026-01-15T19:59:39.870-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=llama.embedding_length default=0 time=2026-01-15T19:59:39.870-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=llama.attention.head_count default=0 time=2026-01-15T19:59:39.870-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=llama.attention.head_count_kv default=0 time=2026-01-15T19:59:39.870-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=llama.attention.key_length default=0 time=2026-01-15T19:59:39.870-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=llama.rope.dimension_count default=0 time=2026-01-15T19:59:39.870-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=llama.attention.layer_norm_rms_epsilon default=0 time=2026-01-15T19:59:39.870-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=llama.rope.freq_base default=100000 time=2026-01-15T19:59:39.870-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=llama.rope.scaling.factor default=1 time=2026-01-15T19:59:39.870-05:00 level=DEBUG source=runner.go:1380 msg="dummy model load took" duration=80.7727ms ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no ggml_cuda_init: found 1 CUDA devices: Device 0: NVIDIA GeForce RTX 3060 Ti, compute capability 8.6, VMM: yes, ID: GPU-2e029dff-70bc-bc67-d675-b378a7fa494a load_backend: loaded CUDA backend from C:\Users\kylew\AppData\Local\Programs\Ollama\lib\ollama\cuda_v12\ggml-cuda.dll time=2026-01-15T19:59:39.880-05:00 level=INFO source=ggml.go:104 msg=system CPU.0.SSE3=1 CPU.0.SSSE3=1 CPU.0.AVX=1 CPU.0.AVX_VNNI=1 CPU.0.AVX2=1 CPU.0.F16C=1 CPU.0.FMA=1 CPU.0.BMI2=1 CPU.0.LLAMAFILE=1 CPU.1.LLAMAFILE=1 CUDA.0.ARCHS=500,520,600,610,700,750,800,860,890,900,1200 CUDA.0.USE_GRAPHS=1 CUDA.0.PEER_MAX_BATCH_SIZE=128 compiler=cgo(clang) time=2026-01-15T19:59:39.880-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=llama.block_count default=0 time=2026-01-15T19:59:39.880-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=llama.pooling_type default=0 time=2026-01-15T19:59:39.880-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=llama.expert_count default=0 time=2026-01-15T19:59:39.880-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=tokenizer.ggml.tokens default="&{size:0 values:[]}" time=2026-01-15T19:59:39.880-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=tokenizer.ggml.scores default="&{size:0 values:[]}" time=2026-01-15T19:59:39.880-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=tokenizer.ggml.token_type default="&{size:0 values:[]}" time=2026-01-15T19:59:39.880-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=tokenizer.ggml.merges default="&{size:0 values:[]}" time=2026-01-15T19:59:39.880-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=tokenizer.ggml.add_bos_token default=true time=2026-01-15T19:59:39.880-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=tokenizer.ggml.bos_token_id default=0 time=2026-01-15T19:59:39.880-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=tokenizer.ggml.add_eos_token default=false time=2026-01-15T19:59:39.880-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=tokenizer.ggml.eos_token_id default=0 time=2026-01-15T19:59:39.880-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=tokenizer.ggml.eos_token_ids default="&{size:0 values:[]}" time=2026-01-15T19:59:39.880-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=tokenizer.ggml.pre default="" time=2026-01-15T19:59:39.880-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=llama.block_count