Downloads · 30 days
148
21% of all-time downloads
Qwen3.8-27B-4bit
agnosticeng/Qwen3.8-27B-4bit
Qwen3.8-27B-4bit is a image-text-to-text model from agnosticeng. 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.
4-bit MLX quantization of Qwen/Qwen3.8-27B, with the Qwen3.8 MTP head bundled at mtp/ for speculative decoding.
All-time downloads
720
Public
Parameters
27.4B
16.3 GB on disk
Likes
1
Public
Repo makeup
Click a slice to open those files.
.safetensors16.3 GB · 100%
Parameter types
How the weights are stored.
U3226.9B · 98%
Try a prompt
Base models
Model card
From the Hugging Face model README
agnosticeng/Qwen3.8-27B-4bit
4-bit MLX quantization of Qwen/Qwen3.8-27B, with the Qwen3.8 MTP head bundled at mtp/ for speculative decoding.
Quantization
- Affine 4-bit, group size 64 (~4.7 bits/weight, ~15 GB)
- Converted with mlx-vlm; vision tower included (image-text-to-text)
MTP head
mtp/weights.safetensors contains the Qwen3.8-27B multi-token-prediction sidecar (4-bit, mtp.-prefixed keys).
- Task
- Image-Text-to-Text
- Library
- mlx
- Type
- qwen3_5
- License
- apache-2.0
- Created
- Sep 5, 2026
- Updated
- Sep 5, 2026