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 #13324] Qwen VL not supported error #34560

New Issue
Closed
opened 2026-04-22 18:15:05 -05:00 by GiteaMirror · 8 comments
GiteaMirror commented 2026-04-22 18:15:05 -05:00
Owner
Copy Link

Originally created by @itzpingcat on GitHub (Dec 4, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/13324

What is the issue?

you are kidding me right...
this is the unsloth Q3_K_s quanted version because I can't fit Q4_K_M

the ollama page literally says >0.12.7 required and im 0.13.1

Relevant log output

time=2025-12-03T22:12:16.401-05:00 level=INFO source=routes.go:1544 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:16384 OLLAMA_DEBUG:INFO 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\\walnu\\.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=2025-12-03T22:12:16.409-05:00 level=INFO source=images.go:522 msg="total blobs: 57"
time=2025-12-03T22:12:16.411-05:00 level=INFO source=images.go:529 msg="total unused blobs removed: 0"
time=2025-12-03T22:12:16.414-05:00 level=INFO source=routes.go:1597 msg="Listening on [::]:11434 (version 0.13.1)"
time=2025-12-03T22:12:16.414-05:00 level=INFO source=runner.go:67 msg="discovering available GPUs..."
time=2025-12-03T22:12:16.421-05:00 level=INFO source=server.go:392 msg="starting runner" cmd="C:\\Users\\walnu\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 62647"
time=2025-12-03T22:12:24.070-05:00 level=INFO source=server.go:392 msg="starting runner" cmd="C:\\Users\\walnu\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 62717"
time=2025-12-03T22:12:24.302-05:00 level=INFO source=server.go:392 msg="starting runner" cmd="C:\\Users\\walnu\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 62725"
time=2025-12-03T22:12:25.259-05:00 level=INFO source=runner.go:106 msg="experimental Vulkan support disabled.  To enable, set OLLAMA_VULKAN=1"
time=2025-12-03T22:12:25.260-05:00 level=INFO source=server.go:392 msg="starting runner" cmd="C:\\Users\\walnu\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 62735"
time=2025-12-03T22:12:25.260-05:00 level=INFO source=server.go:392 msg="starting runner" cmd="C:\\Users\\walnu\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 62736"
time=2025-12-03T22:12:25.455-05:00 level=INFO source=types.go:42 msg="inference compute" id=GPU-0d16588b-3fc3-9446-a124-6a37a00b0be1 filter_id="" library=CUDA compute=12.0 name=CUDA0 description="NVIDIA GeForce RTX 5060 Ti" libdirs=ollama,cuda_v12 driver=12.9 pci_id=0000:01:00.0 type=discrete total="15.9 GiB" available="15.5 GiB"
time=2025-12-03T22:12:25.455-05:00 level=INFO source=routes.go:1638 msg="entering low vram mode" "total vram"="15.9 GiB" threshold="20.0 GiB"
[GIN] 2025/12/03 - 22:12:31 | 200 |            0s |       127.0.0.1 | GET      "/api/version"
[GIN] 2025/12/03 - 22:12:31 | 200 |      5.7351ms |       127.0.0.1 | GET      "/api/tags"
[GIN] 2025/12/03 - 22:12:32 | 200 |     50.2021ms |       127.0.0.1 | POST     "/api/show"
[GIN] 2025/12/03 - 22:12:35 | 200 |     20.5349ms |       127.0.0.1 | GET      "/api/tags"
[GIN] 2025/12/03 - 22:12:35 | 200 |     65.6344ms |       127.0.0.1 | POST     "/api/show"
[GIN] 2025/12/03 - 22:12:35 | 200 |     25.6527ms |       127.0.0.1 | POST     "/api/show"
time=2025-12-03T22:12:35.152-05:00 level=INFO source=server.go:392 msg="starting runner" cmd="C:\\Users\\walnu\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 56881"
time=2025-12-03T22:12:35.296-05:00 level=INFO source=cpu_windows.go:148 msg=packages count=1
time=2025-12-03T22:12:35.296-05:00 level=INFO source=cpu_windows.go:195 msg="" package=0 cores=6 efficiency=0 threads=12
llama_model_loader: loaded meta data with 45 key-value pairs and 579 tensors from C:\Users\walnu\.ollama\models\blobs\sha256-0c90aa852175e5e242a3856c4d0881498b16efde20716c596c2271c8fabbb9ee (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              = qwen3vlmoe
llama_model_loader: - kv   1:                               general.type str              = model
llama_model_loader: - kv   2:                               general.name str              = Qwen3-Vl-30B-A3B-Instruct
llama_model_loader: - kv   3:                           general.finetune str              = Instruct
llama_model_loader: - kv   4:                           general.basename str              = Qwen3-Vl-30B-A3B-Instruct
