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 #11663] Error: 500 Internal Server Error: unable to load model with "alibayram/smollm3:latest" and "alibayram/hunyuan:7b" #69770

New Issue
Closed
opened 2026-05-04 19:08:31 -05:00 by GiteaMirror · 7 comments
GiteaMirror commented 2026-05-04 19:08:31 -05:00
Owner
Copy Link

Originally created by @SilentWhiteRabbit on GitHub (Aug 5, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/11663

What is the issue?

hello, when i use ollama to run 【alibayram/smollm3:latest】and 【alibayram/hunyuan:7b】,this error happens.i will use【alibayram/hunyuan:7b】as an example:

C:\Users\xxx>ollama run alibayram/hunyuan:7b
Error: 500 Internal Server Error: unable to load model: C:\Users\xxx.ollama\models\blobs\sha256-e59a4dd7d94142c65e0aef5e20b0a44637467b472628dac00dfe9be23dc4d18d

and I also use deepseek-r1:8b to test，it‘s ok.

C:\Users\xxx>ollama run alibayram/hunyuan:7b
Error: 500 Internal Server Error: unable to load model: C:\Users\xxx.ollama\models\blobs\sha256-e59a4dd7d94142c65e0aef5e20b0a44637467b472628dac00dfe9be23dc4d18d
C:\Users\xxx>ollama run deepseek-r1:8b
>>>

so may there some wrong with 【alibayram/smollm3:latest】and 【alibayram/hunyuan:7b】

Relevant log output

this is logs，i use 【alibayram/hunyuan:7b】 as an example.
app.log has no change.

