github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-06 16:11:34 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #11833] Cannot run gpt-oss #33613

New Issue
Closed
opened 2026-04-22 16:28:31 -05:00 by GiteaMirror · 1 comment
GiteaMirror commented 2026-04-22 16:28:31 -05:00
Owner
Copy Link

Originally created by @sinchro1 on GitHub (Aug 9, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/11833

What is the issue?

Cannot run gpt-oss-20b-GGUF:Q2_K. "500 Internal Server Error: unable to load model”. Any other models work well.

Relevant log output

time=2025-08-09T16:03:57.387+02:00 level=DEBUG source=amd_common.go:44 msg="detected ROCM next to ollama executable C:\\Users\\xxx\\AppData\\Local\\Programs\\Ollama\\lib\\ollama\\rocm"
time=2025-08-09T16:03:57.387+02:00 level=DEBUG source=amd_windows.go:73 msg="detected hip devices" count=1
time=2025-08-09T16:03:57.387+02:00 level=DEBUG source=amd_windows.go:93 msg="hip device" id=0 name="AMD Radeon RX 9070" gfx=gfx1201
time=2025-08-09T16:03:57.761+02:00 level=DEBUG source=amd_windows.go:146 msg="amdgpu is supported" gpu=0 gpu_type=gfx1201
time=2025-08-09T16:03:57.761+02:00 level=DEBUG source=amd_windows.go:149 msg="amdgpu memory" gpu=0 total="15.9 GiB"
time=2025-08-09T16:03:57.761+02:00 level=DEBUG source=amd_windows.go:150 msg="amdgpu memory" gpu=0 available="15.8 GiB"
time=2025-08-09T16:03:57.761+02:00 level=INFO source=types.go:130 msg="inference compute" id=0 library=rocm variant="" compute=gfx1201 driver=6.4 name="AMD Radeon RX 9070" total="15.9 GiB" available="15.8 GiB"
time=2025-08-09T16:03:57.761+02:00 level=INFO source=routes.go:1398 msg="entering low vram mode" "total vram"="15.9 GiB" threshold="20.0 GiB"
[GIN] 2025/08/09 - 16:04:01 | 200 |            0s |       127.0.0.1 | HEAD     "/"
time=2025-08-09T16:04:02.045+02:00 level=DEBUG source=ggml.go:208 msg="key with type not found" key=general.alignment default=32
[GIN] 2025/08/09 - 16:04:02 | 200 |     71.8335ms |       127.0.0.1 | POST     "/api/show"
time=2025-08-09T16:04:02.095+02:00 level=DEBUG source=gpu.go:391 msg="updating system memory data" before.total="47.9 GiB" before.free="37.6 GiB" before.free_swap="35.5 GiB" now.total="47.9 GiB" now.free="37.6 GiB" now.free_swap="35.2 GiB"
time=2025-08-09T16:04:02.501+02:00 level=DEBUG source=amd_windows.go:197 msg="updating rocm free memory" gpu=0 name="AMD Radeon RX 9070" before="15.8 GiB" now="15.6 GiB"
time=2025-08-09T16:04:02.502+02:00 level=INFO source=sched.go:187 msg="one or more GPUs detected that are unable to accurately report free memory - disabling default concurrency"
time=2025-08-09T16:04:02.520+02:00 level=DEBUG source=ggml.go:208 msg="key with type not found" key=general.alignment default=32
time=2025-08-09T16:04:02.563+02:00 level=DEBUG source=sched.go:226 msg="loading first model" model=D:\OLLAMA_MODELS\blobs\sha256-129b8e3865517cbba55bbb7d4f0cc2444a014e73a619eafbac247ef6573a19ee
time=2025-08-09T16:04:02.563+02:00 level=DEBUG source=memory.go:111 msg=evaluating library=rocm gpu_count=1 available="[15.6 GiB]"
time=2025-08-09T16:04:02.563+02:00 level=DEBUG source=ggml.go:208 msg="key with type not found" key=gpt-oss.vision.block_count default=0
time=2025-08-09T16:04:02.563+02:00 level=INFO source=sched.go:786 msg="new model will fit in available VRAM in single GPU, loading" model=D:\OLLAMA_MODELS\blobs\sha256-129b8e3865517cbba55bbb7d4f0cc2444a014e73a619eafbac247ef6573a19ee gpu=0 parallel=1 available=16778919936 required="1.8 GiB"
time=2025-08-09T16:04:02.563+02:00 level=DEBUG source=gpu.go:391 msg="updating system memory data" before.total="47.9 GiB" before.free="37.6 GiB" before.free_swap="35.2 GiB" now.total="47.9 GiB" now.free="37.5 GiB" now.free_swap="35.0 GiB"
time=2025-08-09T16:04:02.921+02:00 level=DEBUG source=amd_windows.go:197 msg="updating rocm free memory" gpu=0 name="AMD Radeon RX 9070" before="15.6 GiB" now="15.5 GiB"
time=2025-08-09T16:04:02.922+02:00 level=INFO source=server.go:135 msg="system memory" total="47.9 GiB" free="37.5 GiB" free_swap="35.0 GiB"
time=2025-08-09T16:04:02.922+02:00 level=DEBUG source=memory.go:111 msg=evaluating library=rocm gpu_count=1 available="[15.6 GiB]"
time=2025-08-09T16:04:02.923+02:00 level=DEBUG source=ggml.go:208 msg="key with type not found" key=gpt-oss.vision.block_count default=0
time=2025-08-09T16:04:02.923+02:00 level=INFO source=server.go:175 msg=offload library=rocm layers.requested=-1 layers.model=25 layers.offload=25 layers.split="" memory.available="[15.6 GiB]" memory.gpu_overhead="0 B" memory.required.full="1.8 GiB" memory.required.partial="1.8 GiB" memory.required.kv="192.0 MiB" memory.required.allocations="[1.8 GiB]" memory.weights.total="931.9 MiB" memory.weights.repeating="345.1 MiB" memory.weights.nonrepeating="586.8 MiB" memory.graph.full="256.0 MiB" memory.graph.partial="256.0 MiB"
time=2025-08-09T16:04:02.923+02:00 level=DEBUG source=server.go:291 msg="compatible gpu libraries" compatible=[rocm]
gguf_init_from_file_impl: tensor 'blk.0.ffn_down_exps.weight' has invalid ggml type 39 (NONE)
gguf_init_from_file_impl: failed to read tensor info
llama_model_load: error loading model: llama_model_loader: failed to load model from D:\OLLAMA_MODELS\blobs\sha256-129b8e3865517cbba55bbb7d4f0cc2444a014e73a619eafbac247ef6573a19ee

