ollama - 💡(How to fix) Fix Qwen GGML models do not load with 0.17.5 [1 participants]

ollama2026-03-03 20:07:36

ON THIS PAGE

Recommended Tools

×6

Utilities matched from this issue’s tags and category — try them while you read without losing context.

GitHub issue graph ai analysis

Paste a GitHub issue URL. We fetch that issue, discover linked issues from bodies/comments/timeline, collect linked pull requests, and produce a structured English report.

The report is written in English Markdown for sharing and archival.

GitHub issue URL

Helpful · Quick feedback

GitHub stats

ollama/ollama#14595•Fetched 2026-04-08 00:33:57

View on GitHub

Comments

Participants

Timeline

Reactions

Author

morti86

Participants

morti86

Timeline (top)

closed ×1labeled ×1subscribed ×1

Error Message

When I try to load the model, I get the following error. Same issue with 9b version. llama_model_load: error loading model: error loading model architecture: unknown model architecture: 'qwen35'

Code Example

time=2026-03-03T21:04:58.094+01:00 level=INFO source=routes.go:1665 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:0 OLLAMA_DEBUG:INFO OLLAMA_EDITOR: OLLAMA_FLASH_ATTENTION:false OLLAMA_GPU_OVERHEAD:0 OLLAMA_HOST:http://127.0.0.1:11434 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:/home/morti/.ollama/models OLLAMA_MULTIUSER_CACHE:false OLLAMA_NEW_ENGINE:false OLLAMA_NOHISTORY:false OLLAMA_NOPRUNE:false OLLAMA_NO_CLOUD: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: http_proxy: https_proxy: no_proxy:]"
time=2026-03-03T21:04:58.094+01:00 level=INFO source=routes.go:1667 msg="Ollama cloud disabled: false"
time=2026-03-03T21:04:58.117+01:00 level=INFO source=images.go:477 msg="total blobs: 45"
time=2026-03-03T21:04:58.118+01:00 level=INFO source=images.go:484 msg="total unused blobs removed: 0"
time=2026-03-03T21:04:58.119+01:00 level=INFO source=routes.go:1720 msg="Listening on 127.0.0.1:11434 (version 0.17.5)"
time=2026-03-03T21:04:58.119+01:00 level=INFO source=runner.go:67 msg="discovering available GPUs..."
time=2026-03-03T21:04:58.120+01:00 level=INFO source=server.go:430 msg="starting runner" cmd="/usr/bin/ollama runner --ollama-engine --port 42571"
time=2026-03-03T21:04:58.176+01:00 level=INFO source=server.go:430 msg="starting runner" cmd="/usr/bin/ollama runner --ollama-engine --port 45443"
time=2026-03-03T21:04:59.531+01:00 level=INFO source=types.go:42 msg="inference compute" id=GPU-735b60ae6f451386 filter_id="" library=ROCm compute=gfx1100 name=ROCm0 description="AMD Radeon RX 7900 XT" libdirs=ollama driver=70226.4 pci_id=0000:2b:00.0 type=discrete total="20.0 GiB" available="17.4 GiB"
time=2026-03-03T21:04:59.531+01:00 level=INFO source=routes.go:1770 msg="vram-based default context" total_vram="20.0 GiB" default_num_ctx=4096
time=2026-03-03T21:05:03.514+01:00 level=INFO source=server.go:430 msg="starting runner" cmd="/usr/bin/ollama runner --ollama-engine --port 36695"
llama_model_loader: loaded meta data with 49 key-value pairs and 851 tensors from /home/morti/.ollama/models/blobs/sha256-84b5f7f112156d63836a01a69dc3f11a6ba63b10a23b8ca7a7efaf52d5a2d806 (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              = qwen35
llama_model_loader: - kv   1:                               general.type str              = model
llama_model_loader: - kv   2:                     general.sampling.top_k i32              = 20
llama_model_loader: - kv   3:                     general.sampling.top_p f32              = 0.950000
llama_model_loader: - kv   4:                      general.sampling.temp f32              = 0.600000
llama_model_loader: - kv   5:                               general.name str              = Qwen3.5-27B
llama_model_loader: - kv   6:                           general.basename str              = Qwen3.5-27B
llama_model_loader: - kv   7:                       general.quantized_by str              = Unsloth
llama_model_loader: - kv   8:                         general.size_label str              = 27B
llama_model_loader: - kv   9:                            general.license str              = apache-2.0
llama_model_loader: - kv  10:                       general.license.link str              = https://huggingface.co/Qwen/Qwen3.5-2...
llama_model_loader: - kv  11:                           general.repo_url str              = https://huggingface.co/unsloth
