mlx-community/Llama-3.3-Swallow-70B-Instruct-v0.4-8bit

Quantization vs tokyotech-llm/Llama-3.3-Swallow-70B-Instruct-v0.4. mlx-community/Llama-3.3-Swallow-70B-Instruct-v0.4-8bit is a quantized version of the other (U32/F16).

On the Hub · Downloads on Model Pulse