llama_model_loader: - kv   5:                       general.quantized_by str              = Unsloth
llama_model_loader: - kv   6:                         general.size_label str              = 30B-A3B
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 30B A3B Instruct
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:                     qwen3vlmoe.block_count u32              = 48
llama_model_loader: - kv  15:                  qwen3vlmoe.context_length u32              = 262144
llama_model_loader: - kv  16:                qwen3vlmoe.embedding_length u32              = 2048
llama_model_loader: - kv  17:             qwen3vlmoe.feed_forward_length u32              = 6144
llama_model_loader: - kv  18:            qwen3vlmoe.attention.head_count u32              = 32
llama_model_loader: - kv  19:         qwen3vlmoe.attention.head_count_kv u32              = 4
llama_model_loader: - kv  20:                  qwen3vlmoe.rope.freq_base f32              = 5000000.000000
llama_model_loader: - kv  21: qwen3vlmoe.attention.layer_norm_rms_epsilon f32              = 0.000001
llama_model_loader: - kv  22:               qwen3vlmoe.expert_used_count u32              = 8
llama_model_loader: - kv  23:            qwen3vlmoe.attention.key_length u32              = 128
llama_model_loader: - kv  24:          qwen3vlmoe.attention.value_length u32              = 128
llama_model_loader: - kv  25:                    qwen3vlmoe.expert_count u32              = 128
llama_model_loader: - kv  26:      qwen3vlmoe.expert_feed_forward_length u32              = 768
llama_model_loader: - kv  27:         qwen3vlmoe.rope.dimension_sections arr[i32,4]       = [24, 20, 20, 0]
llama_model_loader: - kv  28:              qwen3vlmoe.n_deepstack_layers u32              = 3
llama_model_loader: - kv  29:                       tokenizer.ggml.model str              = gpt2
llama_model_loader: - kv  30:                         tokenizer.ggml.pre str              = qwen2
llama_model_loader: - kv  31:                      tokenizer.ggml.tokens arr[str,151936]  = ["!", "\"", "#", "$", "%", "&", "'", ...
llama_model_loader: - kv  32:                  tokenizer.ggml.token_type arr[i32,151936]  = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ...
llama_model_loader: - kv  33:                      tokenizer.ggml.merges arr[str,151387]  = ["Ġ Ġ", "ĠĠ ĠĠ", "i n", "Ġ t",...
llama_model_loader: - kv  34:                tokenizer.ggml.eos_token_id u32              = 151645
llama_model_loader: - kv  35:            tokenizer.ggml.padding_token_id u32              = 151654
llama_model_loader: - kv  36:                tokenizer.ggml.bos_token_id u32              = 151643
llama_model_loader: - kv  37:               tokenizer.ggml.add_bos_token bool             = false
llama_model_loader: - kv  38:                    tokenizer.chat_template str              = {%- if tools %}\n    {{- '<|im_start|>...
llama_model_loader: - kv  39:               general.quantization_version u32              = 2
llama_model_loader: - kv  40:                          general.file_type u32              = 11
llama_model_loader: - kv  41:                      quantize.imatrix.file str              = Qwen3-VL-30B-A3B-Instruct-GGUF/imatri...
llama_model_loader: - kv  42:                   quantize.imatrix.dataset str              = unsloth_calibration_Qwen3-VL-30B-A3B-...
llama_model_loader: - kv  43:             quantize.imatrix.entries_count u32              = 384
llama_model_loader: - kv  44:              quantize.imatrix.chunks_count u32              = 154
llama_model_loader: - type  f32:  241 tensors
llama_model_loader: - type q3_K:  337 tensors
llama_model_loader: - type q6_K:    1 tensors
print_info: file format = GGUF V3 (latest)
print_info: file type   = Q3_K - Small
print_info: file size   = 12.37 GiB (3.48 BPW) 
llama_model_load: error loading model: error loading model architecture: unknown model architecture: 'qwen3vlmoe'
llama_model_load_from_file_impl: failed to load model
time=2025-12-03T22:12:35.366-05:00 level=INFO source=sched.go:425 msg="NewLlamaServer failed" model=C:\Users\walnu\.ollama\models\blobs\sha256-0c90aa852175e5e242a3856c4d0881498b16efde20716c596c2271c8fabbb9ee error="unable to load model: C:\\Users\\walnu\\.ollama\\models\\blobs\\sha256-0c90aa852175e5e242a3856c4d0881498b16efde20716c596c2271c8fabbb9ee"
[GIN] 2025/12/03 - 22:12:35 | 500 |    265.4364ms |       127.0.0.1 | POST     "/api/chat"

