mlx-community/Qwen2.5-Coder-1.5B-Instruct-4bit
Quantization vs Qwen/Qwen2.5-Coder-1.5B. mlx-community/Qwen2.5-Coder-1.5B-Instruct-4bit is a quantized version of the other (U32/F16).
2 derivatives checked
- avirajkhare00/bhai-lang-coder-1.5b: Quantization
- devstudio-live/DevStudio-Coder-1.5B: Quantization
3 other repos hold byte-for-byte identical weight files.