mlx-community/Llama-3.1-Swallow-8B-Instruct-v0.3-4bit

Quantization vs tokyotech-llm/Llama-3.1-Swallow-8B-Instruct-v0.3. mlx-community/Llama-3.1-Swallow-8B-Instruct-v0.3-4bit is a quantized version of the other (U32/F16).

On the Hub · Downloads on Model Pulse