[GH-ISSUE #6296] Better to add athene70b f16 and q8 #3946

Closed
opened 2026-04-12 14:49:29 -05:00 by GiteaMirror · 3 comments
Owner

Originally created by @Llamadouble999q on GitHub (Aug 10, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/6296

Why ollama stopped uploading athene?

Originally created by @Llamadouble999q on GitHub (Aug 10, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/6296 Why ollama stopped uploading athene?
GiteaMirror added the model label 2026-04-12 14:49:29 -05:00
Author
Owner

@MaxJa4 commented on GitHub (Aug 11, 2024):

The used GGUF source (https://huggingface.co/bullerwins/Athene-70B-GGUF) had split files for Q6_K and Q8_0, which is not compatible with Ollama's import yet (#5245).

I converted the GGUFs myself now from the original model authors' HF and quantized the remaining types, so there's Q6_K, Q8_0 and FP16 now too:
https://ollama.com/finalend/athene-70b

<!-- gh-comment-id:2282839282 --> @MaxJa4 commented on GitHub (Aug 11, 2024): The used GGUF source (https://huggingface.co/bullerwins/Athene-70B-GGUF) had split files for Q6_K and Q8_0, which is not compatible with Ollama's import yet (#5245). I converted the GGUFs myself now from the original model authors' HF and quantized the remaining types, so there's Q6_K, Q8_0 and FP16 now too: https://ollama.com/finalend/athene-70b
Author
Owner

@MaxJa4 commented on GitHub (Aug 14, 2024):

@Llamadouble999q can this be closed now?

<!-- gh-comment-id:2290074078 --> @MaxJa4 commented on GitHub (Aug 14, 2024): @Llamadouble999q can this be closed now?
Author
Owner

@jmorganca commented on GitHub (Sep 2, 2024):

Thanks for uploading @MaxJa4. I'll close for now @Llamadouble999q but let me know any issues remain

<!-- gh-comment-id:2325369824 --> @jmorganca commented on GitHub (Sep 2, 2024): Thanks for uploading @MaxJa4. I'll close for now @Llamadouble999q but let me know any issues remain
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#3946