isogen's picture
Upload folder using huggingface_hub
2ea45b9 verified
metadata
base_model: Qwen/Qwen3-1.7B-Base

EXL3 quantization of Qwen3-1.7B-Base, 8 bits per weight, including output layers.

HumanEval (argmax)

Model Q4 Q6 Q8 FP16
Qwen3-1.7B-exl3-8bpw-h8 0.0% 70.7% 68.3% 68.9%
Qwen3-1.7B-Base-exl3-8bpw-h8 0.0% 66.5% 70.7% 70.1%