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 #12388] Ollama windows build regression - Failing to use AMD GPU gfx1030 #33989

New Issue
Closed
opened 2026-04-22 17:12:31 -05:00 by GiteaMirror · 3 comments
GiteaMirror commented 2026-04-22 17:12:31 -05:00
Owner
Copy Link

Originally created by @dsimoes on GitHub (Sep 23, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/12388

What is the issue?

I installed a new version of Ollama 0.12.1 for windows, updating my previous one (don't know the previous version, several months older), and now Ollama fails to run with my GPU - AMD 6800 XT.
Attaching the log below.

Thanks in advance for the help

Relevant log output

time=2025-09-24T00:25:12.801+01:00 level=INFO source=routes.go:1475 msg="server config" env="map[CUDA_VISIBLE_DEVICES: GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: HTTPS_PROXY: HTTP_PROXY: NO_PROXY: OLLAMA_CONTEXT_LENGTH:4096 OLLAMA_DEBUG:INFO OLLAMA_FLASH_ATTENTION:false OLLAMA_GPU_OVERHEAD:0 OLLAMA_HOST:http://0.0.0.0:11434 OLLAMA_INTEL_GPU:false 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\\dsimo\\.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 ROCR_VISIBLE_DEVICES:]"
time=2025-09-24T00:25:12.805+01:00 level=INFO source=images.go:518 msg="total blobs: 34"
time=2025-09-24T00:25:12.807+01:00 level=INFO source=images.go:525 msg="total unused blobs removed: 0"
time=2025-09-24T00:25:12.808+01:00 level=INFO source=routes.go:1528 msg="Listening on [::]:11434 (version 0.12.1)"
time=2025-09-24T00:25:12.808+01:00 level=INFO source=gpu.go:217 msg="looking for compatible GPUs"
time=2025-09-24T00:25:12.808+01:00 level=INFO source=gpu_windows.go:167 msg=packages count=1
time=2025-09-24T00:25:12.808+01:00 level=INFO source=gpu_windows.go:183 msg="efficiency cores detected" maxEfficiencyClass=1
time=2025-09-24T00:25:12.808+01:00 level=INFO source=gpu_windows.go:214 msg="" package=0 cores=16 efficiency=8 threads=24
time=2025-09-24T00:25:13.182+01:00 level=INFO source=types.go:131 msg="inference compute" id=0 library=rocm variant="" compute=gfx1030 driver=6.4 name="AMD Radeon RX 6800 XT" total="16.0 GiB" available="15.8 GiB"
time=2025-09-24T00:25:13.182+01:00 level=INFO source=routes.go:1569 msg="entering low vram mode" "total vram"="16.0 GiB" threshold="20.0 GiB"
[GIN] 2025/09/24 - 00:25:13 | 200 |      2.0352ms |       127.0.0.1 | GET      "/api/tags"
[GIN] 2025/09/24 - 00:25:13 | 200 |     33.4291ms |       127.0.0.1 | POST     "/api/show"
[GIN] 2025/09/24 - 00:26:14 | 200 |            0s |       127.0.0.1 | HEAD     "/"
[GIN] 2025/09/24 - 00:26:14 | 200 |     67.0215ms |       127.0.0.1 | POST     "/api/show"
time=2025-09-24T00:26:14.906+01:00 level=INFO source=sched.go:192 msg="one or more GPUs detected that are unable to accurately report free memory - disabling default concurrency"
time=2025-09-24T00:26:15.347+01:00 level=INFO source=server.go:399 msg="starting runner" cmd="C:\\Users\\dsimo\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --model C:\\Users\\dsimo\\.ollama\\models\\blobs\\sha256-aeda25e63ebd698fab8638ffb778e68bed908b960d39d0becc650fa981609d25 --port 57590"
time=2025-09-24T00:26:15.349+01:00 level=INFO source=server.go:672 msg="loading model" "model layers"=35 requested=-1
time=2025-09-24T00:26:15.373+01:00 level=INFO source=runner.go:1252 msg="starting ollama engine"
time=2025-09-24T00:26:15.374+01:00 level=INFO source=runner.go:1287 msg="Server listening on 127.0.0.1:57590"
time=2025-09-24T00:26:15.687+01:00 level=INFO source=server.go:678 msg="system memory" total="31.8 GiB" free="19.2 GiB" free_swap="22.0 GiB"
time=2025-09-24T00:26:15.687+01:00 level=INFO source=server.go:686 msg="gpu memory" id=0 available="15.3 GiB" free="15.7 GiB" minimum="457.0 MiB" overhead="0 B"
time=2025-09-24T00:26:15.688+01:00 level=INFO source=runner.go:1171 msg=load request="{Operation:fit LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:false KvSize:4096 KvCacheType: NumThreads:8 GPULayers:35[ID:0 Layers:35(0..34)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}"
time=2025-09-24T00:26:15.722+01:00 level=INFO source=ggml.go:131 msg="" architecture=gemma3 file_type=Q4_K_M name="" description="" num_tensors=883 num_key_values=36
ggml_cuda_init: GGML_CUDA_FORCE_MMQ:    no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 ROCm devices:
  Device 0: AMD Radeon RX 6800 XT, gfx1030 (0x1030), VMM: no, Wave Size: 32, ID: 0
load_backend: loaded ROCm backend from C:\Users\dsimo\AppData\Local\Programs\Ollama\lib\ollama\ggml-hip.dll
load_backend: loaded CPU backend from C:\Users\dsimo\AppData\Local\Programs\Ollama\lib\ollama\ggml-cpu-alderlake.dll
ggml_cuda_init: GGML_CUDA_FORCE_MMQ:    no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 ROCm devices:
  Device 0: AMD Radeon RX 6800 XT, gfx1030 (0x1030), VMM: no, Wave Size: 32
load_backend: loaded ROCm backend from C:\Users\dsimo\AppData\Local\Programs\Ollama\lib\ollama\rocm\ggml-hip.dll
Exception 0xc0000005 0x8 0xf 0xf
PC=0xf
signal arrived during external code execution

