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 #14524] Unknown model architecture: 'qwen35' when loading bazobehram/qwen3.5-flash-27b #71483

New Issue
Closed
opened 2026-05-05 01:53:06 -05:00 by GiteaMirror · 0 comments
GiteaMirror commented 2026-05-05 01:53:06 -05:00
Owner
Copy Link

Originally created by @sanel on GitHub (Mar 1, 2026).
Original GitHub issue: https://github.com/ollama/ollama/issues/14524

What is the issue?

Hi guys, I'm getting this error after I'm trying to load bazobehram/qwen3.5-flash-27b and sparksammy/qwen3.5-27b-unsloth:small-hotfixed models via:

ollama run bazobehram/qwen3.5-flash-27b

# or
ollama run sparksammy/qwen3.5-27b-unsloth:small-hotfixed

Any idea what is going on? GPU is Nvidia RTX 4000 ADA Gen.

Relevant log output

time=2026-03-01T09:56:41.919Z level=INFO source=server.go:431 msg="starting runner" cmd="/opt/ollama/bin/ollama runner --ollama-engine --port 36945"
 llama_model_loader: loaded meta data with 39 key-value pairs and 851 tensors from /var/lib/ollama/.ollama/models/blobs/sha256-d4d089fbfa2a2ef034faa5c99a1743523ce69a18c562f7de0>
 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              = Hf
 llama_model_loader: - kv   6:                         general.size_label str              = 27B
 llama_model_loader: - kv   7:                            general.license str              = apache-2.0
 llama_model_loader: - kv   8:                       general.license.link str              = https://huggingface.co/Qwen/Qwen3.5-2...
 llama_model_loader: - kv   9:                               general.tags arr[str,1]       = ["image-text-to-text"]
 llama_model_loader: - kv  10:                         qwen35.block_count u32              = 64
 llama_model_loader: - kv  11:                      qwen35.context_length u32              = 262144
 llama_model_loader: - kv  12:                    qwen35.embedding_length u32              = 5120
 llama_model_loader: - kv  13:                 qwen35.feed_forward_length u32              = 17408
 llama_model_loader: - kv  14:                qwen35.attention.head_count u32              = 24
 llama_model_loader: - kv  15:             qwen35.attention.head_count_kv u32              = 4
 llama_model_loader: - kv  16:             qwen35.rope.dimension_sections arr[i32,4]       = [11, 11, 10, 0]
 llama_model_loader: - kv  17:                      qwen35.rope.freq_base f32              = 10000000.000000
 llama_model_loader: - kv  18:    qwen35.attention.layer_norm_rms_epsilon f32              = 0.000001
 llama_model_loader: - kv  19:                qwen35.attention.key_length u32              = 256
 llama_model_loader: - kv  20:              qwen35.attention.value_length u32              = 256
 llama_model_loader: - kv  21:                     qwen35.ssm.conv_kernel u32              = 4
 llama_model_loader: - kv  22:                      qwen35.ssm.state_size u32              = 128
 llama_model_loader: - kv  23:                     qwen35.ssm.group_count u32              = 16
 llama_model_loader: - kv  24:                  qwen35.ssm.time_step_rank u32              = 48
 llama_model_loader: - kv  25:                      qwen35.ssm.inner_size u32              = 6144
 llama_model_loader: - kv  26:             qwen35.full_attention_interval u32              = 4
 llama_model_loader: - kv  27:                qwen35.rope.dimension_count u32              = 64
 llama_model_loader: - kv  28:                       tokenizer.ggml.model str              = gpt2
 llama_model_loader: - kv  29:                         tokenizer.ggml.pre str              = qwen35
 llama_model_loader: - kv  30:                      tokenizer.ggml.tokens arr[str,248320]  = ["!", "\"", "#", "$", "%", "&", "'", ...
 llama_model_loader: - kv  31:                  tokenizer.ggml.token_type arr[i32,248320]  = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ...
 llama_model_loader: - kv  32:                      tokenizer.ggml.merges arr[str,247587]  = ["Ġ Ġ", "ĠĠ ĠĠ", "i n", "Ġ t",...
 llama_model_loader: - kv  33:                tokenizer.ggml.eos_token_id u32              = 248046
 llama_model_loader: - kv  34:            tokenizer.ggml.padding_token_id u32              = 248044
 llama_model_loader: - kv  35:               tokenizer.ggml.add_bos_token bool             = false
 llama_model_loader: - kv  36:                    tokenizer.chat_template str              = {%- set image_count = namespace(value...
 llama_model_loader: - kv  37:               general.quantization_version u32              = 2
 llama_model_loader: - kv  38:                          general.file_type u32              = 15
 llama_model_loader: - type  f32:  353 tensors
 llama_model_loader: - type q4_K:  407 tensors
 llama_model_loader: - type q5_K:   48 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   = 15.39 GiB (4.92 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