llama_model_loader: - kv  12:                   general.base_model.count u32              = 1
llama_model_loader: - kv  13:                  general.base_model.0.name str              = Qwen3.5 27B
llama_model_loader: - kv  14:          general.base_model.0.organization str              = Qwen
llama_model_loader: - kv  15:              general.base_model.0.repo_url str              = https://huggingface.co/Qwen/Qwen3.5-27B
llama_model_loader: - kv  16:                               general.tags arr[str,3]       = ["qwen3_5_moe", "unsloth", "image-tex...
llama_model_loader: - kv  17:                         qwen35.block_count u32              = 64
llama_model_loader: - kv  18:                      qwen35.context_length u32              = 262144
llama_model_loader: - kv  19:                    qwen35.embedding_length u32              = 5120
llama_model_loader: - kv  20:                 qwen35.feed_forward_length u32              = 17408
llama_model_loader: - kv  21:                qwen35.attention.head_count u32              = 24
llama_model_loader: - kv  22:             qwen35.attention.head_count_kv u32              = 4
llama_model_loader: - kv  23:             qwen35.rope.dimension_sections arr[i32,4]       = [11, 11, 10, 0]
llama_model_loader: - kv  24:                      qwen35.rope.freq_base f32              = 10000000.000000
llama_model_loader: - kv  25:    qwen35.attention.layer_norm_rms_epsilon f32              = 0.000001
llama_model_loader: - kv  26:                qwen35.attention.key_length u32              = 256
llama_model_loader: - kv  27:              qwen35.attention.value_length u32              = 256
llama_model_loader: - kv  28:                     qwen35.ssm.conv_kernel u32              = 4
llama_model_loader: - kv  29:                      qwen35.ssm.state_size u32              = 128
llama_model_loader: - kv  30:                     qwen35.ssm.group_count u32              = 16
llama_model_loader: - kv  31:                  qwen35.ssm.time_step_rank u32              = 48
llama_model_loader: - kv  32:                      qwen35.ssm.inner_size u32              = 6144
llama_model_loader: - kv  33:             qwen35.full_attention_interval u32              = 4
llama_model_loader: - kv  34:                qwen35.rope.dimension_count u32              = 64
llama_model_loader: - kv  35:                       tokenizer.ggml.model str              = gpt2
llama_model_loader: - kv  36:                         tokenizer.ggml.pre str              = qwen35
llama_model_loader: - kv  37:                      tokenizer.ggml.tokens arr[str,248320]  = ["!", "\"", "#", "$", "%", "&", "'", ...
llama_model_loader: - kv  38:                  tokenizer.ggml.token_type arr[i32,248320]  = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ...
llama_model_loader: - kv  39:                      tokenizer.ggml.merges arr[str,247587]  = ["Ġ Ġ", "ĠĠ ĠĠ", "i n", "Ġ t",...
llama_model_loader: - kv  40:                tokenizer.ggml.eos_token_id u32              = 248046
llama_model_loader: - kv  41:            tokenizer.ggml.padding_token_id u32              = 248055
llama_model_loader: - kv  42:                    tokenizer.chat_template str              = {%- set image_count = namespace(value...
llama_model_loader: - kv  43:               general.quantization_version u32              = 2
llama_model_loader: - kv  44:                          general.file_type u32              = 15
llama_model_loader: - kv  45:                      quantize.imatrix.file str              = Qwen3.5-27B-GGUF/imatrix_unsloth.gguf
llama_model_loader: - kv  46:                   quantize.imatrix.dataset str              = unsloth_calibration_Qwen3.5-27B.txt
llama_model_loader: - kv  47:             quantize.imatrix.entries_count u32              = 496
llama_model_loader: - kv  48:              quantize.imatrix.chunks_count u32              = 80
llama_model_loader: - type  f32:  353 tensors
llama_model_loader: - type q8_0:   96 tensors
llama_model_loader: - type q4_K:  263 tensors
llama_model_loader: - type q5_K:   96 tensors
llama_model_loader: - type q6_K:   43 tensors
print_info: file format = GGUF V3 (latest)
print_info: file type   = Q4_K - Medium
print_info: file size   = 15.58 GiB (4.98 BPW) 
llama_model_load: error loading model: error loading model architecture: unknown model architecture: 'qwen35'
llama_model_load_from_file_impl: failed to load model

