Qwen/Qwen2.5-3B-Instruct-AWQ

Quantization vs Qwen/Qwen2.5-3B-Instruct. Qwen/Qwen2.5-3B-Instruct-AWQ is a quantized version of the other (I32/F16).

1 derivatives checked

• FractalGPT/RuQwen2.5-3B-Instruct-AWQ: Same weights, repacked

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

On the Hub · Downloads on Model Pulse