server.log's change as follows：

[GIN] 2025/08/05 - 17:14:40 | 200 |            0s |       127.0.0.1 | HEAD     "/"
[GIN] 2025/08/05 - 17:14:40 | 200 |    225.4768ms |       127.0.0.1 | POST     "/api/show"
time=2025-08-05T17:14:41.107+08:00 level=INFO source=server.go:135 msg="system memory" total="31.7 GiB" free="9.8 GiB" free_swap="7.4 GiB"
time=2025-08-05T17:14:41.108+08:00 level=INFO source=server.go:175 msg=offload library=cuda layers.requested=-1 layers.model=33 layers.offload=10 layers.split="" memory.available="[6.0 GiB]" memory.gpu_overhead="0 B" memory.required.full="11.7 GiB" memory.required.partial="5.9 GiB" memory.required.kv="4.0 GiB" memory.required.allocations="[5.9 GiB]" memory.weights.total="4.3 GiB" memory.weights.repeating="3.9 GiB" memory.weights.nonrepeating="410.7 MiB" memory.graph.full="2.7 GiB" memory.graph.partial="2.7 GiB"
llama_model_loader: loaded meta data with 39 key-value pairs and 354 tensors from C:\Users\xxx\.ollama\models\blobs\sha256-e59a4dd7d94142c65e0aef5e20b0a44637467b472628dac00dfe9be23dc4d18d (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              = hunyuan-dense
llama_model_loader: - kv   1:                               general.type str              = model
llama_model_loader: - kv   2:                               general.name str              = Hunyuan 7B Instruct
llama_model_loader: - kv   3:                           general.finetune str              = Instruct
llama_model_loader: - kv   4:                           general.basename str              = Hunyuan
llama_model_loader: - kv   5:                         general.size_label str              = 7B
llama_model_loader: - kv   6:                   general.base_model.count u32              = 1
llama_model_loader: - kv   7:                  general.base_model.0.name str              = Hunyuan 7B Pretrain
llama_model_loader: - kv   8:          general.base_model.0.organization str              = Tencent
llama_model_loader: - kv   9:              general.base_model.0.repo_url str              = https://huggingface.co/tencent/Hunyua...
llama_model_loader: - kv  10:                  hunyuan-dense.block_count u32              = 32
llama_model_loader: - kv  11:               hunyuan-dense.context_length u32              = 262144
llama_model_loader: - kv  12:             hunyuan-dense.embedding_length u32              = 4096
llama_model_loader: - kv  13:          hunyuan-dense.feed_forward_length u32              = 14336
llama_model_loader: - kv  14:         hunyuan-dense.attention.head_count u32              = 32
llama_model_loader: - kv  15:      hunyuan-dense.attention.head_count_kv u32              = 8
llama_model_loader: - kv  16:               hunyuan-dense.rope.freq_base f32              = 11158840.000000
llama_model_loader: - kv  17: hunyuan-dense.attention.layer_norm_rms_epsilon f32              = 0.000010
llama_model_loader: - kv  18:         hunyuan-dense.attention.key_length u32              = 128
llama_model_loader: - kv  19:       hunyuan-dense.attention.value_length u32              = 128
llama_model_loader: - kv  20:            hunyuan-dense.rope.scaling.type str              = none
llama_model_loader: - kv  21:          hunyuan-dense.rope.scaling.factor f32              = 1.000000
llama_model_loader: - kv  22: hunyuan-dense.rope.scaling.original_context_length u32              = 262144
llama_model_loader: - kv  23:                       tokenizer.ggml.model str              = gpt2
llama_model_loader: - kv  24:                         tokenizer.ggml.pre str              = hunyuan
llama_model_loader: - kv  25:                      tokenizer.ggml.tokens arr[str,128167]  = ["!", "\"", "#", "$", "%", "&", "'", ...
llama_model_loader: - kv  26:                  tokenizer.ggml.token_type arr[i32,128167]  = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ...
llama_model_loader: - kv  27:                      tokenizer.ggml.merges arr[str,127698]  = ["Ġ Ġ", "ĠĠ ĠĠ", "i n", "Ġ t",...
llama_model_loader: - kv  28:                tokenizer.ggml.bos_token_id u32              = 127958
llama_model_loader: - kv  29:                tokenizer.ggml.eos_token_id u32              = 127960
llama_model_loader: - kv  30:          tokenizer.ggml.seperator_token_id u32              = 127962
llama_model_loader: - kv  31:            tokenizer.ggml.padding_token_id u32              = 127961
llama_model_loader: - kv  32:                    tokenizer.chat_template str              = {%- if not add_generation_prompt is d...
llama_model_loader: - kv  33:               general.quantization_version u32              = 2
llama_model_loader: - kv  34:                          general.file_type u32              = 15
llama_model_loader: - kv  35:                      quantize.imatrix.file str              = Hunyuan-7B-Instruct/Hunyuan-7B-Instru...
llama_model_loader: - kv  36:                   quantize.imatrix.dataset str              = calibration_datav3.txt
llama_model_loader: - kv  37:             quantize.imatrix.entries_count u32              = 224
llama_model_loader: - kv  38:              quantize.imatrix.chunks_count u32              = 130
llama_model_loader: - type  f32:  129 tensors
llama_model_loader: - type q4_K:  192 tensors
llama_model_loader: - type q6_K:   33 tensors
print_info: file format = GGUF V3 (latest)
print_info: file type   = Q4_K - Medium
print_info: file size   = 4.30 GiB (4.92 BPW) 
llama_model_load: error loading model: error loading model architecture: unknown model architecture: 'hunyuan-dense'
llama_model_load_from_file_impl: failed to load model
time=2025-08-05T17:14:41.554+08:00 level=INFO source=sched.go:453 msg="NewLlamaServer failed" model=C:\Users\xxx\.ollama\models\blobs\sha256-e59a4dd7d94142c65e0aef5e20b0a44637467b472628dac00dfe9be23dc4d18d error="unable to load model: C:\\Users\\xxx\\.ollama\\models\\blobs\\sha256-e59a4dd7d94142c65e0aef5e20b0a44637467b472628dac00dfe9be23dc4d18d"
[GIN] 2025/08/05 - 17:14:41 | 500 |    805.9905ms |       127.0.0.1 | POST     "/api/generate"