llama_model_load_from_file_impl: failed to load model
time=2025-08-09T16:04:02.970+02:00 level=INFO source=sched.go:453 msg="NewLlamaServer failed" model=D:\OLLAMA_MODELS\blobs\sha256-129b8e3865517cbba55bbb7d4f0cc2444a014e73a619eafbac247ef6573a19ee error="unable to load model: D:\\OLLAMA_MODELS\\blobs\\sha256-129b8e3865517cbba55bbb7d4f0cc2444a014e73a619eafbac247ef6573a19ee"
[GIN] 2025/08/09 - 16:04:02 | 500 |    922.0023ms |       127.0.0.1 | POST     "/api/generate"

OS

Windows

GPU

AMD

CPU

AMD

Ollama version

0.11.4

Originally created by @sinchro1 on GitHub (Aug 9, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/11833 ### What is the issue? Cannot run gpt-oss-20b-GGUF:Q2_K. "500 Internal Server Error: unable to load model”. Any other models work well. ### Relevant log output ```shell time=2025-08-09T16:03:57.387+02:00 level=DEBUG source=amd_common.go:44 msg="detected ROCM next to ollama executable C:\\Users\\xxx\\AppData\\Local\\Programs\\Ollama\\lib\\ollama\\rocm" time=2025-08-09T16:03:57.387+02:00 level=DEBUG source=amd_windows.go:73 msg="detected hip devices" count=1 time=2025-08-09T16:03:57.387+02:00 level=DEBUG source=amd_windows.go:93 msg="hip device" id=0 name="AMD Radeon RX 9070" gfx=gfx1201 time=2025-08-09T16:03:57.761+02:00 level=DEBUG source=amd_windows.go:146 msg="amdgpu is supported" gpu=0 gpu_type=gfx1201 time=2025-08-09T16:03:57.761+02:00 level=DEBUG source=amd_windows.go:149 msg="amdgpu memory" gpu=0 total="15.9 GiB" time=2025-08-09T16:03:57.761+02:00 level=DEBUG source=amd_windows.go:150 msg="amdgpu memory" gpu=0 available="15.8 GiB" time=2025-08-09T16:03:57.761+02:00 level=INFO source=types.go:130 msg="inference compute" id=0 library=rocm variant="" compute=gfx1201 driver=6.4 name="AMD Radeon RX 9070" total="15.9 GiB" available="15.8 GiB" time=2025-08-09T16:03:57.761+02:00 level=INFO source=routes.go:1398 msg="entering low vram mode" "total vram"="15.9 GiB" threshold="20.0 GiB" [GIN] 2025/08/09 - 16:04:01 | 200 | 0s | 127.0.0.1 | HEAD "/" time=2025-08-09T16:04:02.045+02:00 level=DEBUG source=ggml.go:208 msg="key with type not found" key=general.alignment default=32 [GIN] 2025/08/09 - 16:04:02 | 200 | 71.8335ms | 127.0.0.1 | POST "/api/show" time=2025-08-09T16:04:02.095+02:00 level=DEBUG source=gpu.go:391 msg="updating system memory data" before.total="47.9 GiB" before.free="37.6 GiB" before.free_swap="35.5 GiB" now.total="47.9 GiB" now.free="37.6 GiB" now.free_swap="35.2 GiB" time=2025-08-09T16:04:02.501+02:00 level=DEBUG source=amd_windows.go:197 msg="updating rocm free memory" gpu=0 name="AMD Radeon RX 9070" before="15.8 GiB" now="15.6 GiB" time=2025-08-09T16:04:02.502+02:00 level=INFO source=sched.go:187 msg="one or more GPUs detected that are unable to accurately report free memory - disabling default concurrency" time=2025-08-09T16:04:02.520+02:00 level=DEBUG source=ggml.go:208 msg="key with type not found" key=general.alignment default=32 time=2025-08-09T16:04:02.563+02:00 level=DEBUG source=sched.go:226 msg="loading first model" model=D:\OLLAMA_MODELS\blobs\sha256-129b8e3865517cbba55bbb7d4f0cc2444a014e73a619eafbac247ef6573a19ee time=2025-08-09T16:04:02.563+02:00 level=DEBUG source=memory.go:111 