mlx-community/Qwen2.5-Coder-7B-Instruct-4bit
Quantization vs Qwen/Qwen2.5-Coder-7B. mlx-community/Qwen2.5-Coder-7B-Instruct-4bit is a quantized version of the other (U32/F16).
2 derivatives checked
- ethanolivertroy/HackIDLE-NIST-Coder-v1.1-GGUF: Quantization
- ethanolivertroy/HackIDLE-NIST-Coder-MLX-4bit: Partial fine-tune
4 other repos hold byte-for-byte identical weight files.