gratex/Mistral-Small-3.2-24B-Instruct-2506-W4A16-AutoRound
Quantization vs mistralai/Mistral-Small-3.2-24B-Instruct-2506. gratex/Mistral-Small-3.2-24B-Instruct-2506-W4A16-AutoRound is a quantized version of the other (I32/BF16).
Quantization vs mistralai/Mistral-Small-3.2-24B-Instruct-2506. gratex/Mistral-Small-3.2-24B-Instruct-2506-W4A16-AutoRound is a quantized version of the other (I32/BF16).