---
license: apache-2.0
base_model: Qwen/Qwen3.5-122B-A10B
base_model_relation: quantized
quantized_by: turboderp
tags:
- exl3
---

EXL3 quants of [Qwen3.5-122B-A10B](https://huggingface.co/Qwen/Qwen3.5-122B-A10B)

⚠️ Requires ExLlamaV3 v0.0.23 (or v0.0.22 `dev` branch)

Base bitrates:

[2.00 bits per weight](https://huggingface.co/turboderp/Qwen3.5-122B-A10B-exl3/tree/2.00bpw)    
[3.00 bits per weight](https://huggingface.co/turboderp/Qwen3.5-122B-A10B-exl3/tree/3.00bpw)    
[4.00 bits per weight](https://huggingface.co/turboderp/Qwen3.5-122B-A10B-exl3/tree/4.00bpw)    
[5.00 bits per weight](https://huggingface.co/turboderp/Qwen3.5-122B-A10B-exl3/tree/5.00bpw)    

Optimized:

[2.28 bits per weight](https://huggingface.co/turboderp/Qwen3.5-122B-A10B-exl3/tree/2.28bpw)    
[3.06 bits per weight](https://huggingface.co/turboderp/Qwen3.5-122B-A10B-exl3/tree/3.06bpw)    
[4.06 bits per weight](https://huggingface.co/turboderp/Qwen3.5-122B-A10B-exl3/tree/4.06bpw)     


# Benchmarks

.        | Ppl¹   | KL-div | HumanEval @1²  
---------|--------|--------|--------------
2.00 bpw | 7.672  | 0.594  | 87.80%
2.28 bpw | 5.077  | 0.243  | 92.07%
3.00 bpw | 4.818  | 0.146  | 94.51%
3.06 bpw | 4.487  | 0.100  | 95.12%
4.00 bpw | 4.312  | 0.058  | 94.51%
4.06 bpw | 4.219  | 0.042  | 95.12%
5.00 bpw | 4.177  | 0.031  | 95.12%
Original | 4.264  |        |

¹ (10 rows of wikitext2)
² Reasoning disabled

*(more coming)*