Downloads · 30 days
146
25% of all-time downloads
Qwen3.8-27B-MLX-4bit
lesa80/Qwen3.8-27B-MLX-4bit
Qwen3.8-27B-MLX-4bit is a image-text-to-text model from lesa80. 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-vlm. The card lists the license as apache-2.0.
MLX 4-bit quantized version of Qwen/Qwen3.8-27B.
All-time downloads
595
Public
Parameters
27.4B
16.1 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors16.1 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
Qwen3.8-27B-MLX-4bit
MLX 4-bit quantized version of Qwen/Qwen3.8-27B.
- BF16 version: lesa80/Qwen3.8-27B-MLX-bf16
All capabilities preserved:
- ✅ Vision — image + video (27-layer ViT encoder)
- ✅ Reasoning — thinking mode (токены
thinking/response) - ✅ Длинный контекст — 262K токенов
- ✅ Multilingual — русский, английский, китайский
| Property | Value |
|---|---|
| Quantization | 4-bit affine, group_size=64 |
| Model size | ~16 GB |
| RAM required | 16-24 GB |
| License | Apache 2.0 |
Usage
hf download lesa80/Qwen3.8-27B-MLX-4bit --local-dir ./qwen-mlx --local-dir-use-symlinks False
from mlx_vlm import load, generate
model, processor = load("lesa80/Qwen3.8-27B-MLX-4bit")
output = generate(model, processor, "Describe this image.", image=["image.jpg"])
print(output)
mlx_vlm.generate --model lesa80/Qwen3.8-27B-MLX-4bit --prompt "Hello" --max-tokens 200
Links
- Task
- Image-Text-to-Text
- Library
- mlx-vlm
- Type
- qwen3_5
- License
- apache-2.0
- Created
- Aug 15, 2026
- Updated
- Aug 15, 2026