github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-07-15 20:54:54 -05:00
Code Issues 16.9k Packages Projects Releases 122 Wiki Activity

[GH-ISSUE #14748] qwen3.5:9b model runner crashes on Apple M4 16GB - "model runner has unexpectedly stopped" #56047

New Issue
Closed
opened 2026-04-29 10:11:16 -05:00 by GiteaMirror · 1 comment
GiteaMirror commented 2026-04-29 10:11:16 -05:00
Owner
Copy Link

Originally created by @vpoma777 on GitHub (Mar 9, 2026).
Original GitHub issue: https://github.com/ollama/ollama/issues/14748

What is the issue?

Description

The qwen3.5:9b model (and the custom modelfile qwen-vialetto-fix based on qwen2.5vl:7b)
crashes immediately when loaded on Apple M4 16GB unified memory with error:

"model runner has unexpectedly stopped, this may be due to resource limitations
or an internal error, check ollama server logs for details"

Environment

  • Hardware: Apple Mac mini M4
  • Unified Memory: 16 GB
  • OS: macOS (latest)
  • Ollama version: latest (started via Ollama.app)
  • GPU: Apple Metal, 11.8 GiB available VRAM (as reported by Ollama)

Steps to Reproduce

curl -X POST http://localhost:11434/api/generate -d '{
  "model": "qwen-vialetto-fix",
  "prompt": "ciao",
  "keep_alive": "24h"
}'

Expected Behavior

Model loads and responds normally.

Actual Behavior

{"error":"model runner has unexpectedly stopped, this may be due to resource limitations
or an internal error, check ollama server logs for details"}

Server Log

time=2026-03-09T22:49:55.794+01:00 level=INFO source=types.go:42
msg="inference compute" id=0 library=Metal name=Metal description="Apple M4"
total="11.8 GiB" available="11.8 GiB"
time=2026-03-09T22:49:55.794+01:00 level=INFO source=routes.go:1763
msg="vram-based default context" total_vram="11.8 GiB" default_num_ctx=4096

No further log entries appear when the crash occurs — the runner stops silently.

Additional Notes

  • qwen2.5:7b (text only) loads and runs correctly on the same machine ✅
  • qwen2.5vl:7b (vision) also loads and runs correctly ✅
  • The crash happens specifically with qwen3.5:9b family models
  • The model size is 8.6 GB, which should fit within the available 11.8 GiB VRAM
  • No other models are loaded simultaneously when the crash occurs (ollama ps is empty)
  • The server log does not show any loading attempt before the crash, suggesting
    the runner exits before even starting to load weights

Workaround

Using qwen2.5vl:7b instead as a vision model works correctly.

Relevant log output

OS

No response

GPU

No response

CPU

No response

Ollama version

No response

Originally created by @vpoma777 on GitHub (Mar 9, 2026). Original GitHub issue: https://github.com/ollama/ollama/issues/14748 ### What is the issue? ## Description The `qwen3.5:9b` model (and the custom modelfile `qwen-vialetto-fix` based on `qwen2.5vl:7b`) crashes immediately when loaded on Apple M4 16GB unified memory with error: > "model runner has unexpectedly stopped, this may be due to resource limitations > or an internal error, check ollama server logs for details" ## Environment - **Hardware:** Apple Mac mini M4 - **Unified Memory:** 16 GB - **OS:** macOS (latest) - **Ollama version:** latest (started via Ollama.app) - **GPU:** Apple Metal, 11.8 GiB available VRAM (as reported by Ollama) ## Steps to Reproduce ```bash curl -X POST http://localhost:11434/api/generate -d '{ "model": "qwen-vialetto-fix", "prompt": "ciao", "keep_alive": "24h" }' ``` ## Expected Behavior Model loads and responds normally. ## Actual Behavior ```json {"error":"model runner has unexpectedly stopped, this may be due to resource limitations or an internal error, check ollama server logs for details"} ``` ## Server Log ``` time=2026-03-09T22:49:55.794+01:00 level=INFO source=types.go:42 msg="inference compute" id=0 library=Metal name=Metal description="Apple M4" total="11.8 GiB" available="11.8 GiB" time=2026-03-09T22:49:55.794+01:00 level=INFO source=routes.go:1763 msg="vram-based default context" total_vram="11.8 GiB" default_num_ctx=4096 ``` No further log entries appear when the crash occurs — the runner stops silently. ## Additional Notes - `qwen2.5:7b` (text only) loads and runs correctly on the same machine ✅ - `qwen2.5vl:7b` (vision) also loads and runs correctly ✅ - The crash happens specifically with `qwen3.5:9b` family models - The model size is 8.6 GB, which should fit within the available 11.8 GiB VRAM - No other models are loaded simultaneously when the crash occurs (`ollama ps` is empty) - The server log does not show any loading attempt before the crash, suggesting the runner exits before even starting to load weights ## Workaround Using `qwen2.5vl:7b` instead as a vision model works correctly. ### Relevant log output ```shell ``` ### OS _No response_ ### GPU _No response_ ### CPU _No response_ ### Ollama version _No response_
GiteaMirror added the bugneeds more info labels 2026-04-29 10:11:17 -05:00
GiteaMirror commented 2026-04-29 10:11:20 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Mar 9, 2026):

Where was the model pulled from? Server logs may aid in debugging.

<!-- gh-comment-id:4027687538 --> @rick-github commented on GitHub (Mar 9, 2026): Where was the model pulled from? [Server logs](https://docs.ollama.com/troubleshooting) may aid in debugging.
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 needs more info
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#56047
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?