File size: 761 Bytes
eb816ca
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
---
base_model: Qwen/Qwen3-4B
---

[EXL3](https://github.com/turboderp-org/exllamav3) quantization of [Qwen3-4B](https://huggingface.co/Qwen/Qwen3-4B), 6 bits per weight.

### HumanEval (argmax)

| Model                                                                        | Q4    | Q6    | Q8    | FP16  |
| ---------------------------------------------------------------------------- | ----- | ----- | ----- | ----- |
| [Qwen3-4B-exl3-4bpw](https://huggingface.co/isogen/Qwen3-4B-exl3-4bpw)       | 80.5% | 81.1% | 81.7% | 80.5% |
| [Qwen3-4B-exl3-6bpw](https://huggingface.co/isogen/Qwen3-4B-exl3-6bpw)       | 80.5% | 85.4% | 86.0% | 86.0% |
| [Qwen3-4B-exl3-8bpw-h8](https://huggingface.co/isogen/Qwen3-4B-exl3-8bpw-h8) | 82.3% | 84.8% | 83.5% | 82.9% |