Qwen3-14B-exl3-4bpw / README.md
isogen's picture
Update README.md
4d3eea7 verified
metadata
base_model: Qwen/Qwen3-14B

EXL3 quantization of Qwen3-14B, 4 bits per weight.

HumanEval (argmax)

Model Q4 Q6 Q8 FP16
Qwen3-14B-exl3-4bpw 88.4 89.0 89.0 89.0
Qwen3-14B-exl3-6bpw 89.6 88.4 89.6 89.0
Qwen3-8B-exl3-4bpw 86.0 85.4 86.0 87.2
Qwen3-8B-exl3-6bpw 84.8 86.0 87.2 87.2
Qwen3-8B-exl3-8bpw-h8 86.0 87.2 86.6 86.6
Qwen3-30B-A3B-exl3-2.25bpw 88.4
Qwen3-30B-A3B-exl3-3bpw 89.6
Qwen3-30B-A3B-exl3-4bpw 92.1
Qwen3-32B-exl3-4bpw 91.5