OS

Windows

GPU

Nvidia

CPU

AMD

Ollama version

0.13.1

Originally created by @itzpingcat on GitHub (Dec 4, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/13324 ### What is the issue? you are kidding me right... this is the unsloth Q3_K_s quanted version because I can't fit Q4_K_M the ollama page literally says >0.12.7 required and im 0.13.1 ### Relevant log output ```shell time=2025-12-03T22:12:16.401-05:00 level=INFO source=routes.go:1544 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:16384 OLLAMA_DEBUG:INFO 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\\walnu\\.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=2025-12-03T22:12:16.409-05:00 level=INFO source=images.go:522 msg="total blobs: 57" time=2025-12-03T22:12:16.411-05:00 level=INFO source=images.go:529 msg="total unused blobs removed: 0" time=2025-12-03T22:12:16.414-05:00 level=INFO source=routes.go:1597 msg="Listening on [::]:11434 (version 0.13.1)" time=2025-12-03T22:12:16.414-05:00 level=INFO source=runner.go:67 msg="discovering available GPUs..." time=2025-12-03T22:12:16.421-05:00 level=INFO source=server.go:392 msg="starting runner" cmd="C:\\Users\\walnu\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 62647" time=2025-12-03T22:12:24.070-05:00 level=INFO source=server.go:392 msg="starting runner" cmd="C:\\Users\\walnu\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 62717" time=2025-12-03T22:12:24.302-05:00 level=INFO source=server.go:392 msg="starting runner" cmd="C:\\Users\\walnu\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 62725" time=2025-12-03T22:12:25.259-05:00 level=INFO source=runner.go:106 msg="experimental Vulkan support disabled. To enable, set OLLAMA_VULKAN=1" time=2025-12-03T22:12:25.260-05:00 level=INFO source=server.go:392 msg="starting runner" cmd="C:\\Users\\walnu\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 62735" time=2025-12-03T22:12:25.260-05:00 level=INFO source=server.go:392 msg="starting runner" cmd="C:\\Users\\walnu\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 62736" time=2025-12-03T22:12:25.455-05:00 level=INFO source=types.go:42 msg="inference compute" id=GPU-0d16588b-3fc3-9446-a124-6a37a00b0be1 filter_id="" library=CUDA compute=12.0 name=CUDA0 description="NVIDIA GeForce RTX 5060 Ti" libdirs=ollama,cuda_v12 driver=12.9 pci_id=0000:01:00.0 type=discrete total="15.9 GiB" available="15.5 GiB" time=2025-12-03T22:12:25.455-05:00 level=INFO source=routes.go:1638 msg="entering low vram mode" "total vram"="15.9 GiB" threshold="20.0 GiB" [GIN] 2025/12/03 - 22:12:31 | 200 | 0s | 127.0.0.1 | GET "/api/version" [GIN] 2025/12/03 - 22:12:31 | 200 | 5.7351ms | 127.0.0.1 | GET "/api/tags" [GIN] 2025/12/03 - 22:12:32 | 200 | 50.2021ms | 127.0.0.1 | POST "/api/show" [GIN] 2025/12/03 - 22:12:35 | 200 | 20.5349ms | 127.0.0.1 | GET "/api/tags" [GIN] 2025/12/03 - 22:12:35 | 200 | 65.6344ms | 127.0.0.1 | POST "/api/show" [GIN] 2025/12/03 - 22:12:35 | 200 | 25.6527ms | 127.0.0.1 | POST "/api/show" time=2025-12-03T22:12:35.152-05:00 level=INFO source=server.go:392 msg="starting runner" cmd="C:\\Users\\walnu\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 56881" time=2025-12-03T22:12:35.296-05:00 level=INFO source=cpu_windows.go:148 msg=packages count=1 time=2025-12-03T22:12:35.296-05:00 level=INFO source=cpu_windows.go:195 msg="" package=0 cores=6 efficiency=0 threads=12 llama_model_loader: loaded meta data with 45 key-value pairs and 579 tensors from C:\Users\walnu\.ollama\models\blobs\sha256-0c90aa852175e5e242a3856c4d0881498b16efde20716c596c2271c8fabbb9ee (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 = qwen3vlmoe llama_model_loader: - kv 1: general.type str = model llama_model_loader: - kv 2: general.name str = Qwen3-Vl-30B-A3B-Instruct llama_model_loader: - kv 