github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-07-17 21:55:43 -05:00
Code Issues 16.9k Packages Projects Releases 122 Wiki Activity

[GH-ISSUE #15577] gemma4:26b / 36b MLX 500 Internal Server Error on 0.20.8-rc0 #87633

New Issue
Closed
opened 2026-05-10 06:11:01 -05:00 by GiteaMirror · 3 comments
GiteaMirror commented 2026-05-10 06:11:01 -05:00
Owner
Copy Link

Originally created by @jregeimbal on GitHub (Apr 14, 2026).
Original GitHub issue: https://github.com/ollama/ollama/issues/15577

What is the issue?

Hi Ollama team,

I have been watching the dev on MLX support closely (https://github.com/ollama/ollama/pull/15244) and wanted to give the RC a spin last night. Just wanted to report that it does not appear to be working on an M5 Max.

If there are other details I can pull that would be useful, let me know.

cc @dhiltgen

~/Dev/jregeimbal/homelab on  main took 2m56s
❯ ollama run dhiltgen/gemma4:26b --verbose <<< "Write a Python code that implements binary search in insert,delete and search operations"                                                                07:28:43 AM
Error: 500 Internal Server Error: unable to load model: /Users/jonregeimbal/.ollama/models/blobs/sha256-27d4493f796da888a1c50d6d43876e446dbe697cd4c4330c44a063d468e35a52

~/Dev/jregeimbal/homelab on  main
❯ ollama run dhiltgen/gemma4:31b --verbose <<< "Write a Python code that implements binary search in insert,delete and search operations"                                                                07:42:05 AM
Error: 500 Internal Server Error: unable to load model: /Users/jonregeimbal/.ollama/models/blobs/sha256-5146d9e5f94c7e8793b56789a863ecaa36bf22affb5cecbae267cf835a5cbad9

~/Dev/jregeimbal/homelab on  main
❯ ollama --version                                                                                                                                                                                       07:42:19 AM
ollama version is 0.20.8-rc0

Non-MLX models are still running fine:

❯ ollama run gemma4:26b --verbose <<< "Write a Python code that implements binary search in insert,delete and search operations"                                                                         07:43:41 AM
Thinking...

*   Task: Imp...

Relevant log output

❯ cat ~/.ollama/logs/server.log | tail -10                                                                                                                                                               07:43:24 AM
llama_model_loader: - type q8_0:   28 tensors
llama_model_loader: - type q4_K:  192 tensors
llama_model_loader: - type q6_K:   14 tensors
print_info: file format = GGUF V3 (latest)
print_info: file type   = Q4_K - Medium
print_info: file size   = 15.63 GiB (5.32 BPW)
llama_model_load: error loading model: error loading model architecture: unknown model architecture: 'gemma4'
llama_model_load_from_file_impl: failed to load model
time=2026-04-14T07:43:24.686-04:00 level=INFO source=sched.go:462 msg="failed to create server" model=dhiltgen/gemma4:26b error="unable to load model: /Users/jonregeimbal/.ollama/models/blobs/sha256-27d4493f796da888a1c50d6d43876e446dbe697cd4c4330c44a063d468e35a52"
[GIN] 2026/04/14 - 07:43:24 | 500 |  276.203459ms |       127.0.0.1 | POST     "/api/generate"

