[GH-ISSUE #108] Error after prompting Llama2 on M1. #62071

Closed
opened 2026-05-03 07:26:19 -05:00 by GiteaMirror · 4 comments
Owner

Originally created by @aelder on GitHub (Jul 19, 2023).
Original GitHub issue: https://github.com/ollama/ollama/issues/108

After starting Ollama and running Llama2, any prompt results in:
Error: Post "http://127.0.0.1:11434/api/generate": EOF
Installed on M1 Macbook Pro
Ollama reports that it is running.
'Ollama list' reports llama2:latest.

Is this a memory issue?

Originally created by @aelder on GitHub (Jul 19, 2023). Original GitHub issue: https://github.com/ollama/ollama/issues/108 After starting Ollama and running Llama2, any prompt results in: `Error: Post "http://127.0.0.1:11434/api/generate": EOF ` Installed on M1 Macbook Pro Ollama reports that it is running. 'Ollama list' reports llama2:latest. Is this a memory issue?
GiteaMirror added the bug label 2026-05-03 07:26:19 -05:00
Author
Owner

@pdevine commented on GitHub (Jul 19, 2023):

How much memory do you have? It should work fine (albeit slow) on a 16GB laptop.

<!-- gh-comment-id:1641211843 --> @pdevine commented on GitHub (Jul 19, 2023): How much memory do you have? It should work fine (albeit slow) on a 16GB laptop.
Author
Owner

@mchiang0610 commented on GitHub (Jul 19, 2023):

@aelder may I ask what was the length of your prompt? I have seen this on longer prompts this morning.

<!-- gh-comment-id:1641292813 --> @mchiang0610 commented on GitHub (Jul 19, 2023): @aelder may I ask what was the length of your prompt? I have seen this on longer prompts this morning.
Author
Owner

@aelder commented on GitHub (Jul 19, 2023):

@mchiang0610 it happens with any length. I’ve tried down to a single character.

Based on comments I imagine it’s lack of memory. I’m only using a base M1 with 8gb unified memory.

<!-- gh-comment-id:1641303258 --> @aelder commented on GitHub (Jul 19, 2023): @mchiang0610 it happens with any length. I’ve tried down to a single character. Based on comments I imagine it’s lack of memory. I’m only using a base M1 with 8gb unified memory.
Author
Owner

@chsasank commented on GitHub (Jul 19, 2023):

Yep, it's out of memory. Reported logs at #118

<!-- gh-comment-id:1641506842 --> @chsasank commented on GitHub (Jul 19, 2023): Yep, it's out of memory. Reported logs at #118
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#62071