Downloads · 30 days
16
6% of all-time downloads
Qwen3.5-0.8B_Abliterated-oQ4
dawncr0w/Qwen3.5-0.8B_Abliterated-oQ4
Qwen3.5-0.8B_Abliterated-oQ4 is a image-text-to-text model from dawncr0w. 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.
This model was quantized using oQ (oMLX v0.3.9.dev1) mixed-precision quantization.
All-time downloads
271
Public
Parameters
853M
666 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors646 MB · 96%
Parameter types
How the weights are stored.
U32752M · 88%
Try a prompt
Model card
From the Hugging Face model README
Qwen3.5-0.8B_Abliterated-oQ4
This model was quantized using oQ (oMLX v0.3.9.dev1) mixed-precision quantization.
Quantization details
- Model type: qwen3_5
- Bits: 4
- Group size: 64
- Format: MLX safetensors
Vision support
This MLX safetensors artifact includes the Qwen3.5 vision tensors and processor config, so the repository is tagged as image-text-to-text.
- Task
- Image-Text-to-Text
- Library
- mlx
- Type
- qwen3_5
- Created
- May 12, 2026
- Updated
- Jun 1, 2026