mlx-community/Dolphin-Mistral-24B-Venice-Edition-mlx-8Bit

Quantization vs dphn/Dolphin-Mistral-24B-Venice-Edition. mlx-community/Dolphin-Mistral-24B-Venice-Edition-mlx-8Bit is a quantized version of the other (U32/F16).

On the Hub · Downloads on Model Pulse