Downloads · 30 days
40
6% of all-time downloads
Huihui-Step3-VL-10B-abliterated-mlx-8bit
AITRADER/Huihui-Step3-VL-10B-abliterated-mlx-8bit
Huihui-Step3-VL-10B-abliterated-mlx-8bit is a image-text-to-text model from AITRADER. 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.
MLX conversion (8-bit affine quantization, group size 64) of huihui-ai/Huihui-Step3-VL-10B-abliterated.
All-time downloads
632
Public
Parameters
9.8B
11.3 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors11.3 GB · 100%
Parameter types
How the weights are stored.
U329.6B · 95%
Try a prompt
Base models
Model card
From the Hugging Face model README
Huihui-Step3-VL-10B-abliterated (MLX 8-bit)
MLX conversion (8-bit affine quantization, group size 64) of huihui-ai/Huihui-Step3-VL-10B-abliterated.
Files
- MLX weights:
model-*.safetensors+model.safetensors.index.json - Loader code:
step3_vl_mlx.py(referenced byconfig.jsonviamodel_file)
Text-Only Usage (mlx-lm)
This repo includes a minimal MLX module tree primarily meant for loading and quantization. Multimodal/image inference is not implemented in the included model file.
pip install -U mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("AITRADER/Huihui-Step3-VL-10B-abliterated-mlx-8bit")
print(generate(model, tokenizer, prompt="Hello!", max_tokens=128))
Source
Original model: huihui-ai/Huihui-Step3-VL-10B-abliterated
- Task
- Image-Text-to-Text
- Library
- mlx
- Type
- step_robotics
- License
- apache-2.0
- Created
- Feb 15, 2026
- Updated
- Feb 15, 2026