3: general.finetune str = Instruct llama_model_loader: - kv 4: general.basename str = Qwen3-Vl-30B-A3B-Instruct llama_model_loader: - kv 5: general.quantized_by str = Unsloth llama_model_loader: - kv 6: general.size_label str = 30B-A3B 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 30B A3B Instruct 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: qwen3vlmoe.block_count u32 = 48 llama_model_loader: - kv 15: qwen3vlmoe.context_length u32 = 262144 llama_model_loader: - kv 16: qwen3vlmoe.embedding_length u32 = 2048 llama_model_loader: - kv 17: qwen3vlmoe.feed_forward_length u32 = 6144 llama_model_loader: - kv 18: qwen3vlmoe.attention.head_count u32 = 32 llama_model_loader: - kv 19: qwen3vlmoe.attention.head_count_kv u32 = 4 llama_model_loader: - kv 20: qwen3vlmoe.rope.freq_base f32 = 5000000.000000 llama_model_loader: - kv 21: qwen3vlmoe.attention.layer_norm_rms_epsilon f32 = 0.000001 llama_model_loader: - kv 22: qwen3vlmoe.expert_used_count u32 = 8 llama_model_loader: - kv 23: qwen3vlmoe.attention.key_length u32 = 128 llama_model_loader: - kv 24: qwen3vlmoe.attention.value_length u32 = 128 llama_model_loader: - kv 25: qwen3vlmoe.expert_count u32 = 128 llama_model_loader: - kv 26: qwen3vlmoe.expert_feed_forward_length u32 = 768 llama_model_loader: - kv 27: qwen3vlmoe.rope.dimension_sections arr[i32,4] = [24, 20, 20, 0] llama_model_loader: - kv 28: qwen3vlmoe.n_deepstack_layers u32 = 3 llama_model_loader: - kv 29: tokenizer.ggml.model str = gpt2 llama_model_loader: - kv 30: tokenizer.ggml.pre str = qwen2 llama_model_loader: - kv 31: tokenizer.ggml.tokens arr[str,151936] = ["!", "\"", "#", "$", "%", "&", "'", ... llama_model_loader: - kv 32: tokenizer.ggml.token_type arr[i32,151936] = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ... llama_model_loader: - kv 33: tokenizer.ggml.merges arr[str,151387] = ["Ġ Ġ", "ĠĠ ĠĠ", "i n", "Ġ t",... llama_model_loader: - kv 34: tokenizer.ggml.eos_token_id u32 = 151645 llama_model_loader: - kv 35: tokenizer.ggml.padding_token_id u32 = 151654 llama_model_loader: - kv 36: tokenizer.ggml.bos_token_id u32 = 151643 llama_model_loader: - kv 37: tokenizer.ggml.add_bos_token bool = false llama_model_loader: - kv 38: tokenizer.chat_template str = {%- if tools %}\n {{- '<|im_start|>... llama_model_loader: - kv 39: general.quantization_version u32 = 2 llama_model_loader: - kv 40: general.file_type u32 = 11 llama_model_loader: - kv 41: quantize.imatrix.file str = Qwen3-VL-30B-A3B-Instruct-GGUF/imatri... llama_model_loader: - kv 42: quantize.imatrix.dataset str = unsloth_calibration_Qwen3-VL-30B-A3B-... llama_model_loader: - kv 43: quantize.imatrix.entries_count u32 = 384 llama_model_loader: - kv 44: quantize.imatrix.chunks_count u32 = 154 llama_model_loader: - type f32: 241 tensors llama_model_loader: - type q3_K: 337 tensors llama_model_loader: - type q6_K: 1 tensors print_info: file format = GGUF V3 (latest) print_info: file type = Q3_K - Small print_info: file size = 12.37 GiB (3.48 BPW) llama_model_load: error loading model: error loading model architecture: unknown model architecture: 'qwen3vlmoe' llama_model_load_from_file_impl: failed to load model time=2025-12-03T22:12:35.366-05:00 level=INFO source=sched.go:425 msg="NewLlamaServer failed" model=C:\Users\walnu\.ollama\models\blobs\sha256-0c90aa852175e5e242a3856c4d0881498b16efde20716c596c2271c8fabbb9ee error="unable to load model: C:\\Users\\walnu\\.ollama\\models\\blobs\\sha256-0c90aa852175e5e242a3856c4d0881498b16efde20716c596c2271c8fabbb9ee" [GIN] 2025/12/03 - 22:12:35 | 500 | 265.4364ms | 127.0.0.1 | POST "/api/chat" ``` ### OS Windows ### GPU Nvidia ### CPU AMD ### Ollama version 0.13.1
GiteaMirror added the bug label 2026-04-22 18:15:05 -05:00
GiteaMirror commented 2026-04-22 18:15:10 -05:00
Author
Owner
Copy Link

