GGorman/DeepSeek-Coder-V2-Instruct-Q4-mlx

Quantization vs deepseek-ai/DeepSeek-Coder-V2-Instruct. GGorman/DeepSeek-Coder-V2-Instruct-Q4-mlx is a quantized version of the other (U32/F16).

On the Hub · Downloads on Model Pulse