runtime.cgocall(0x7ff634a02660, 0xc00004b9d0)
	C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/cgocall.go:167 +0x3e fp=0xc00004b9a8 sp=0xc00004b940 pc=0x7ff633ce2dbe
github.com/ollama/ollama/ml/backend/ggml/ggml/src._Cfunc_ggml_backend_reg_get_proc_address(0x23421e1fc00, 0x23421dfdc90)
(... stacktrace)

OS

Windows

GPU

AMD

CPU

Intel

Ollama version

0.12.1

Originally created by @dsimoes on GitHub (Sep 23, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/12388 ### What is the issue? I installed a new version of Ollama 0.12.1 for windows, updating my previous one (don't know the previous version, several months older), and now Ollama fails to run with my GPU - AMD 6800 XT. Attaching the log below. Thanks in advance for the help ### Relevant log output ```shell time=2025-09-24T00:25:12.801+01:00 level=INFO source=routes.go:1475 msg="server config" env="map[CUDA_VISIBLE_DEVICES: GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: HTTPS_PROXY: HTTP_PROXY: NO_PROXY: OLLAMA_CONTEXT_LENGTH:4096 OLLAMA_DEBUG:INFO OLLAMA_FLASH_ATTENTION:false OLLAMA_GPU_OVERHEAD:0 OLLAMA_HOST:http://0.0.0.0:11434 OLLAMA_INTEL_GPU:false 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\\dsimo\\.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 ROCR_VISIBLE_DEVICES:]" time=2025-09-24T00:25:12.805+01:00 level=INFO source=images.go:518 msg="total blobs: 34" time=2025-09-24T00:25:12.807+01:00 level=INFO source=images.go:525 msg="total unused blobs removed: 0" time=2025-09-24T00:25:12.808+01:00 level=INFO source=routes.go:1528 msg="Listening on [::]:11434 (version 0.12.1)" time=2025-09-24T00:25:12.808+01:00 level=INFO source=gpu.go:217 msg="looking for compatible GPUs" time=2025-09-24T00:25:12.808+01:00 level=INFO source=gpu_windows.go:167 msg=packages count=1 time=2025-09-24T00:25:12.808+01:00 level=INFO source=gpu_windows.go:183 msg="efficiency cores detected" maxEfficiencyClass=1 time=2025-09-24T00:25:12.808+01:00 level=INFO source=gpu_windows.go:214 msg="" package=0 cores=16 efficiency=8 threads=24 time=2025-09-24T00:25:13.182+01:00 level=INFO source=types.go:131 msg="inference compute" id=0 library=rocm variant="" compute=gfx1030 driver=6.4 name="AMD Radeon RX 6800 XT" total="16.0 GiB" available="15.8 GiB" time=2025-09-24T00:25:13.182+01:00 level=INFO source=routes.go:1569 msg="entering low vram mode" "total vram"="16.0 GiB" threshold="20.0 GiB" [GIN] 2025/09/24 - 00:25:13 | 200 | 2.0352ms | 127.0.0.1 | GET "/api/tags" [GIN] 2025/09/24 - 00:25:13 | 200 | 33.4291ms | 127.0.0.1 | POST "/api/show" [GIN] 2025/09/24 - 00:26:14 | 200 | 0s | 127.0.0.1 | HEAD "/" [GIN] 2025/09/24 - 00:26:14 | 200 | 67.0215ms | 127.0.0.1 | POST "/api/show" time=2025-09-24T00:26:14.906+01:00 level=INFO source=sched.go:192 msg="one or more GPUs detected that are unable to accurately report free memory - disabling default concurrency" time=2025-09-24T00:26:15.347+01:00 level=INFO source=server.go:399 msg="starting runner" cmd="C:\\Users\\dsimo\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --model C:\\Users\\dsimo\\.ollama\\models\\blobs\\sha256-aeda25e63ebd698fab8638ffb778e68bed908b960d39d0becc650fa981609d25 --port 57590" time=2025-09-24T00:26:15.349+01:00 level=INFO source=server.go:672 msg="loading model" "model layers"=35 requested=-1 time=2025-09-24T00:26:15.373+01:00 level=INFO source=runner.go:1252 