github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-22 21:51:37 -05:00
Code Issues 16.9k Packages Projects Releases 122 Wiki Activity

[GH-ISSUE #12944] Qwen3 VL unknown architecture on v0.12.9 #55095

New Issue
Closed
opened 2026-04-29 08:19:43 -05:00 by GiteaMirror · 2 comments
GiteaMirror commented 2026-04-29 08:19:43 -05:00
Owner
Copy Link

Originally created by @logxdx on GitHub (Nov 4, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/12944

What is the issue?

Ollama does not recognize qwen3vl model architecture.
Reinstall didn't work.

Relevant log output

ollama serve
time=2025-11-04T14:39:57.310+05:30 level=INFO source=routes.go:1524 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:INFO OLLAMA_FLASH_ATTENTION:true OLLAMA_GPU_OVERHEAD:0 OLLAMA_HOST:http://127.0.0.1:11434 OLLAMA_INTEL_GPU:false OLLAMA_KEEP_ALIVE:5m0s OLLAMA_KV_CACHE_TYPE:q8 OLLAMA_LLM_LIBRARY: OLLAMA_LOAD_TIMEOUT:5m0s OLLAMA_MAX_LOADED_MODELS:0 OLLAMA_MAX_QUEUE:512 OLLAMA_MODELS:C:\\Users\\iamka\\.ollama\\models OLLAMA_MULTIUSER_CACHE:false OLLAMA_NEW_ENGINE:true 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=2025-11-04T14:39:57.321+05:30 level=INFO source=images.go:522 msg="total blobs: 124"
time=2025-11-04T14:39:57.324+05:30 level=INFO source=images.go:529 msg="total unused blobs removed: 0"
time=2025-11-04T14:39:57.326+05:30 level=INFO source=routes.go:1577 msg="Listening on 127.0.0.1:11434 (version 0.12.9)"
time=2025-11-04T14:39:57.328+05:30 level=INFO source=runner.go:76 msg="discovering available GPUs..."
time=2025-11-04T14:39:57.331+05:30 level=INFO source=server.go:400 msg="starting runner" cmd="C:\\Users\\iamka\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 57888"
time=2025-11-04T14:39:57.482+05:30 level=INFO source=server.go:400 msg="starting runner" cmd="C:\\Users\\iamka\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 57892"
time=2025-11-04T14:39:57.548+05:30 level=INFO source=server.go:400 msg="starting runner" cmd="C:\\Users\\iamka\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 57896"
time=2025-11-04T14:39:57.702+05:30 level=INFO source=server.go:400 msg="starting runner" cmd="C:\\Users\\iamka\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 57900"
time=2025-11-04T14:39:57.702+05:30 level=INFO source=server.go:400 msg="starting runner" cmd="C:\\Users\\iamka\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 57901"
time=2025-11-04T14:39:57.858+05:30 level=INFO source=types.go:42 msg="inference compute" id=GPU-71ff890f-0c96-f116-24c3-62d930353a93 filtered_id="" library=CUDA compute=8.9 name=CUDA0 description="NVIDIA GeForce RTX 4050 Laptop GPU" libdirs=ollama,cuda_v13 driver=13.0 pci_id=0000:01:00.0 type=discrete total="6.0 GiB" available="5.6 GiB"
time=2025-11-04T14:39:57.858+05:30 level=INFO source=routes.go:1618 msg="entering low vram mode" "total vram"="6.0 GiB" threshold="20.0 GiB"
[GIN] 2025/11/04 - 14:40:12 | 200 |            0s |       127.0.0.1 | HEAD     "/"
[GIN] 2025/11/04 - 14:40:12 | 200 |     42.0572ms |       127.0.0.1 | POST     "/api/show"
[GIN] 2025/11/04 - 14:40:12 | 200 |     50.1346ms |       127.0.0.1 | POST     "/api/show"
time=2025-11-04T14:40:12.516+05:30 level=INFO source=server.go:400 msg="starting runner" cmd="C:\\Users\\iamka\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 57911"
time=2025-11-04T14:40:12.655+05:30 level=INFO source=cpu_windows.go:139 msg=packages count=1
time=2025-11-04T14:40:12.655+05:30 level=INFO source=cpu_windows.go:155 msg="efficiency cores detected" maxEfficiencyClass=1
time=2025-11-04T14:40:12.656+05:30 level=INFO source=cpu_windows.go:186 msg="" package=0 cores=8 efficiency=4 threads=12
llama_model_loader: loaded meta data with 42 key-value pairs and 310 tensors from C:\Users\iamka\.ollama\models\blobs\sha256-6f1d3d8fa65d2e30265fead346be6ad87e712523b8b8f92e031b8009853f0a1b (version GGUF V3 (latest))
llama_model_loader: Dumping metadata keys/values. Note: KV overrides do not apply in this output.
llama_model_loader: - kv   0:                       general.architecture str              = qwen3vl
llama_model_loader: - kv   1:                               general.type str              = model
llama_model_loader: - kv   2:                               general.name str              = Qwen3-Vl-2B-Thinking
llama_model_loader: - kv   3:                           general.finetune str              = Thinking
llama_model_loader: - kv   4:                           general.basename str              = Qwen3-Vl-2B-Thinking
llama_model_loader: - kv   5:                       general.quantized_by str              = Unsloth
llama_model_loader: - kv   6:                         general.size_label str              = 2B