Nvidia

CPU

Intel

Ollama version

0.17.4

Originally created by @sanel on GitHub (Mar 1, 2026). Original GitHub issue: https://github.com/ollama/ollama/issues/14524 ### What is the issue? Hi guys, I'm getting this error after I'm trying to load `bazobehram/qwen3.5-flash-27b` and `sparksammy/qwen3.5-27b-unsloth:small-hotfixed` models via: ```bash ollama run bazobehram/qwen3.5-flash-27b # or ollama run sparksammy/qwen3.5-27b-unsloth:small-hotfixed ``` Any idea what is going on? GPU is Nvidia RTX 4000 ADA Gen. ### Relevant log output ```shell time=2026-03-01T09:56:41.919Z level=INFO source=server.go:431 msg="starting runner" cmd="/opt/ollama/bin/ollama runner --ollama-engine --port 36945" llama_model_loader: loaded meta data with 39 key-value pairs and 851 tensors from /var/lib/ollama/.ollama/models/blobs/sha256-d4d089fbfa2a2ef034faa5c99a1743523ce69a18c562f7de0> 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 = Hf llama_model_loader: - kv 6: general.size_label str = 27B llama_model_loader: - kv 7: general.license str = apache-2.0 llama_model_loader: - kv 8: general.license.link str = https://huggingface.co/Qwen/Qwen3.5-2... llama_model_loader: - kv 9: general.tags arr[str,1] = ["image-text-to-text"] llama_model_loader: - kv 10: qwen35.block_count u32 = 64 llama_model_loader: - kv 11: qwen35.context_length u32 = 262144 llama_model_loader: - kv 12: qwen35.embedding_length u32 = 5120 llama_model_loader: - kv 13: qwen35.feed_forward_length u32 = 17408 llama_model_loader: - kv 14: qwen35.attention.head_count u32 = 24 llama_model_loader: - kv 15: qwen35.attention.head_count_kv u32 = 4 llama_model_loader: - kv 16: qwen35.rope.dimension_sections arr[i32,4] = [11, 11, 10, 0] llama_model_loader: - kv 17: qwen35.rope.freq_base f32 = 10000000.000000 llama_model_loader: - kv 18: qwen35.attention.layer_norm_rms_epsilon f32 = 0.000001 llama_model_loader: - kv 19: qwen35.attention.key_length u32 = 256 llama_model_loader: - kv 20: qwen35.attention.value_length u32 = 256 llama_model_loader: - kv 21: qwen35.ssm.conv_kernel u32 = 4 llama_model_loader: - kv 22: qwen35.ssm.state_size u32 = 128 llama_model_loader: - kv 23: qwen35.ssm.group_count u32 = 16 llama_model_loader: - kv 24: qwen35.ssm.time_step_rank u32 = 48 llama_model_loader: - kv 25: qwen35.ssm.inner_size u32 = 6144 llama_model_loader: - kv 26: qwen35.full_attention_interval u32 = 4 llama_model_loader: - kv 27: qwen35.rope.dimension_count u32 = 64 llama_model_loader: - kv 28: tokenizer.ggml.model str = gpt2 llama_model_loader: - kv 29: tokenizer.ggml.pre str = qwen35 llama_model_loader: - kv 30: tokenizer.ggml.tokens arr[str,248320] = ["!", "\"", "#", "$", "%", "&", "'", ... llama_model_loader: - kv 31: tokenizer.ggml.token_type arr[i32,248320] = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ... llama_model_loader: - kv 32: tokenizer.ggml.merges arr[str,247587] = ["Ġ Ġ", "ĠĠ ĠĠ", "i n", "Ġ t",... llama_model_loader: - kv 33: tokenizer.ggml.eos_token_id u32 = 248046 llama_model_loader: - kv 34: tokenizer.ggml.padding_token_id u32 = 248044 llama_model_loader: - kv 35: tokenizer.ggml.add_bos_token bool = false llama_model_loader: - kv 36: tokenizer.chat_template str = {%- set image_count = namespace(value... llama_model_loader: - kv 37: general.quantization_version u32 = 2 llama_model_loader: - kv 38: general.file_type u32 = 15 llama_model_loader: - type f32: 353 tensors llama_model_loader: - type q4_K: 407 tensors llama_model_loader: - type q5_K: 48 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 = 15.39 GiB (4.92 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 Nvidia ### CPU Intel ### Ollama version 0.17.4
GiteaMirror added the bug label 2026-05-05 01:53:06 -05:00
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#71483
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?