[GH-ISSUE #4930] Application Failure on Latest MacBook M1, Runs Smoothly on Intel Mac #49628

Closed
opened 2026-04-28 12:26:29 -05:00 by GiteaMirror · 2 comments
Owner

Originally created by @hylexus on GitHub (Jun 8, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/4930

What is the issue?

ollama run qwen2
Error: llama runner process has terminated: signal: abort trap error:error loading model vocabulary: unknown pre-tokenizer type: 'qwen2'

OS

macOS

GPU

Apple

CPU

Apple

Ollama version

0.1.37

Originally created by @hylexus on GitHub (Jun 8, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/4930 ### What is the issue? ``` ollama run qwen2 Error: llama runner process has terminated: signal: abort trap error:error loading model vocabulary: unknown pre-tokenizer type: 'qwen2' ``` ### OS macOS ### GPU Apple ### CPU Apple ### Ollama version 0.1.37
GiteaMirror added the bug label 2026-04-28 12:26:29 -05:00
Author
Owner

@jamfor999 commented on GitHub (Jun 8, 2024):

Is that the same version you're running on your intel mac?
Qwen2 support was only added in the latest release https://github.com/ollama/ollama/releases/tag/v0.1.42

<!-- gh-comment-id:2156024443 --> @jamfor999 commented on GitHub (Jun 8, 2024): Is that the same version you're running on your intel mac? Qwen2 support was only added in the latest release https://github.com/ollama/ollama/releases/tag/v0.1.42
Author
Owner

@jmorganca commented on GitHub (Jun 8, 2024):

Hi sorry about this, updating to 0.1.42 will fix it as Qwen requires this version

<!-- gh-comment-id:2156201652 --> @jmorganca commented on GitHub (Jun 8, 2024): Hi sorry about this, updating to 0.1.42 will fix it as Qwen requires this version
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#49628