OS

Windows

GPU

Nvidia

CPU

Intel

Ollama version

0.10.1

Originally created by @SilentWhiteRabbit on GitHub (Aug 5, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/11663 ### What is the issue? hello, when i use ollama to run 【alibayram/smollm3:latest】and 【alibayram/hunyuan:7b】,this error happens.i will use【alibayram/hunyuan:7b】as an example: > C:\Users\xxx>ollama run alibayram/hunyuan:7b > Error: 500 Internal Server Error: unable to load model: C:\Users\xxx\.ollama\models\blobs\sha256-e59a4dd7d94142c65e0aef5e20b0a44637467b472628dac00dfe9be23dc4d18d and I also use deepseek-r1:8b to test，it‘s ok. > C:\Users\xxx>ollama run alibayram/hunyuan:7b > Error: 500 Internal Server Error: unable to load model: C:\Users\xxx\.ollama\models\blobs\sha256-e59a4dd7d94142c65e0aef5e20b0a44637467b472628dac00dfe9be23dc4d18d > C:\Users\xxx>ollama run deepseek-r1:8b > \>\>\> so may there some wrong with 【alibayram/smollm3:latest】and 【alibayram/hunyuan:7b】 ### Relevant log output ```shell this is logs，i use 【alibayram/hunyuan:7b】 as an example. app.log has no change. server.log's change as follows： [GIN] 2025/08/05 - 17:14:40 | 200 | 0s | 127.0.0.1 | HEAD "/" [GIN] 2025/08/05 - 17:14:40 | 200 | 225.4768ms | 127.0.0.1 | POST "/api/show" time=2025-08-05T17:14:41.107+08:00 level=INFO source=server.go:135 msg="system memory" total="31.7 GiB" free="9.8 GiB" free_swap="7.4 GiB" time=2025-08-05T17:14:41.108+08:00 level=INFO source=server.go:175 msg=offload library=cuda layers.requested=-1 layers.model=33 layers.offload=10 layers.split="" memory.available="[6.0 GiB]" memory.gpu_overhead="0 B" memory.required.full="11.7 GiB" memory.required.partial="5.9 GiB" memory.required.kv="4.0 GiB" memory.required.allocations="[5.9 GiB]" memory.weights.total="4.3 GiB" memory.weights.repeating="3.9 GiB" memory.weights.nonrepeating="410.7 MiB" memory.graph.full="2.7 GiB" memory.graph.partial="2.7 GiB" llama_model_loader: loaded meta data with 39 key-value pairs and 354 tensors from C:\Users\xxx\.ollama\models\blobs\sha256-e59a4dd7d94142c65e0aef5e20b0a44637467b472628dac00dfe9be23dc4d18d (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 = hunyuan-dense llama_model_loader: - kv 1: general.type str = model llama_model_loader: - kv 2: general.name str = Hunyuan 7B Instruct llama_model_loader: - kv 3: general.finetune str = Instruct llama_model_loader: - kv 4: general.basename str = Hunyuan llama_model_loader: - kv 5: general.size_label str = 7B llama_model_loader: - kv 6: general.base_model.count u32 = 1 llama_model_loader: - kv 7: general.base_model.0.name str = Hunyuan 7B Pretrain llama_model_loader: - kv 8: general.base_model.0.organization str = Tencent llama_model_loader: - kv 9: general.base_model.0.repo_url str = https://huggingface.co/tencent/Hunyua... llama_model_loader: - kv 10: hunyuan-dense.block_count u32 = 32 llama_model_loader: - kv 11: hunyuan-dense.context_length u32 = 262144 llama_model_loader: - kv 12: hunyuan-dense.embedding_length u32 = 4096 llama_model_loader: - kv 13: hunyuan-dense.feed_forward_length u32 = 14336 llama_model_loader: - kv 14: hunyuan-dense.attention.head_count u32 = 32 llama_model_loader: - kv 15: hunyuan-dense.attention.head_count_kv u32 = 8 llama_model_loader: - kv 16: hunyuan-dense.rope.freq_base f32 = 11158840.000000 llama_model_loader: - kv 17: hunyuan-dense.attention.layer_norm_rms_epsilon f32 = 0.000010 llama_model_loader: - kv 18: hunyuan-dense.attention.key_length u32 = 128 llama_model_loader: - kv 19: hunyuan-dense.attention.value_length u32 = 128 llama_model_loader: - kv 20: hunyuan-dense.rope.scaling.type str = none llama_model_loader: - kv 21: hunyuan-dense.rope.scaling.factor f32 = 1.000000 llama_model_loader: - kv 22: hunyuan-dense.rope.scaling.original_context_length u32 = 262144 llama_model_loader: - kv 23: tokenizer.ggml.model str = gpt2 llama_model_loader: - kv 24: tokenizer.ggml.pre str = hunyuan llama_model_loader: - kv 25: tokenizer.ggml.tokens arr[str,128167] = ["!", "\"", "#", "$", "%", "&", "'", ... llama_model_loader: - kv 26: tokenizer.ggml.token_type arr[i32,128167] = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ... llama_model_loader: - kv 27: tokenizer.ggml.merges arr[str,127698] = ["Ġ Ġ", "ĠĠ ĠĠ", "i n", "Ġ t",... llama_model_loader: - kv 28: tokenizer.ggml.bos_token_id u32 = 127958 llama_model_loader: - kv 29: tokenizer.ggml.eos_token_id u32 = 127960 llama_model_loader: - kv 30: tokenizer.ggml.seperator_token_id u32 = 127962 llama_model_loader: - kv 31: tokenizer.ggml.padding_token_id u32 = 127961 llama_model_loader: - kv 32: tokenizer.chat_template str = {%- if not add_generation_prompt is d... llama_model_loader: - kv 33: general.quantization_version u32 = 2 llama_model_loader: - kv 34: general.file_type u32 = 15 llama_model_loader: - kv 35: quantize.imatrix.file str = Hunyuan-7B-Instruct/Hunyuan-7B-Instru... llama_model_loader: - kv 36: quantize.imatrix.dataset str = calibration_datav3.txt llama_model_loader: - kv 37: quantize.imatrix.entries_count u32 = 224 llama_model_loader: - kv 38: quantize.imatrix.chunks_count u32 = 130 llama_model_loader: - type f32: 129 tensors llama_model_loader: - type q4_K: 192 tensors llama_model_loader: - type q6_K: 33 tensors print_info: file format = GGUF V3 (latest) print_info: file type = Q4_K - Medium print_info: file size = 4.30 GiB (4.92 BPW) llama_model_load: error loading model: error loading model architecture: unknown model architecture: 'hunyuan-dense' llama_model_load_from_file_impl: failed to load model time=2025-08-05T17:14:41.554+08:00 level=INFO source=sched.go:453 msg="NewLlamaServer failed" model=C:\Users\xxx\.ollama\models\blobs\sha256-e59a4dd7d94142c65e0aef5e20b0a44637467b472628dac00dfe9be23dc4d18d error="unable to load model: C:\\Users\\xxx\\.ollama\\models\\blobs\\sha256-e59a4dd7d94142c65e0aef5e20b0a44637467b472628dac00dfe9be23dc4d18d" [GIN] 2025/08/05 - 17:14:41 | 500 | 805.9905ms | 127.0.0.1 | POST "/api/generate" ``` ### OS Windows ### GPU Nvidia ### CPU Intel ### Ollama version 0.10.1
GiteaMirror added the bug label 2026-05-04 19:08:31 -05:00
GiteaMirror commented 2026-05-04 19:08:37 -05:00
Author
Owner
Copy Link