llama_model_loader: - kv   7:                            general.license str              = apache-2.0
llama_model_loader: - kv   8:                           general.repo_url str              = https://huggingface.co/unsloth
llama_model_loader: - kv   9:                   general.base_model.count u32              = 1
llama_model_loader: - kv  10:                  general.base_model.0.name str              = Qwen3 VL 2B Thinking
llama_model_loader: - kv  11:          general.base_model.0.organization str              = Qwen
llama_model_loader: - kv  12:              general.base_model.0.repo_url str              = https://huggingface.co/Qwen/Qwen3-VL-...
llama_model_loader: - kv  13:                               general.tags arr[str,2]       = ["unsloth", "image-text-to-text"]
llama_model_loader: - kv  14:                        qwen3vl.block_count u32              = 28
llama_model_loader: - kv  15:                     qwen3vl.context_length u32              = 262144
llama_model_loader: - kv  16:                   qwen3vl.embedding_length u32              = 2048
llama_model_loader: - kv  17:                qwen3vl.feed_forward_length u32              = 6144
llama_model_loader: - kv  18:               qwen3vl.attention.head_count u32              = 16
llama_model_loader: - kv  19:            qwen3vl.attention.head_count_kv u32              = 8
llama_model_loader: - kv  20:                     qwen3vl.rope.freq_base f32              = 5000000.000000
llama_model_loader: - kv  21:   qwen3vl.attention.layer_norm_rms_epsilon f32              = 0.000001
llama_model_loader: - kv  22:               qwen3vl.attention.key_length u32              = 128
llama_model_loader: - kv  23:             qwen3vl.attention.value_length u32              = 128
llama_model_loader: - kv  24:            qwen3vl.rope.dimension_sections arr[i32,4]       = [24, 20, 20, 0]
llama_model_loader: - kv  25:                 qwen3vl.n_deepstack_layers u32              = 3
llama_model_loader: - kv  26:                       tokenizer.ggml.model str              = gpt2
llama_model_loader: - kv  27:                         tokenizer.ggml.pre str              = qwen2
llama_model_loader: - kv  28:                      tokenizer.ggml.tokens arr[str,151936]  = ["!", "\"", "#", "$", "%", "&", "'", ...
llama_model_loader: - kv  29:                  tokenizer.ggml.token_type arr[i32,151936]  = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ...
llama_model_loader: - kv  30:                      tokenizer.ggml.merges arr[str,151387]  = ["Ġ Ġ", "ĠĠ ĠĠ", "i n", "Ġ t",...
llama_model_loader: - kv  31:                tokenizer.ggml.eos_token_id u32              = 151645
llama_model_loader: - kv  32:            tokenizer.ggml.padding_token_id u32              = 151654
llama_model_loader: - kv  33:                tokenizer.ggml.bos_token_id u32              = 151643
llama_model_loader: - kv  34:               tokenizer.ggml.add_bos_token bool             = false
llama_model_loader: - kv  35:                    tokenizer.chat_template str              = {# Unsloth template fixes #}\n{%- set ...
llama_model_loader: - kv  36:               general.quantization_version u32              = 2
llama_model_loader: - kv  37:                          general.file_type u32              = 18
llama_model_loader: - kv  38:                      quantize.imatrix.file str              = Qwen3-VL-2B-Thinking-GGUF/imatrix_uns...
llama_model_loader: - kv  39:                   quantize.imatrix.dataset str              = unsloth_calibration_Qwen3-VL-2B-Think...
llama_model_loader: - kv  40:             quantize.imatrix.entries_count u32              = 196
llama_model_loader: - kv  41:              quantize.imatrix.chunks_count u32              = 672
llama_model_loader: - type  f32:  113 tensors
llama_model_loader: - type q8_0:  105 tensors
llama_model_loader: - type q6_K:   92 tensors
print_info: file format = GGUF V3 (latest)
print_info: file type   = Q6_K
print_info: file size   = 1.49 GiB (7.46 BPW)
llama_model_load: error loading model: error loading model architecture: unknown model architecture: 'qwen3vl'
llama_model_load_from_file_impl: failed to load model
time=2025-11-04T14:40:12.752+05:30 level=INFO source=sched.go:418 msg="NewLlamaServer failed" model=C:\Users\iamka\.ollama\models\blobs\sha256-6f1d3d8fa65d2e30265fead346be6ad87e712523b8b8f92e031b8009853f0a1b error="unable to load model: C:\\Users\\iamka\\.ollama\\models\\blobs\\sha256-6f1d3d8fa65d2e30265fead346be6ad87e712523b8b8f92e031b8009853f0a1b"
[GIN] 2025/11/04 - 14:40:12 | 500 |    300.5951ms |       127.0.0.1 | POST     "/api/generate"

