Downloads · 30 days
14
36% of all-time downloads
Ocelot-1-VL-MLX-2bit
gnukeith/Ocelot-1-VL-MLX-2bit
Ocelot-1-VL-MLX-2bit is a image-text-to-text model from gnukeith. 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 2-bit, group-size 64 conversion of Ocelot-1-VL, merged into its BF16 Qwen3-VL-4B-Instruct base. Effective quantization is 3.764 bits/weight because sensitive and unsupported tensors remain at higher precision.
All-time downloads
39
Public
Parameters
4.4B
2.1 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors2.1 GB · 99%
Parameter types
How the weights are stored.
U324B · 91%
Try a prompt
Base models
Model card
From the Hugging Face model README
Ocelot-1-VL MLX 2-bit
MLX 2-bit, group-size 64 conversion of Ocelot-1-VL, merged into its BF16 Qwen3-VL-4B-Instruct base. Effective quantization is 3.764 bits/weight because sensitive and unsupported tensors remain at higher precision.
This model is specialized only for webpage summarization. Follow the strict prompt contract and limitations in the original model card. This maximum-compression variant has the greatest quality risk; prefer 4-bit unless memory is constrained.
pip install 'mlx-vlm @ git+https://github.com/Blaizzy/mlx-vlm.git'
python -m mlx_vlm generate --model . --prompt 'The is the text of a webpage: <page>Page text here</page> Summarise the content between the <page> tags, or if no content is found use the screenshots provided, in the Brave Summary style.' --max-tokens 512
Converted with MLX-VLM revision 0b1d25e334686bd36dda71b2307d186dbb3e7859. Text generation smoke test passed.
- Task
- Image-Text-to-Text
- Library
- mlx
- Type
- qwen3_vl
- License
- apache-2.0
- Created
- Jul 22, 2026
- Updated
- Jul 22, 2026