eramax

/

Darwin-27B-Opus-GGUF

like 0

Are you likely to make any other weights Q6, Q8 etc?
What did you use to do the hf to gguf conversion?

Thanks for the gguf.

./llama-quantize
./models/Darwin-27B-Opus-F16.gguf
./models/Darwin-27B-Opus-Q4_K_M.gguf
Q4_K_M \

Now i am creating Q6 for you

This model is very good.

Darwin-27B-Opus-Q6_K_M.gguf

Thanks heaps.