nafisabdkhan/DeepSeek-Coder-V2-Lite-Instruct-mlx-8Bit

Quantization vs deepseek-ai/DeepSeek-Coder-V2-Lite-Instruct. nafisabdkhan/DeepSeek-Coder-V2-Lite-Instruct-mlx-8Bit is a quantized version of the other (U32/F16).

On the Hub · Downloads on Model Pulse