default=0 time=2026-01-15T19:59:39.880-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=llama.embedding_length default=0 time=2026-01-15T19:59:39.880-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=llama.attention.head_count default=0 time=2026-01-15T19:59:39.880-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=llama.attention.head_count_kv default=0 time=2026-01-15T19:59:39.880-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=llama.attention.key_length default=0 time=2026-01-15T19:59:39.880-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=llama.rope.dimension_count default=0 time=2026-01-15T19:59:39.880-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=llama.attention.layer_norm_rms_epsilon default=0 time=2026-01-15T19:59:39.880-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=llama.rope.freq_base default=100000 time=2026-01-15T19:59:39.880-05:00 level=DEBUG source=ggml.go:296 msg="key with type not found" key=llama.rope.scaling.factor default=1 time=2026-01-15T19:59:39.880-05:00 level=DEBUG source=runner.go:1380 msg="dummy model load took" duration=91.613ms ggml_backend_cuda_device_get_memory device GPU-2e029dff-70bc-bc67-d675-b378a7fa494a utilizing NVML memory reporting free: 7703863296 total: 8589934592 time=2026-01-15T19:59:39.888-05:00 level=DEBUG source=runner.go:1385 msg="gathering device infos took" duration=18.0196ms time=2026-01-15T19:59:39.888-05:00 level=TRACE source=runner.go:467 msg="runner enumerated devices" OLLAMA_LIBRARY_PATH="[C:\\Users\\kylew\\AppData\\Local\\Programs\\Ollama\\lib\\ollama C:\\Users\\kylew\\AppData\\Local\\Programs\\Ollama\\lib\\ollama\\cuda_v13]" devices="[{DeviceID:{ID:GPU-2e029dff-70bc-bc67-d675-b378a7fa494a Library:CUDA} Name:CUDA0 Description:NVIDIA GeForce RTX 3060 Ti FilterID: Integrated:false PCIID:0000:01:00.0 TotalMemory:8589934592 FreeMemory:7703863296 ComputeMajor:8 ComputeMinor:6 DriverMajor:13 DriverMinor:1 LibraryPath:[C:\\Users\\kylew\\AppData\\Local\\Programs\\Ollama\\lib\\ollama C:\\Users\\kylew\\AppData\\Local\\Programs\\Ollama\\lib\\ollama\\cuda_v13]}]" time=2026-01-15T19:59:39.888-05:00 level=DEBUG source=runner.go:437 msg="bootstrap discovery took" duration=133.9558ms OLLAMA_LIBRARY_PATH="[C:\\Users\\kylew\\AppData\\Local\\Programs\\Ollama\\lib\\ollama C:\\Users\\kylew\\AppData\\Local\\Programs\\Ollama\\lib\\ollama\\cuda_v13]" extra_envs="map[CUDA_VISIBLE_DEVICES:GPU-2e029dff-70bc-bc67-d675-b378a7fa494a GGML_CUDA_INIT:1]" ggml_backend_cuda_device_get_memory device GPU-2e029dff-70bc-bc67-d675-b378a7fa494a utilizing NVML memory reporting free: 7703863296 total: 8589934592 time=2026-01-15T19:59:39.903-05:00 level=DEBUG source=runner.go:1385 msg="gathering device infos took" duration=22.6888ms time=2026-01-15T19:59:39.904-05:00 level=TRACE source=runner.go:467 msg="runner enumerated devices" OLLAMA_LIBRARY_PATH="[C:\\Users\\kylew\\AppData\\Local\\Programs\\Ollama\\lib\\ollama C:\\Users\\kylew\\AppData\\Local\\Programs\\Ollama\\lib\\ollama\\cuda_v12]" devices="[{DeviceID:{ID:GPU-2e029dff-70bc-bc67-d675-b378a7fa494a Library:CUDA} Name:CUDA0 Description:NVIDIA GeForce RTX 3060 Ti FilterID: Integrated:false PCIID:0000:01:00.0 TotalMemory:8589934592 FreeMemory:7703863296 ComputeMajor:8 ComputeMinor:6 DriverMajor:13 DriverMinor:1 LibraryPath:[C:\\Users\\kylew\\AppData\\Local\\Programs\\Ollama\\lib\\ollama C:\\Users\\kylew\\AppData\\Local\\Programs\\Ollama\\lib\\ollama\\cuda_v12]}]" time=2026-01-15T19:59:39.904-05:00 