mlx-community/Llama-3.1-Swallow-8B-Instruct-v0.5-4bit

Quantization vs tokyotech-llm/Llama-3.1-Swallow-8B-Instruct-v0.5. mlx-community/Llama-3.1-Swallow-8B-Instruct-v0.5-4bit is a quantized version of the other (U32/BF16).

On the Hub · Downloads on Model Pulse