[GH-ISSUE #9096] Ollama cannot run models #5920

Closed
opened 2026-04-12 17:15:36 -05:00 by GiteaMirror · 2 comments
Owner

Originally created by @leecloudvictor on GitHub (Feb 14, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/9096

What is the issue?

Ollama cannot run models

Relevant log output

time=2025-02-14T16:31:09.620+08:00 level=INFO source=server.go:100 msg="system memory" total="15.9 GiB" free="10.9 GiB" free_swap="16.7 GiB"
time=2025-02-14T16:31:09.626+08:00 level=INFO source=memory.go:356 msg="offload to cpu" layers.requested=-1 layers.model=37 layers.offload=0 layers.split="" memory.available="[10.9 GiB]" memory.gpu_overhead="0 B" memory.required.full="2.4 GiB" memory.required.partial="0 B" memory.required.kv="288.0 MiB" memory.required.allocations="[2.4 GiB]" memory.weights.total="1.8 GiB" memory.weights.repeating="1.6 GiB" memory.weights.nonrepeating="243.4 MiB" memory.graph.full="300.8 MiB" memory.graph.partial="544.2 MiB"
time=2025-02-14T16:31:09.640+08:00 level=INFO source=sched.go:428 msg="NewLlamaServer failed" model=D:\users\.ollama\models\blobs\sha256-5ee4f07cdb9beadbbb293e85803c569b01bd37ed059d2715faa7bb405f31caa6 error="unable to evaluate symlinks for executable path: The system cannot find the path specified."
[GIN] 2025/02/14 - 16:31:09 | 404 |     79.3573ms |       127.0.0.1 | POST     "/api/generate"
[GIN] 2025/02/14 - 16:33:58 | 200 |            0s |       127.0.0.1 | HEAD     "/"
[GIN] 2025/02/14 - 16:33:58 | 200 |     58.8864ms |       127.0.0.1 | POST     "/api/show"
time=2025-02-14T16:33:59.006+08:00 level=INFO source=server.go:100 msg="system memory" total="15.9 GiB" free="11.1 GiB" free_swap="16.9 GiB"
time=2025-02-14T16:33:59.007+08:00 level=INFO source=memory.go:356 msg="offload to cpu" layers.requested=-1 layers.model=37 layers.offload=0 layers.split="" memory.available="[11.1 GiB]" memory.gpu_overhead="0 B" memory.required.full="2.4 GiB" memory.required.partial="0 B" memory.required.kv="288.0 MiB" memory.required.allocations="[2.4 GiB]" memory.weights.total="1.8 GiB" memory.weights.repeating="1.6 GiB" memory.weights.nonrepeating="243.4 MiB" memory.graph.full="300.8 MiB" memory.graph.partial="544.2 MiB"
time=2025-02-14T16:33:59.017+08:00 level=INFO source=sched.go:428 msg="NewLlamaServer failed" model=D:\users\.ollama\models\blobs\sha256-5ee4f07cdb9beadbbb293e85803c569b01bd37ed059d2715faa7bb405f31caa6 error="unable to evaluate symlinks for executable path: The system cannot find the path specified."
[GIN] 2025/02/14 - 16:33:59 | 404 |     84.4106ms |       127.0.0.1 | POST     "/api/generate"

OS

Windows

GPU

Other

CPU

Intel

Ollama version

0.5.9,0.5.10

Originally created by @leecloudvictor on GitHub (Feb 14, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/9096 ### What is the issue? Ollama cannot run models ### Relevant log output ```shell time=2025-02-14T16:31:09.620+08:00 level=INFO source=server.go:100 msg="system memory" total="15.9 GiB" free="10.9 GiB" free_swap="16.7 GiB" time=2025-02-14T16:31:09.626+08:00 level=INFO source=memory.go:356 msg="offload to cpu" layers.requested=-1 layers.model=37 layers.offload=0 layers.split="" memory.available="[10.9 GiB]" memory.gpu_overhead="0 B" memory.required.full="2.4 GiB" memory.required.partial="0 B" memory.required.kv="288.0 MiB" memory.required.allocations="[2.4 GiB]" memory.weights.total="1.8 GiB" memory.weights.repeating="1.6 GiB" memory.weights.nonrepeating="243.4 MiB" memory.graph.full="300.8 MiB" memory.graph.partial="544.2 MiB" time=2025-02-14T16:31:09.640+08:00 level=INFO source=sched.go:428 msg="NewLlamaServer failed" model=D:\users\.ollama\models\blobs\sha256-5ee4f07cdb9beadbbb293e85803c569b01bd37ed059d2715faa7bb405f31caa6 error="unable to evaluate symlinks for executable path: The system cannot find the path specified." [GIN] 2025/02/14 - 16:31:09 | 404 | 79.3573ms | 127.0.0.1 | POST "/api/generate" [GIN] 2025/02/14 - 16:33:58 | 200 | 0s | 127.0.0.1 | HEAD "/" [GIN] 2025/02/14 - 16:33:58 | 200 | 58.8864ms | 127.0.0.1 | POST "/api/show" time=2025-02-14T16:33:59.006+08:00 level=INFO source=server.go:100 msg="system memory" total="15.9 GiB" free="11.1 GiB" free_swap="16.9 GiB" time=2025-02-14T16:33:59.007+08:00 level=INFO source=memory.go:356 msg="offload to cpu" layers.requested=-1 layers.model=37 layers.offload=0 layers.split="" memory.available="[11.1 GiB]" memory.gpu_overhead="0 B" memory.required.full="2.4 GiB" memory.required.partial="0 B" memory.required.kv="288.0 MiB" memory.required.allocations="[2.4 GiB]" memory.weights.total="1.8 GiB" memory.weights.repeating="1.6 GiB" memory.weights.nonrepeating="243.4 MiB" memory.graph.full="300.8 MiB" memory.graph.partial="544.2 MiB" time=2025-02-14T16:33:59.017+08:00 level=INFO source=sched.go:428 msg="NewLlamaServer failed" model=D:\users\.ollama\models\blobs\sha256-5ee4f07cdb9beadbbb293e85803c569b01bd37ed059d2715faa7bb405f31caa6 error="unable to evaluate symlinks for executable path: The system cannot find the path specified." [GIN] 2025/02/14 - 16:33:59 | 404 | 84.4106ms | 127.0.0.1 | POST "/api/generate" ``` ### OS Windows ### GPU Other ### CPU Intel ### Ollama version 0.5.9,0.5.10
GiteaMirror added the bug label 2026-04-12 17:15:36 -05:00
Author
Owner

@jmorganca commented on GitHub (Feb 14, 2025):

Hi there, this should be fixed in https://github.com/ollama/ollama/releases/tag/v0.5.11 (in pre-release). Would it be possible to try the OllamaSetup.exe in that release? Sorry this happened.

<!-- gh-comment-id:2658640178 --> @jmorganca commented on GitHub (Feb 14, 2025): Hi there, this should be fixed in https://github.com/ollama/ollama/releases/tag/v0.5.11 (in pre-release). Would it be possible to try the `OllamaSetup.exe` in that release? Sorry this happened.
Author
Owner

@jmorganca commented on GitHub (Feb 14, 2025):

This should be fixed now in 0.5.11, sorry again about the issue!

<!-- gh-comment-id:2659859360 --> @jmorganca commented on GitHub (Feb 14, 2025): This should be fixed now in 0.5.11, sorry again about the issue!
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#5920