Thank You for Viewing This Release! Model files (GGUF) are still being uploaded.
This modelcard will be updated soon!
Your understanding and patience is very much appreciated.
Mistral-Small-4-119B-A6B is a huge model in physical storage size
and due to this: Uploads are taking longer than expected.*
Technical Details ___________________ These quantized GGUF files found in this release are unique in the sense that when initially converting
this model it was observed that there are native Float32 (F32) weights in the layers.
Upon realizing this during the initial conversion;the model was then re-converted using an "F32" flag in Llama.cpp (Version 9888)
prior to being quantized. (This was done in order to snub quality loss compared to converting to BF16 or F16 conversion+quantize)
