Downloads · 30 days
28
10% of all-time downloads
Qwen3.8-27B-bf16
airagrp/Qwen3.8-27B-bf16
Qwen3.8-27B-bf16 is a machine learning model from airagrp. Use it for the machine learning 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 converted using mlx-vlm for apple silicon. This is an unquantized version. MTP head airagrp/Qwen3.8-27B-MTP-bf16
All-time downloads
280
Public
Parameters
27.4B
54.7 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors54.7 GB · 100%
At a glance
- Library
- mlx
- Model type
- qwen3_5
- Access
- Public
- Created
- Aug 18, 2026
- Updated
- Aug 18, 2026
- SHA
- bcc52b5f
Base models
Model card
From the Hugging Face model README
Qwen3.8-27B-bf16
This model was converted using mlx-vlm for apple silicon. This is an unquantized version. MTP head airagrp/Qwen3.8-27B-MTP-bf16
python -m mlx_vlm server --model airagrp/Qwen3.8-27B-bf16 \
--draft-model airagrp/Qwen3.8-27B-MTP-bf16 --draft-kind mtp --draft-block-size 3 \
--enable-thinking --host 127.0.0.1 --port 8080 --max-kv-size 262144
Works with omlx
- Library
- mlx
- Type
- qwen3_5
- Created
- Aug 18, 2026
- Updated
- Aug 18, 2026