metadata
base_model: Qwen/Qwen3-4B
EXL3 quantization of Qwen3-4B, 6 bits per weight.
HumanEval (argmax)
Model | Q4 | Q6 | Q8 | FP16 |
---|---|---|---|---|
Qwen3-4B-exl3-4bpw | 80.5% | 81.1% | 81.7% | 80.5% |
Qwen3-4B-exl3-6bpw | 80.5% | 85.4% | 86.0% | 86.0% |
Qwen3-4B-exl3-8bpw-h8 | 82.3% | 84.8% | 83.5% | 82.9% |