Downloads · 30 days
254
19% of all-time downloads
Qwen3.8-23B-Mini-Me-4bit
StargazerLabs/Qwen3.8-23B-Mini-Me-4bit
Qwen3.8-23B-Mini-Me-4bit is a image-text-to-text model from StargazerLabs. 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.
This model has been through a battery of personal probes rather than standard benchmarks; there are no standard benchmark metrics to report yet.
All-time downloads
1.3K
Public
Parameters
22.8B
13.5 GB on disk
Likes
6
Public
Repo makeup
Click a slice to open those files.
.safetensors13.5 GB · 100%
Parameter types
How the weights are stored.
U3222.3B · 98%
Try a prompt
Base models
Model card
From the Hugging Face model README
Qwen3.8-23B-Mini-Me (4bit)
This model has been through a battery of personal probes rather than standard benchmarks; there are no standard benchmark metrics to report yet.
During internal use, it has held for coding and agentic work — long multi-turn conversations, tool calling, instruction retention past its nominal context — while landing slightly short of the parent across most things.
Expect it to be smaller, faster, and just a little bit less smart than Qwen3.8-27B, not a different model.
Architecture: Same as the original Qwen3.8-27B minus 12 layers: 52 layers, vision tower intact and untouched
Layers 12–15, 24–27, and 36–39 were all removed based on lesion probing across different combinations of depth prunes; these were the most favorable combination of layers to remove based on internal tests
- Task
- Image-Text-to-Text
- Library
- mlx
- Type
- qwen3_5
- License
- apache-2.0
- Created
- Aug 19, 2026
- Updated
- Aug 19, 2026