OS

Windows

GPU

Nvidia

CPU

Intel

Ollama version

0.12.9

Originally created by @logxdx on GitHub (Nov 4, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/12944 ### What is the issue? Ollama does not recognize qwen3vl model architecture. Reinstall didn't work. ### Relevant log output ```shell ollama serve time=2025-11-04T14:39:57.310+05:30 level=INFO source=routes.go:1524 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:INFO OLLAMA_FLASH_ATTENTION:true OLLAMA_GPU_OVERHEAD:0 OLLAMA_HOST:http://127.0.0.1:11434 OLLAMA_INTEL_GPU:false OLLAMA_KEEP_ALIVE:5m0s OLLAMA_KV_CACHE_TYPE:q8 OLLAMA_LLM_LIBRARY: OLLAMA_LOAD_TIMEOUT:5m0s OLLAMA_MAX_LOADED_MODELS:0 OLLAMA_MAX_QUEUE:512 OLLAMA_MODELS:C:\\Users\\iamka\\.ollama\\models OLLAMA_MULTIUSER_CACHE:false OLLAMA_NEW_ENGINE:true 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=2025-11-04T14:39:57.321+05:30 level=INFO source=images.go:522 msg="total blobs: 124" time=2025-11-04T14:39:57.324+05:30 level=INFO source=images.go:529 msg="total unused blobs removed: 0" time=2025-11-04T14:39:57.326+05:30 level=INFO source=routes.go:1577 msg="Listening on 127.0.0.1:11434 (version 0.12.9)" time=2025-11-04T14:39:57.328+05:30 level=INFO source=runner.go:76 msg="discovering available GPUs..." time=2025-11-04T14:39:57.331+05:30 level=INFO source=server.go:400 msg="starting runner" cmd="C:\\Users\\iamka\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 57888" time=2025-11-04T14:39:57.482+05:30 level=INFO source=server.go:400 msg="starting runner" cmd="C:\\Users\\iamka\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 57892" time=2025-11-04T14:39:57.548+05:30 level=INFO source=server.go:400 msg="starting runner" cmd="C:\\Users\\iamka\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 57896" time=2025-11-04T14:39:57.702+05:30 level=INFO source=server.go:400 msg="starting runner" cmd="C:\\Users\\iamka\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 57900" time=2025-11-04T14:39:57.702+05:30 level=INFO source=server.go:400 msg="starting runner" cmd="C:\\Users\\iamka\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 57901" time=2025-11-04T14:39:57.858+05:30 level=INFO source=types.go:42 msg="inference compute" id=GPU-71ff890f-0c96-f116-24c3-62d930353a93 filtered_id="" library=CUDA compute=8.9 name=CUDA0 description="NVIDIA GeForce RTX 4050 Laptop GPU" libdirs=ollama,cuda_v13 driver=13.0 pci_id=0000:01:00.0 type=discrete total="6.0 GiB" available="5.6 GiB" time=2025-11-04T14:39:57.858+05:30 level=INFO source=routes.go:1618 msg="entering low vram mode" "total vram"="6.0 GiB" threshold="20.0 GiB" [GIN] 2025/11/04 - 14:40:12 | 200 | 0s | 127.0.0.1 | HEAD "/" [GIN] 2025/11/04 - 14:40:12 | 200 | 42.0572ms | 127.0.0.1 | POST "/api/show" [GIN] 2025/11/04 - 14:40:12 | 200 | 50.1346ms | 127.0.0.1 | POST "/api/show" time=2025-11-04T14:40:12.516+05:30 level=INFO source=server.go:400 msg="starting runner" cmd="C:\\Users\\iamka\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 57911" time=2025-11-04T14:40:12.655+05:30 level=INFO source=cpu_windows.go:139 msg=packages count=1 time=2025-11-04T14:40:12.655+05:30 level=INFO source=cpu_windows.go:155 msg="efficiency cores detected" maxEfficiencyClass=1 time=2025-11-04T14:40:12.656+05:30 level=INFO source=cpu_windows.go:186 msg="" package=0 cores=8 efficiency=4 threads=12 llama_model_loader: loaded meta data with 42 key-value pairs and 310 tensors from C:\Users\iamka\.ollama\models\blobs\sha256-6f1d3d8fa65d2e30265fead346be6ad87e712523b8b8f92e031b8009853f0a1b (version GGUF V3 (latest)) llama_model_loader: Dumping metadata keys/values. Note: KV overrides do not apply in this output. llama_model_loader: - kv 0: general.architecture str = qwen3vl llama_model_loader: - kv 1: general.type str = model llama_model_loader: - kv 2: general.name str = Qwen3-Vl-2B-Thinking llama_model_loader: - kv 3: general.finetune str = Thinking llama_model_loader: - kv 4: general.basename str = Qwen3-Vl-2B-Thinking llama_model_loader: - kv 5: general.quantized_by str = Unsloth llama_model_loader: - kv 6: general.size_label str = 2B llama_model_loader: - kv 7: general.license str = apache-2.0 llama_model_loader: - kv 8: general.repo_url str = https://huggingface.co/unsloth llama_model_loader: - kv 9: general.base_model.count u32 = 1 llama_model_loader: - kv 10: general.base_model.0.name str = Qwen3 VL 2B Thinking llama_model_loader: - kv 11: general.base_model.0.organization str = Qwen llama_model_loader: - kv 12: general.base_model.0.repo_url str = https://huggingface.co/Qwen/Qwen3-VL-... llama_model_loader: - kv 13: general.tags arr[str,2] = ["unsloth", "image-text-to-text"] llama_model_loader: - kv 14: qwen3vl.block_count u32 = 28 llama_model_loader: - kv 15: qwen3vl.context_length u32 = 262144 llama_model_loader: - kv 16: qwen3vl.embedding_length u32 = 2048 llama_model_loader: - kv 17: qwen3vl.feed_forward_length u32 = 6144 llama_model_loader: - kv 18: qwen3vl.attention.head_count u32 = 16 llama_model_loader: - kv 19: qwen3vl.attention.head_count_kv u32 = 8 llama_model_loader: - kv 20: qwen3vl.rope.freq_base f32 = 5000000.000000 llama_model_loader: - kv 21: qwen3vl.attention.layer_norm_rms_epsilon f32 = 0.000001 llama_model_loader: - kv 22: qwen3vl.attention.key_length u32 = 128 llama_model_loader: - kv 23: qwen3vl.attention.value_length u32 = 128 llama_model_loader: - kv 24: qwen3vl.rope.dimension_sections arr[i32,4] = [24, 20, 20, 0] llama_model_loader: - kv 25: qwen3vl.n_deepstack_layers u32 = 3 llama_model_loader: - kv 26: tokenizer.ggml.model str = gpt2 llama_model_loader: - kv 27: tokenizer.ggml.pre str = qwen2 llama_model_loader: - kv 28: tokenizer.ggml.tokens arr[str,151936] = ["!", "\"", "#", "$", "%", "&", "'", ... llama_model_loader: - kv 29: tokenizer.ggml.token_type arr[i32,151936] = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ... llama_model_loader: - kv 30: tokenizer.ggml.merges arr[str,151387] = ["Ġ Ġ", "ĠĠ ĠĠ", "i n", "Ġ t",... llama_model_loader: - kv 31: tokenizer.ggml.eos_token_id u32 = 151645 llama_model_loader: - kv 32: tokenizer.ggml.padding_token_id u32 = 151654 llama_model_loader: - kv 33: tokenizer.ggml.bos_token_id u32 = 151643 llama_model_loader: - kv 34: tokenizer.ggml.add_bos_token bool = false llama_model_loader: - kv 35: tokenizer.chat_template str = {# Unsloth template fixes #}\n{%- set ... llama_model_loader: - kv 36: general.quantization_version u32 = 2 llama_model_loader: - kv 37: general.file_type u32 = 18 llama_model_loader: - kv 38: quantize.imatrix.file str = Qwen3-VL-2B-Thinking-GGUF/imatrix_uns... llama_model_loader: - kv 39: quantize.imatrix.dataset str = unsloth_calibration_Qwen3-VL-2B-Think... llama_model_loader: - kv 40: quantize.imatrix.entries_count u32 = 196 llama_model_loader: - kv 41: quantize.imatrix.chunks_count u32 = 672 llama_model_loader: - type f32: 113 tensors llama_model_loader: - type q8_0: 105 tensors llama_model_loader: - type q6_K: 92 tensors print_info: file format = GGUF V3 (latest) print_info: file type = Q6_K print_info: file size = 1.49 GiB (7.46 BPW) llama_model_load: error loading model: error loading model architecture: unknown model architecture: 'qwen3vl' llama_model_load_from_file_impl: failed to load model time=2025-11-04T14:40:12.752+05:30 level=INFO source=sched.go:418 msg="NewLlamaServer failed" model=C:\Users\iamka\.ollama\models\blobs\sha256-6f1d3d8fa65d2e30265fead346be6ad87e712523b8b8f92e031b8009853f0a1b error="unable to load model: C:\\Users\\iamka\\.ollama\\models\\blobs\\sha256-6f1d3d8fa65d2e30265fead346be6ad87e712523b8b8f92e031b8009853f0a1b" [GIN] 2025/11/04 - 14:40:12 | 500 | 300.5951ms | 127.0.0.1 | POST "/api/generate" ``` ### OS Windows ### GPU Nvidia ### CPU Intel ### Ollama version 0.12.9
GiteaMirror added the bug label 2026-04-29 08:19:43 -05:00
GiteaMirror commented 2026-04-29 08:19:47 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Nov 4, 2025):

https://github.com/ollama/ollama/issues/12897#issuecomment-3475889931

<!-- gh-comment-id:3485085695 --> @rick-github commented on GitHub (Nov 4, 2025): https://github.com/ollama/ollama/issues/12897#issuecomment-3475889931
GiteaMirror commented 2026-04-29 08:19:47 -05:00
Author
Owner
Copy Link

@pdevine commented on GitHub (Nov 4, 2025):

Closing as a dupe.

<!-- gh-comment-id:3488410850 --> @pdevine commented on GitHub (Nov 4, 2025): Closing as a dupe.
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#55095
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?