[GH-ISSUE #2746] gemma:7b-instruct-fp16 #79331

Closed
opened 2026-05-09 04:52:29 -05:00 by GiteaMirror · 1 comment
Owner

Originally created by @marabgol on GitHub (Feb 25, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/2746

OS= MacOS 14.3.1 (23D60)
I run .ollama serve

I just pulled gemma and it does not work on my mac , what would be wrong ?

$ollama -v
ollama version is 0.0.0
Warning: client version is 0.1.27
$ollama run gemma:7b-instruct-fp16
Error: error loading model /Volumes/T9/.ollama/blobs/sha256:d19e52732bddcb9902347a9c60c117801ad7a3b776b700b9d1649f63f6d80dc0

also in server logs I get this error:
2024/02/25 11:41:46 ext_server_common.go:87: concurrent llm servers not yet supported, waiting for prior server to complete

note : I only ran "ollama run gemma:7b-instruct-fp16"

Originally created by @marabgol on GitHub (Feb 25, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/2746 OS= MacOS 14.3.1 (23D60) I run .ollama serve I just pulled gemma and it does not work on my mac , what would be wrong ? $ollama -v ollama version is 0.0.0 Warning: client version is 0.1.27 $ollama run gemma:7b-instruct-fp16 Error: error loading model /Volumes/T9/.ollama/blobs/sha256:d19e52732bddcb9902347a9c60c117801ad7a3b776b700b9d1649f63f6d80dc0 also in server logs I get this error: 2024/02/25 11:41:46 ext_server_common.go:87: concurrent llm servers not yet supported, waiting for prior server to complete note : I only ran "ollama run gemma:7b-instruct-fp16"
Author
Owner

@marabgol commented on GitHub (Feb 25, 2024):

never-mind, when I clone 0.1.27 version I forgot to re-build it

<!-- gh-comment-id:1962999877 --> @marabgol commented on GitHub (Feb 25, 2024): never-mind, when I clone 0.1.27 version I forgot to re-build it
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#79331