noneUsername/Mistral-Nemo-Instruct-2407-W8A8-Dynamic-Per-Token

Quantization vs unsloth/Mistral-Nemo-Instruct-2407. noneUsername/Mistral-Nemo-Instruct-2407-W8A8-Dynamic-Per-Token is a quantized version of the other (I8/BF16).

On the Hub · Downloads on Model Pulse