OS

macOS

GPU

Apple

CPU

Apple

Ollama version

0.20.8-rc0

Originally created by @jregeimbal on GitHub (Apr 14, 2026). Original GitHub issue: https://github.com/ollama/ollama/issues/15577 ### What is the issue? Hi Ollama team, I have been watching the dev on MLX support closely (https://github.com/ollama/ollama/pull/15244) and wanted to give the RC a spin last night. Just wanted to report that it does not appear to be working on an M5 Max. If there are other details I can pull that would be useful, let me know. cc @dhiltgen ``` ~/Dev/jregeimbal/homelab on  main took 2m56s ❯ ollama run dhiltgen/gemma4:26b --verbose <<< "Write a Python code that implements binary search in insert,delete and search operations" 07:28:43 AM Error: 500 Internal Server Error: unable to load model: /Users/jonregeimbal/.ollama/models/blobs/sha256-27d4493f796da888a1c50d6d43876e446dbe697cd4c4330c44a063d468e35a52 ~/Dev/jregeimbal/homelab on  main ❯ ollama run dhiltgen/gemma4:31b --verbose <<< "Write a Python code that implements binary search in insert,delete and search operations" 07:42:05 AM Error: 500 Internal Server Error: unable to load model: /Users/jonregeimbal/.ollama/models/blobs/sha256-5146d9e5f94c7e8793b56789a863ecaa36bf22affb5cecbae267cf835a5cbad9 ~/Dev/jregeimbal/homelab on  main ❯ ollama --version 07:42:19 AM ollama version is 0.20.8-rc0 ``` Non-MLX models are still running fine: ``` ❯ ollama run gemma4:26b --verbose <<< "Write a Python code that implements binary search in insert,delete and search operations" 07:43:41 AM Thinking... * Task: Imp... ``` ### Relevant log output ```shell ❯ cat ~/.ollama/logs/server.log | tail -10 07:43:24 AM llama_model_loader: - type q8_0: 28 tensors llama_model_loader: - type q4_K: 192 tensors llama_model_loader: - type q6_K: 14 tensors print_info: file format = GGUF V3 (latest) print_info: file type = Q4_K - Medium print_info: file size = 15.63 GiB (5.32 BPW) llama_model_load: error loading model: error loading model architecture: unknown model architecture: 'gemma4' llama_model_load_from_file_impl: failed to load model time=2026-04-14T07:43:24.686-04:00 level=INFO source=sched.go:462 msg="failed to create server" model=dhiltgen/gemma4:26b error="unable to load model: /Users/jonregeimbal/.ollama/models/blobs/sha256-27d4493f796da888a1c50d6d43876e446dbe697cd4c4330c44a063d468e35a52" [GIN] 2026/04/14 - 07:43:24 | 500 | 276.203459ms | 127.0.0.1 | POST "/api/generate" ``` ### OS macOS ### GPU Apple ### CPU Apple ### Ollama version 0.20.8-rc0
GiteaMirror added the bug label 2026-05-10 06:11:01 -05:00
GiteaMirror commented 2026-05-10 06:11:03 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Apr 14, 2026):

dhiltgen/gemma4:26b and dhiltgen/gemma4:31b are not MLX models, they are split GGUF models. Split models run on the llama.cpp engine which doesn't have support for gemma4 yet. If you want to try MLX models, try dhiltgen/gemma4:26b-nvfp4 or dhiltgen/gemma4:31b-nvfp4.

<!-- gh-comment-id:4243705093 --> @rick-github commented on GitHub (Apr 14, 2026): dhiltgen/gemma4:26b and dhiltgen/gemma4:31b are not MLX models, they are split GGUF models. Split models run on the llama.cpp engine which doesn't have support for gemma4 yet. If you want to try MLX models, try dhiltgen/gemma4:26b-nvfp4 or dhiltgen/gemma4:31b-nvfp4.
GiteaMirror commented 2026-05-10 06:11:04 -05:00
Author
Owner
Copy Link

@jregeimbal commented on GitHub (Apr 14, 2026):

@rick-github THANKS - missed the view all. Closing this :)

<!-- gh-comment-id:4244966115 --> @jregeimbal commented on GitHub (Apr 14, 2026): @rick-github THANKS - missed the [view all](https://ollama.com/dhiltgen/gemma4/tags). Closing this :)
GiteaMirror commented 2026-05-10 06:11:05 -05:00
Author
Owner
Copy Link

@dhiltgen commented on GitHub (Apr 14, 2026):

Sorry for the confusion. The MLX tags are now pushed to the library, so you should be able to run "ollama run gemma4:26b-nvfp4" on the RC.

<!-- gh-comment-id:4245094283 --> @dhiltgen commented on GitHub (Apr 14, 2026): Sorry for the confusion. The MLX tags are now pushed to the library, so you should be able to run "ollama run gemma4:26b-nvfp4" on the RC.
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#87633
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?