mlx-community/Hermes-3-Llama-3.2-3B-8bit

Quantization vs NousResearch/Hermes-3-Llama-3.2-3B. mlx-community/Hermes-3-Llama-3.2-3B-8bit is a quantized version of the other (U32/F16).

On the Hub · Downloads on Model Pulse