github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-07 00:22:43 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #8464] DeepSeek-v3 fails on M4 Max Pro 128GB with ollama v0.5.7: “signal: killed” error #31205

New Issue
Closed
opened 2026-04-22 11:26:16 -05:00 by GiteaMirror · 1 comment
GiteaMirror commented 2026-04-22 11:26:16 -05:00
Owner
Copy Link

Originally created by @totorofly on GitHub (Jan 17, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/8464

What is the issue?

Description:
I’m running a fully specced M4 Max Pro with 128GB of unified memory. When I execute:

ollama run deepseek-v3

(using deepseek-v3 with ollama v0.5.7), I encounter this error:

Error: llama runner process has terminated: signal: killed

Image

I’m using Q4_K_M quantization, which should be 4-bit. Given 128GB of unified memory, it seems like there should be enough memory available. Why is this error occurring, and is there any workaround or additional configuration needed to prevent the process from being killed?

Thank you for your help!

OS

macOS

GPU

Apple

CPU

Apple

Ollama version

v0.5.7

Originally created by @totorofly on GitHub (Jan 17, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/8464 ### What is the issue? Description: I’m running a fully specced M4 Max Pro with 128GB of unified memory. When I execute: ```ollama run deepseek-v3``` (using [deepseek-v3](https://ollama.com/library/deepseek-v3) with ollama v0.5.7), I encounter this error: ```Error: llama runner process has terminated: signal: killed``` <img width="445" alt="Image" src="https://github.com/user-attachments/assets/18610684-f54b-4a61-bf70-20133f1a7895" /> I’m using Q4_K_M quantization, which should be 4-bit. Given 128GB of unified memory, it seems like there should be enough memory available. Why is this error occurring, and is there any workaround or additional configuration needed to prevent the process from being killed? Thank you for your help! ### OS macOS ### GPU Apple ### CPU Apple ### Ollama version v0.5.7
GiteaMirror added the bug label 2026-04-22 11:26:16 -05:00
GiteaMirror commented 2026-04-22 11:26:18 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Jan 17, 2025):

The model is 404GB. Server logs will provide insight.

<!-- gh-comment-id:2597234647 --> @rick-github commented on GitHub (Jan 17, 2025): The model is 404GB. [Server logs](https://github.com/ollama/ollama/blob/main/docs/troubleshooting.md#how-to-troubleshoot-issues) will provide insight.
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#31205
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?