Downloads · 30 days
30
9% of all-time downloads
Qwen3.8-27B-mxfp8
deconfined/Qwen3.8-27B-mxfp8
Qwen3.8-27B-mxfp8 is a text generation model from deconfined. Use it when you need the model to write or continue text. It is set up for mlx. The card lists the license as apache-2.0.
This model connstruct/Qwen3.8-27B-mxfp8 was converted to MLX format from Qwen/Qwen3.8-27B using mlx-lm version 0.31.3.
All-time downloads
349
Public
Parameters
26.9B
27.8 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors27.7 GB · 100%
Parameter types
How the weights are stored.
U3226.9B · 100%
Try a prompt
Base models
Model card
From the Hugging Face model README
connstruct/Qwen3.8-27B-mxfp8
This model connstruct/Qwen3.8-27B-mxfp8 was converted to MLX format from Qwen/Qwen3.8-27B using mlx-lm version 0.31.3.
Use with mlx
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("connstruct/Qwen3.8-27B-mxfp8")
prompt = "hello"
if tokenizer.chat_template is not None:
messages = [{"role": "user", "content": prompt}]
prompt = tokenizer.apply_chat_template(
messages, add_generation_prompt=True, return_dict=False,
)
response = generate(model, tokenizer, prompt=prompt, verbose=True)
- Task
- Text Generation
- Library
- mlx
- Type
- qwen3_5
- License
- apache-2.0
- Created
- Aug 14, 2026
- Updated
- Aug 14, 2026