msg=evaluating library=rocm gpu_count=1 available="[15.6 GiB]" time=2025-08-09T16:04:02.563+02:00 level=DEBUG source=ggml.go:208 msg="key with type not found" key=gpt-oss.vision.block_count default=0 time=2025-08-09T16:04:02.563+02:00 level=INFO source=sched.go:786 msg="new model will fit in available VRAM in single GPU, loading" model=D:\OLLAMA_MODELS\blobs\sha256-129b8e3865517cbba55bbb7d4f0cc2444a014e73a619eafbac247ef6573a19ee gpu=0 parallel=1 available=16778919936 required="1.8 GiB" time=2025-08-09T16:04:02.563+02:00 level=DEBUG source=gpu.go:391 msg="updating system memory data" before.total="47.9 GiB" before.free="37.6 GiB" before.free_swap="35.2 GiB" now.total="47.9 GiB" now.free="37.5 GiB" now.free_swap="35.0 GiB" time=2025-08-09T16:04:02.921+02:00 level=DEBUG source=amd_windows.go:197 msg="updating rocm free memory" gpu=0 name="AMD Radeon RX 9070" before="15.6 GiB" now="15.5 GiB" time=2025-08-09T16:04:02.922+02:00 level=INFO source=server.go:135 msg="system memory" total="47.9 GiB" free="37.5 GiB" free_swap="35.0 GiB" time=2025-08-09T16:04:02.922+02:00 level=DEBUG source=memory.go:111 msg=evaluating library=rocm gpu_count=1 available="[15.6 GiB]" time=2025-08-09T16:04:02.923+02:00 level=DEBUG source=ggml.go:208 msg="key with type not found" key=gpt-oss.vision.block_count default=0 time=2025-08-09T16:04:02.923+02:00 level=INFO source=server.go:175 msg=offload library=rocm layers.requested=-1 layers.model=25 layers.offload=25 layers.split="" memory.available="[15.6 GiB]" memory.gpu_overhead="0 B" memory.required.full="1.8 GiB" memory.required.partial="1.8 GiB" memory.required.kv="192.0 MiB" memory.required.allocations="[1.8 GiB]" memory.weights.total="931.9 MiB" memory.weights.repeating="345.1 MiB" memory.weights.nonrepeating="586.8 MiB" memory.graph.full="256.0 MiB" memory.graph.partial="256.0 MiB" time=2025-08-09T16:04:02.923+02:00 level=DEBUG source=server.go:291 msg="compatible gpu libraries" compatible=[rocm] gguf_init_from_file_impl: tensor 'blk.0.ffn_down_exps.weight' has invalid ggml type 39 (NONE) gguf_init_from_file_impl: failed to read tensor info llama_model_load: error loading model: llama_model_loader: failed to load model from D:\OLLAMA_MODELS\blobs\sha256-129b8e3865517cbba55bbb7d4f0cc2444a014e73a619eafbac247ef6573a19ee llama_model_load_from_file_impl: failed to load model time=2025-08-09T16:04:02.970+02:00 level=INFO source=sched.go:453 msg="NewLlamaServer failed" model=D:\OLLAMA_MODELS\blobs\sha256-129b8e3865517cbba55bbb7d4f0cc2444a014e73a619eafbac247ef6573a19ee error="unable to load model: D:\\OLLAMA_MODELS\\blobs\\sha256-129b8e3865517cbba55bbb7d4f0cc2444a014e73a619eafbac247ef6573a19ee" [GIN] 2025/08/09 - 16:04:02 | 500 | 922.0023ms | 127.0.0.1 | POST "/api/generate" ``` ### OS Windows ### GPU AMD ### CPU AMD ### Ollama version 0.11.4
GiteaMirror added the bug label 2026-04-22 16:28:31 -05:00
GiteaMirror commented 2026-04-22 16:28:34 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Aug 9, 2025):

#11714

<!-- gh-comment-id:3171562651 --> @rick-github commented on GitHub (Aug 9, 2025): #11714
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#33613
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?