@SilentWhiteRabbit commented on GitHub (Aug 5, 2025):

【alibayram/smollm3:latest】has the similiar log：

llama_model_load: error loading model: error loading model architecture: unknown model architecture: 'smollm3'
llama_model_load_from_file_impl: failed to load model

<!-- gh-comment-id:3154274335 --> @SilentWhiteRabbit commented on GitHub (Aug 5, 2025): 【alibayram/smollm3:latest】has the similiar log： llama_model_load: error loading model: error loading model architecture: unknown model architecture: 'smollm3' llama_model_load_from_file_impl: failed to load model
GiteaMirror commented 2026-05-04 19:08:39 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Aug 5, 2025):

These models are currently unsupported on ollama.

<!-- gh-comment-id:3154675728 --> @rick-github commented on GitHub (Aug 5, 2025): These models are currently unsupported on ollama.
GiteaMirror commented 2026-05-04 19:08:40 -05:00
Author
Owner
Copy Link

@printlndarling commented on GitHub (Aug 5, 2025):

These models are currently unsupported on ollama.

Hi, I'm running into the same issue where hunyuan-dense isn't supported by Ollama. It seems like an architecture compatibility problem. Are there plans to support it in the future? Thanks!

<!-- gh-comment-id:3155811344 --> @printlndarling commented on GitHub (Aug 5, 2025): > These models are currently unsupported on ollama. Hi, I'm running into the same issue where hunyuan-dense isn't supported by Ollama. It seems like an architecture compatibility problem. Are there plans to support it in the future? Thanks!
GiteaMirror commented 2026-05-04 19:08:41 -05:00
Author
Owner
Copy Link

@jmcastagnetto commented on GitHub (Aug 10, 2025):

I think it is related to what is discussed in this issue: https://github.com/ollama/ollama/issues/2232#issuecomment-3165046147

<!-- gh-comment-id:3172753776 --> @jmcastagnetto commented on GitHub (Aug 10, 2025): I think it is related to what is discussed in this issue: https://github.com/ollama/ollama/issues/2232#issuecomment-3165046147
GiteaMirror commented 2026-05-04 19:08:41 -05:00
Author
Owner
Copy Link

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

These models are currently unsupported on ollama.

#11823 should add support.

<!-- gh-comment-id:3172764368 --> @rick-github commented on GitHub (Aug 10, 2025): These models are currently unsupported on ollama. #11823 should add support.
GiteaMirror commented 2026-05-04 19:08:42 -05:00
Author
Owner
Copy Link

@fabiomatricardi commented on GitHub (Aug 13, 2025):

so why are they present in the official Ollama model hub?

<!-- gh-comment-id:3182184024 --> @fabiomatricardi commented on GitHub (Aug 13, 2025): so why are they present in the official Ollama model hub?
GiteaMirror commented 2026-05-04 19:08:43 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Aug 13, 2025):

They are not in the official ollama model hub. They are in the user uploaded model hub.

<!-- gh-comment-id:3182374724 --> @rick-github commented on GitHub (Aug 13, 2025): They are not in the official ollama model hub. They are in the user uploaded model hub.
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#69770
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?