RAW_BUFFERClick to expand / collapse

What is the issue?

When I try to load the model, I get the following error. Same issue with 9b version.

Relevant log output

time=2026-03-03T21:04:58.094+01:00 level=INFO source=routes.go:1665 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:0 OLLAMA_DEBUG:INFO OLLAMA_EDITOR: OLLAMA_FLASH_ATTENTION:false OLLAMA_GPU_OVERHEAD:0 OLLAMA_HOST:http://127.0.0.1:11434 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:/home/morti/.ollama/models OLLAMA_MULTIUSER_CACHE:false OLLAMA_NEW_ENGINE:false OLLAMA_NOHISTORY:false OLLAMA_NOPRUNE:false OLLAMA_NO_CLOUD: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: http_proxy: https_proxy: no_proxy:]"
time=2026-03-03T21:04:58.094+01:00 level=INFO source=routes.go:1667 msg="Ollama cloud disabled: false"
time=2026-03-03T21:04:58.117+01:00 level=INFO source=images.go:477 msg="total blobs: 45"
time=2026-03-03T21:04:58.118+01:00 level=INFO source=images.go:484 msg="total unused blobs removed: 0"
time=2026-03-03T21:04:58.119+01:00 level=INFO source=routes.go:1720 msg="Listening on 127.0.0.1:11434 (version 0.17.5)"
time=2026-03-03T21:04:58.119+01:00 level=INFO source=runner.go:67 msg="discovering available GPUs..."
time=2026-03-03T21:04:58.120+01:00 level=INFO source=server.go:430 msg="starting runner" cmd="/usr/bin/ollama runner --ollama-engine --port 42571"
time=2026-03-03T21:04:58.176+01:00 level=INFO source=server.go:430 msg="starting runner" cmd="/usr/bin/ollama runner --ollama-engine --port 45443"
time=2026-03-03T21:04:59.531+01:00 level=INFO source=types.go:42 msg="inference compute" id=GPU-735b60ae6f451386 filter_id="" library=ROCm compute=gfx1100 name=ROCm0 description="AMD Radeon RX 7900 XT" libdirs=ollama driver=70226.4 pci_id=0000:2b:00.0 type=discrete total="20.0 GiB" available="17.4 GiB"
time=2026-03-03T21:04:59.531+01:00 level=INFO source=routes.go:1770 msg="vram-based default context" total_vram="20.0 GiB" default_num_ctx=4096
time=2026-03-03T21:05:03.514+01:00 level=INFO source=server.go:430 msg="starting runner" cmd="/usr/bin/ollama runner --ollama-engine --port 36695"
llama_model_loader: loaded meta data with 49 key-value pairs and 851 tensors from /home/morti/.ollama/models/blobs/sha256-84b5f7f112156d63836a01a69dc3f11a6ba63b10a23b8ca7a7efaf52d5a2d806 (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              = qwen35
llama_model_loader: - kv   1:                               general.type str              = model
llama_model_loader: - kv   2:                     general.sampling.top_k i32              = 20
llama_model_loader: - kv   3:                     general.sampling.top_p f32              = 0.950000
llama_model_loader: - kv   4:                      general.sampling.temp f32              = 0.600000
llama_model_loader: - kv   5:                               general.name str              = Qwen3.5-27B
llama_model_loader: - kv   6:                           general.basename str              = Qwen3.5-27B
llama_model_loader: - kv   7:                       general.quantized_by str              = Unsloth
llama_model_loader: - kv   8:                         general.size_label str              = 27B
llama_model_loader: - kv   9:                            general.license str              = apache-2.0
llama_model_loader: - kv  10:                       general.license.link str              = https://huggingface.co/Qwen/Qwen3.5-2...
llama_model_loader: - kv  11:                           general.repo_url str              = https://huggingface.co/unsloth
llama_model_loader: - kv  12:                   general.base_model.count u32              = 1
llama_model_loader: - kv  13:                  general.base_model.0.name str              = Qwen3.5 27B
llama_model_loader: - kv  14:          general.base_model.0.organization str              = Qwen
llama_model_loader: - kv  15:              general.base_model.0.repo_url str              = https://huggingface.co/Qwen/Qwen3.5-27B
