mlx-community/Qwen2.5-3B-Instruct-4bit

Quantization vs Qwen/Qwen2.5-3B. mlx-community/Qwen2.5-3B-Instruct-4bit is a quantized version of the other (U32/F16).

1 derivatives checked

• inglebhavin98/hinglish-smooth-talker-qwen2.5-3b-experimental: Partial fine-tune

1 other repos hold byte-for-byte identical weight files.

On the Hub · Downloads on Model Pulse