msg="starting ollama engine" time=2025-09-24T00:26:15.374+01:00 level=INFO source=runner.go:1287 msg="Server listening on 127.0.0.1:57590" time=2025-09-24T00:26:15.687+01:00 level=INFO source=server.go:678 msg="system memory" total="31.8 GiB" free="19.2 GiB" free_swap="22.0 GiB" time=2025-09-24T00:26:15.687+01:00 level=INFO source=server.go:686 msg="gpu memory" id=0 available="15.3 GiB" free="15.7 GiB" minimum="457.0 MiB" overhead="0 B" time=2025-09-24T00:26:15.688+01:00 level=INFO source=runner.go:1171 msg=load request="{Operation:fit LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:false KvSize:4096 KvCacheType: NumThreads:8 GPULayers:35[ID:0 Layers:35(0..34)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}" time=2025-09-24T00:26:15.722+01:00 level=INFO source=ggml.go:131 msg="" architecture=gemma3 file_type=Q4_K_M name="" description="" num_tensors=883 num_key_values=36 ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no ggml_cuda_init: found 1 ROCm devices: Device 0: AMD Radeon RX 6800 XT, gfx1030 (0x1030), VMM: no, Wave Size: 32, ID: 0 load_backend: loaded ROCm backend from C:\Users\dsimo\AppData\Local\Programs\Ollama\lib\ollama\ggml-hip.dll load_backend: loaded CPU backend from C:\Users\dsimo\AppData\Local\Programs\Ollama\lib\ollama\ggml-cpu-alderlake.dll ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no ggml_cuda_init: found 1 ROCm devices: Device 0: AMD Radeon RX 6800 XT, gfx1030 (0x1030), VMM: no, Wave Size: 32 load_backend: loaded ROCm backend from C:\Users\dsimo\AppData\Local\Programs\Ollama\lib\ollama\rocm\ggml-hip.dll Exception 0xc0000005 0x8 0xf 0xf PC=0xf signal arrived during external code execution runtime.cgocall(0x7ff634a02660, 0xc00004b9d0) C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/cgocall.go:167 +0x3e fp=0xc00004b9a8 sp=0xc00004b940 pc=0x7ff633ce2dbe github.com/ollama/ollama/ml/backend/ggml/ggml/src._Cfunc_ggml_backend_reg_get_proc_address(0x23421e1fc00, 0x23421dfdc90) (... stacktrace) ``` ### OS Windows ### GPU AMD ### CPU Intel ### Ollama version 0.12.1
GiteaMirror added the bug label 2026-04-22 17:12:31 -05:00
GiteaMirror commented 2026-04-22 17:12:33 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Sep 24, 2025):

You have multiple copies of ggml-hip.dll. I suggest stopping ollama, deleting C:\Users\dsimo\AppData\Local\Programs\Ollama\lib\ollama and re-installing.

<!-- gh-comment-id:3326027354 --> @rick-github commented on GitHub (Sep 24, 2025): You have multiple copies of ggml-hip.dll. I suggest stopping ollama, deleting C:\Users\dsimo\AppData\Local\Programs\Ollama\lib\ollama and re-installing.
GiteaMirror commented 2026-04-22 17:12:34 -05:00
Author
Owner
Copy Link

@pdevine commented on GitHub (Sep 24, 2025):

cc @dhiltgen

<!-- gh-comment-id:3326114484 --> @pdevine commented on GitHub (Sep 24, 2025): cc @dhiltgen
GiteaMirror commented 2026-04-22 17:12:34 -05:00
Author
Owner
Copy Link

@dsimoes commented on GitHub (Sep 24, 2025):

Thanks @rick-github I've done like you suggested and It's working now.
Cheers.

<!-- gh-comment-id:3327221119 --> @dsimoes commented on GitHub (Sep 24, 2025): Thanks @rick-github I've done like you suggested and It's working now. Cheers.
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
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#33989
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?