llama_model_loader: - kv  16:                               general.tags arr[str,3]       = ["qwen3_5_moe", "unsloth", "image-tex...
llama_model_loader: - kv  17:                         qwen35.block_count u32              = 64
llama_model_loader: - kv  18:                      qwen35.context_length u32              = 262144
llama_model_loader: - kv  19:                    qwen35.embedding_length u32              = 5120
llama_model_loader: - kv  20:                 qwen35.feed_forward_length u32              = 17408
llama_model_loader: - kv  21:                qwen35.attention.head_count u32              = 24
llama_model_loader: - kv  22:             qwen35.attention.head_count_kv u32              = 4
llama_model_loader: - kv  23:             qwen35.rope.dimension_sections arr[i32,4]       = [11, 11, 10, 0]
llama_model_loader: - kv  24:                      qwen35.rope.freq_base f32              = 10000000.000000
llama_model_loader: - kv  25:    qwen35.attention.layer_norm_rms_epsilon f32              = 0.000001
llama_model_loader: - kv  26:                qwen35.attention.key_length u32              = 256
llama_model_loader: - kv  27:              qwen35.attention.value_length u32              = 256
llama_model_loader: - kv  28:                     qwen35.ssm.conv_kernel u32              = 4
llama_model_loader: - kv  29:                      qwen35.ssm.state_size u32              = 128
llama_model_loader: - kv  30:                     qwen35.ssm.group_count u32              = 16
llama_model_loader: - kv  31:                  qwen35.ssm.time_step_rank u32              = 48
llama_model_loader: - kv  32:                      qwen35.ssm.inner_size u32              = 6144
llama_model_loader: - kv  33:             qwen35.full_attention_interval u32              = 4
llama_model_loader: - kv  34:                qwen35.rope.dimension_count u32              = 64
llama_model_loader: - kv  35:                       tokenizer.ggml.model str              = gpt2
llama_model_loader: - kv  36:                         tokenizer.ggml.pre str              = qwen35
llama_model_loader: - kv  37:                      tokenizer.ggml.tokens arr[str,248320]  = ["!", "\"", "#", "$", "%", "&", "'", ...
llama_model_loader: - kv  38:                  tokenizer.ggml.token_type arr[i32,248320]  = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ...
llama_model_loader: - kv  39:                      tokenizer.ggml.merges arr[str,247587]  = ["Ġ Ġ", "ĠĠ ĠĠ", "i n", "Ġ t",...
llama_model_loader: - kv  40:                tokenizer.ggml.eos_token_id u32              = 248046
llama_model_loader: - kv  41:            tokenizer.ggml.padding_token_id u32              = 248055
llama_model_loader: - kv  42:                    tokenizer.chat_template str              = {%- set image_count = namespace(value...
llama_model_loader: - kv  43:               general.quantization_version u32              = 2
llama_model_loader: - kv  44:                          general.file_type u32              = 15
llama_model_loader: - kv  45:                      quantize.imatrix.file str              = Qwen3.5-27B-GGUF/imatrix_unsloth.gguf
llama_model_loader: - kv  46:                   quantize.imatrix.dataset str              = unsloth_calibration_Qwen3.5-27B.txt
llama_model_loader: - kv  47:             quantize.imatrix.entries_count u32              = 496
llama_model_loader: - kv  48:              quantize.imatrix.chunks_count u32              = 80
llama_model_loader: - type  f32:  353 tensors
llama_model_loader: - type q8_0:   96 tensors
llama_model_loader: - type q4_K:  263 tensors
llama_model_loader: - type q5_K:   96 tensors
llama_model_loader: - type q6_K:   43 tensors
print_info: file format = GGUF V3 (latest)
print_info: file type   = Q4_K - Medium
print_info: file size   = 15.58 GiB (4.98 BPW) 
llama_model_load: error loading model: error loading model architecture: unknown model architecture: 'qwen35'
llama_model_load_from_file_impl: failed to load model

