RedHatAI/Devstral-Small-2-24B-Instruct-2512

Quantization vs mistralai/Mistral-Small-3.1-24B-Base-2503. RedHatAI/Devstral-Small-2-24B-Instruct-2512 is a quantized version of the other (F8_E4M3/BF16).

7 other repos hold byte-for-byte identical weight files.

On the Hub · Downloads on Model Pulse