Downloads · 30 days
65
3% of all-time downloads
TheCluster/Qwen3.5-122B-A10B-Heretic-v2-MLX-mxfp8
Qwen3.5-122B-A10B-Heretic-v2-MLX-mxfp8 is a image-text-to-text model from TheCluster. Use it for the image-text-to-text task on the model card, and read the license before you ship it in a product. It is set up for mlx. The card lists the license as apache-2.0.
<div align="center"<img width="400px" src="https://qianwen-res.oss-accelerate.aliyuncs.com/logoqwen3.5.png"</div
Downloads · 30 days
65
3% of all-time downloads
All-time downloads
2.2K
Public
Parameters
122B
127 GB on disk
Likes
2
Public
Click a slice to open those files.
.safetensors127 GB · 100%
How the weights are stored.
U32122B · 100%
From the Hugging Face model README
Quality: quantized (mxfp8, group size: 32)
This is an uncensored version of Qwen/Qwen3.5-122B-A10B, made using Heretic v1.2.0 with Multi-directional refusal supression
| Metric | This model | Original model (Qwen/Qwen3.5-122B-A10B) |
|---|---|---|
| KL divergence | 0.0646 | 0 (by definition) |
| Refusals | 16/100 | 84/100 |
temperature=1.0, top_p=0.95, top_k=20, min_p=0.0, presence_penalty=1.5, repetition_penalty=1.0temperature=0.6, top_p=0.95, top_k=20, min_p=0.0, presence_penalty=0.0, repetition_penalty=1.0temperature=0.7, top_p=0.8, top_k=20, min_p=0.0, presence_penalty=1.5, repetition_penalty=1.0temperature=1.0, top_p=1.0, top_k=40, min_p=0.0, presence_penalty=2.0, repetition_penalty=1.0presence_penalty parameter between 0 and 2 to reduce endless repetitions. However, using a higher value may occasionally result in language mixing and a slight decrease in model performance.This model was converted to MLX format from coder3101/Qwen3.5-122B-A10B-heretic-v2 using mlx-vlm version 0.4.0.