OS

Linux

GPU

AMD

CPU

AMD

Ollama version

0.17.5

extent analysis

Fix Plan

To resolve the issue of loading the model, we need to address the "unknown model architecture" error. The error message indicates that the model architecture 'qwen35' is not recognized.

Here are the steps to fix the issue:

Check the model configuration and ensure that the architecture is correctly specified.
Verify that the model file is not corrupted and is compatible with the Ollama version being used.
Update the Ollama version to the latest release, as the issue might be resolved in a newer version.

Code Changes

No code changes are required for this fix. However, you can try to specify the model architecture explicitly when loading the model.

For example:

model = load_model('qwen35', architecture='qwen35')

Replace 'qwen35' with the correct architecture name if it's different.

Configuration Changes

Check the ollama.cfg file and ensure that the model architecture is correctly configured.

Verification

After applying the fix, try loading the model again and verify that it loads successfully. You can do this by running the following command:

ollama --load-model Qwen3.5-27B

If the model loads successfully, you should see a message indicating that the model has been loaded.

Extra Tips

Ensure that the model file is not corrupted by checking its integrity using tools like md5sum or sha256sum.
If you're using a custom model, verify that it's compatible with the Ollama version being used.
Check the Ollama documentation for any specific requirements or restrictions on model architectures.

Vote matrix · Quick signals

Works

Did the solution work? Tap to confirm.

Easy Fix

Was it a quick fix?

Time Saver

Did it save you time?

Blocking

Was it severely blocking?

Common Issue

Are others likely hitting this too?

Flaky / Intermittent

Is it intermittent?

Verified / Reproducible

Can you reproduce it reliably?

#api #ssr #installation #tensor shape #autograd error #prompt formatting #chain error #conversation history

Still need to ship something?

×6

Another batch ranked right after the header list — different links, same matching logic.

Data

Security

Network

Code

UI/UX

Text

System

Multimedia

Protocol

API

Engineering

ollama - 💡(How to fix) Fix Qwen GGML models do not load with 0.17.5 [1 participants]

Recommended Tools

GitHub issue graph ai analysis

Error Message

Code Example

What is the issue?

Relevant log output

OS

GPU

CPU

Ollama version

extent analysis

Fix Plan

Code Changes

Configuration Changes

Verification

Extra Tips

Still need to ship something?

TRENDING

ollama - 💡(How to fix) Fix Qwen GGML models do not load with 0.17.5 [1 participants]

Recommended Tools

GitHub issue graph ai analysis

Error Message

Code Example

What is the issue?

Relevant log output

OS

GPU

CPU

Ollama version

extent analysis

Fix Plan

Code Changes

Configuration Changes

Verification

Extra Tips

Still need to ship something?

RELATED_DISCOVERY

TRENDING