level=DEBUG source=runner.go:437 msg="bootstrap discovery took" duration=149.4678ms OLLAMA_LIBRARY_PATH="[C:\\Users\\kylew\\AppData\\Local\\Programs\\Ollama\\lib\\ollama C:\\Users\\kylew\\AppData\\Local\\Programs\\Ollama\\lib\\ollama\\cuda_v12]" extra_envs="map[CUDA_VISIBLE_DEVICES:GPU-2e029dff-70bc-bc67-d675-b378a7fa494a GGML_CUDA_INIT:1]" time=2026-01-15T19:59:39.904-05:00 level=TRACE source=runner.go:174 msg="supported GPU library combinations before filtering" supported="map[CUDA:map[C:\\Users\\kylew\\AppData\\Local\\Programs\\Ollama\\lib\\ollama\\cuda_v12:map[GPU-2e029dff-70bc-bc67-d675-b378a7fa494a:0] C:\\Users\\kylew\\AppData\\Local\\Programs\\Ollama\\lib\\ollama\\cuda_v13:map[GPU-2e029dff-70bc-bc67-d675-b378a7fa494a:1]]]" time=2026-01-15T19:59:39.904-05:00 level=DEBUG source=runner.go:401 msg="filtering device with overlapping libraries" id=GPU-2e029dff-70bc-bc67-d675-b378a7fa494a library=C:\Users\kylew\AppData\Local\Programs\Ollama\lib\ollama\cuda_v12 delete_index=0 kept_library=C:\Users\kylew\AppData\Local\Programs\Ollama\lib\ollama\cuda_v13 time=2026-01-15T19:59:39.904-05:00 level=TRACE source=runner.go:183 msg="removing unsupported or overlapping GPU combination" libDir=C:\Users\kylew\AppData\Local\Programs\Ollama\lib\ollama\cuda_v12 description="NVIDIA GeForce RTX 3060 Ti" compute=8.6 pci_id=0000:01:00.0 time=2026-01-15T19:59:39.904-05:00 level=DEBUG source=runner.go:40 msg="GPU bootstrap discovery took" duration=3.7713077s time=2026-01-15T19:59:39.905-05:00 level=INFO source=types.go:42 msg="inference compute" id=GPU-2e029dff-70bc-bc67-d675-b378a7fa494a filter_id="" library=CUDA compute=8.6 name=CUDA0 description="NVIDIA GeForce RTX 3060 Ti" libdirs=ollama,cuda_v13 driver=13.1 pci_id=0000:01:00.0 type=discrete total="8.0 GiB" available="7.2 GiB" time=2026-01-15T19:59:39.905-05:00 level=INFO source=routes.go:1708 msg="entering low vram mode" "total vram"="8.0 GiB" threshold="20.0 GiB" ```
GiteaMirror commented 2026-04-22 18:35:52 -05:00
Author
Owner
Copy Link

@kyleweishaupt commented on GitHub (Jan 16, 2026):

After debugging this, it turns out I had also tried installing Ollama in WSL. The port 11434 was being used by WSL and was not removed as part of uninstalling it. I had to use a command to get the IP Helper service to remove it.

After that and restarting the Host Network Service, I got Ollama to start up.

<!-- gh-comment-id:3758017829 --> @kyleweishaupt commented on GitHub (Jan 16, 2026): After debugging this, it turns out I had also tried installing Ollama in WSL. The port 11434 was being used by WSL and was not removed as part of uninstalling it. I had to use a command to get the IP Helper service to remove it. After that and restarting the Host Network Service, I got Ollama to start up.
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
amd
api
app
bug
build
cli
cloud
compatibility
context-length
create
docker
documentation
embeddings
feature request
feedback wanted
good first issue
gpt-oss
gpu
harmony
help wanted
image
install
intel
js
launch
linux
macos
memory
mlx
model
needs more info
networking
nvidia
ollama.com
performance
pull-request
Mirrored from GitHub Pull Request
 python
question
registry
rendering
thinking
tools
top
vulkan
windows
wsl
No Label bug windows
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
GiteaMirror ninjasurge
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#34765
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?