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 #15541] Metal backend crash on Apple Silicon M5: MTLLibrary bfloat/half mismatch causes llama runner termination (500) #35690

New Issue
Closed
opened 2026-04-22 20:22:32 -05:00 by GiteaMirror · 3 comments
GiteaMirror commented 2026-04-22 20:22:32 -05:00
Owner
Copy Link

Originally created by @rahul238xaviers on GitHub (Apr 13, 2026).
Original GitHub issue: https://github.com/ollama/ollama/issues/15541

Summary

Ollama consistently fails to run any model due to a Metal backend initialization failure. The runner process terminates and the API returns 500.

Environment

  • Ollama version: 0.20.6
  • Platform: macOS 26.3.1 (build 25D771280a)
  • Hardware: Apple Silicon M5
  • Install type: Ollama desktop app + CLI
  • Reproducibility: 100% (all tested models)

Steps to Reproduce

  1. Start Ollama.
  2. Run any model prompt, for example:
    • ollama run gemma2:2b "Hello"
  3. Observe server-side runner crash and client-side 500 error.

Expected Behavior

Model loads successfully and returns a response.

Actual Behavior

Model load fails during Metal initialization; llama runner exits; client receives:

  • 500 Internal Server Error: llama runner process has terminated: %!w(<nil>)

Error Signature (sanitized)

  • static_assert failed: Input types must match cooperative tensor types
  • bfloat/half mismatch in MetalPerformancePrimitives matmul path
  • ggml_metal_init: error: failed to initialize the Metal library
  • llama_init_from_model: failed to initialize the context: failed to initialize Metal backend
  • panic: unable to create llama context
  • llama runner terminated: exit status 2

Representative framework references:

  • /System/Library/Frameworks/MetalPerformancePrimitives.framework/Headers/__impl/MPPTensorOpsMatMul2dImpl.h:3266
  • /System/Library/Frameworks/MetalPerformancePrimitives.framework/Headers/__impl/MPPTensorOpsMatMul2dImpl.h:3267

Additional Observations

  • Failure occurs across multiple models, not model-specific.
  • Model blobs download and verification succeed.
  • Runtime fails at backend initialization stage.

Workarounds Tried

  • Reinstall Ollama
  • Install/update Xcode and Metal toolchain components
  • Restart app/processes
  • Alternate host/port setup
  • Disable flash attention
  • KV cache type adjustments

Result: same failure path in Metal backend.

Impact

Ollama is unusable for inference in this environment because all model runs terminate before serving.

Privacy Note

All user-identifying information and local absolute paths have been redacted.

Originally created by @rahul238xaviers on GitHub (Apr 13, 2026). Original GitHub issue: https://github.com/ollama/ollama/issues/15541 ## Summary Ollama consistently fails to run any model due to a Metal backend initialization failure. The runner process terminates and the API returns 500. ## Environment - Ollama version: 0.20.6 - Platform: macOS 26.3.1 (build 25D771280a) - Hardware: Apple Silicon M5 - Install type: Ollama desktop app + CLI - Reproducibility: 100% (all tested models) ## Steps to Reproduce 1. Start Ollama. 2. Run any model prompt, for example: - `ollama run gemma2:2b "Hello"` 3. Observe server-side runner crash and client-side 500 error. ## Expected Behavior Model loads successfully and returns a response. ## Actual Behavior Model load fails during Metal initialization; llama runner exits; client receives: - `500 Internal Server Error: llama runner process has terminated: %!w(<nil>)` ## Error Signature (sanitized) - static_assert failed: `Input types must match cooperative tensor types` - bfloat/half mismatch in MetalPerformancePrimitives matmul path - `ggml_metal_init: error: failed to initialize the Metal library` - `llama_init_from_model: failed to initialize the context: failed to initialize Metal backend` - `panic: unable to create llama context` - `llama runner terminated: exit status 2` Representative framework references: - `/System/Library/Frameworks/MetalPerformancePrimitives.framework/Headers/__impl/MPPTensorOpsMatMul2dImpl.h:3266` - `/System/Library/Frameworks/MetalPerformancePrimitives.framework/Headers/__impl/MPPTensorOpsMatMul2dImpl.h:3267` ## Additional Observations - Failure occurs across multiple models, not model-specific. - Model blobs download and verification succeed. - Runtime fails at backend initialization stage. ## Workarounds Tried - Reinstall Ollama - Install/update Xcode and Metal toolchain components - Restart app/processes - Alternate host/port setup - Disable flash attention - KV cache type adjustments Result: same failure path in Metal backend. ## Impact Ollama is unusable for inference in this environment because all model runs terminate before serving. ## Privacy Note All user-identifying information and local absolute paths have been redacted.
GiteaMirror commented 2026-04-22 20:22:34 -05:00
Author
Owner
Copy Link

@tjtoed commented on GitHub (Apr 13, 2026):

Same issue here on a new Macbook Pro M5 running 26.2 25C56 and Ollama 0.20.6

<!-- gh-comment-id:4236937547 --> @tjtoed commented on GitHub (Apr 13, 2026): Same issue here on a new Macbook Pro M5 running 26.2 25C56 and Ollama 0.20.6
GiteaMirror commented 2026-04-22 20:22:34 -05:00
Author
Owner
Copy Link

@rahul238xaviers commented on GitHub (Apr 13, 2026):

Same issue here on a new Macbook Pro M5 running 26.2 25C56 and Ollama 0.20.6

I have just finished the update of mac os and now it has started working. Seems like the compatibility issue was with the metal library. Will keep this issue open until I verify with the larger model and then will close it.

Image
<!-- gh-comment-id:4236971741 --> @rahul238xaviers commented on GitHub (Apr 13, 2026): > Same issue here on a new Macbook Pro M5 running 26.2 25C56 and Ollama 0.20.6 I have just finished the update of mac os and now it has started working. Seems like the compatibility issue was with the metal library. Will keep this issue open until I verify with the larger model and then will close it. <img width="984" height="212" alt="Image" src="https://github.com/user-attachments/assets/15e73586-e204-4deb-ba1c-cdf6d9da05e3" />
GiteaMirror commented 2026-04-22 20:22:36 -05:00
Author
Owner
Copy Link

@rahul238xaviers commented on GitHub (Apr 13, 2026):

Confirmed, the Mac OS update resolved the issue.

Image
<!-- gh-comment-id:4237049670 --> @rahul238xaviers commented on GitHub (Apr 13, 2026): Confirmed, the Mac OS update resolved the issue. <img width="1172" height="264" alt="Image" src="https://github.com/user-attachments/assets/04cc25f6-2185-40bc-885d-8ebf4510ce8f" />
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
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#35690
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?