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

Models downloaded from HF typically are split format, separate text and vision weights. The ollama engine only supports fused multi-modal models, so the server tries to use the llama.cpp engine to load the model, which doesn't support qwen3-vl yet.

<!-- gh-comment-id:3611669656 --> @rick-github commented on GitHub (Dec 4, 2025): Models downloaded from HF typically are split format, separate text and vision weights. The ollama engine only supports fused multi-modal models, so the server tries to use the llama.cpp engine to load the model, which doesn't support qwen3-vl yet.
GiteaMirror commented 2026-04-22 18:15:10 -05:00
Author
Owner
Copy Link

@itzpingcat commented on GitHub (Dec 4, 2025):

Feature request: auto compress separate vision and text weights

<!-- gh-comment-id:3613902557 --> @itzpingcat commented on GitHub (Dec 4, 2025): Feature request: auto compress separate vision and text weights
GiteaMirror commented 2026-04-22 18:15:11 -05:00
Author
Owner
Copy Link

@maternion commented on GitHub (Dec 5, 2025):

Feature request: auto compress separate vision and text weights

https://github.com/ollama/ollama/pull/12992
Should work with the release which includes the new llama.cpp build.

<!-- gh-comment-id:3615444492 --> @maternion commented on GitHub (Dec 5, 2025): > Feature request: auto compress separate vision and text weights https://github.com/ollama/ollama/pull/12992 Should work with the release which includes the new llama.cpp build.
GiteaMirror commented 2026-04-22 18:15:12 -05:00
Author
Owner
Copy Link

@MohanBarathi commented on GitHub (Dec 9, 2025):

it is fixed in v0.13.2 🚀

<!-- gh-comment-id:3634043884 --> @MohanBarathi commented on GitHub (Dec 9, 2025): it is fixed in v0.13.2 🚀
GiteaMirror commented 2026-04-22 18:15:12 -05:00
Author
Owner
Copy Link

@pleabargain commented on GitHub (Dec 10, 2025):

Image not working qwen3vl not working with latest Ollama ollama --version ollama version is 0.13.2
<!-- gh-comment-id:3635787629 --> @pleabargain commented on GitHub (Dec 10, 2025): <img width="1799" height="654" alt="Image" src="https://github.com/user-attachments/assets/34d089f8-14c7-4f5f-b69f-e2a00ed457eb" /> not working qwen3vl not working with latest Ollama ollama --version ollama version is 0.13.2
GiteaMirror commented 2026-04-22 18:15:12 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Dec 10, 2025):

@pleabargain Different issue, https://github.com/ollama/ollama/issues/13211

<!-- gh-comment-id:3636611453 --> @rick-github commented on GitHub (Dec 10, 2025): @pleabargain Different issue, https://github.com/ollama/ollama/issues/13211
GiteaMirror commented 2026-04-22 18:15:13 -05:00
Author
Owner
Copy Link

@itzpingcat commented on GitHub (Dec 12, 2025):

i think it is fixed? so closing now, rick can reopen if not fixed

<!-- gh-comment-id:3644645363 --> @itzpingcat commented on GitHub (Dec 12, 2025): i think it is fixed? so closing now, rick can reopen if not fixed
GiteaMirror commented 2026-04-22 18:15:13 -05:00
Author
Owner
Copy Link

@pleabargain commented on GitHub (Dec 12, 2025):

ollama --version
ollama version is 0.13.2

This model doesn't support images.

Image

No joy for me.

<!-- gh-comment-id:3645121180 --> @pleabargain commented on GitHub (Dec 12, 2025): ollama --version ollama version is 0.13.2 This model doesn't support images. <img width="1871" height="725" alt="Image" src="https://github.com/user-attachments/assets/48e0313d-dcc0-4515-a5f5-f8d1d069e865" /> No joy for me.
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#34560
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?