Downloads · 30 days
286
35% of all-time downloads
Swift-Qwen3.8-27B-Uncensored-MTP-mlx-8Bit
kylar/Swift-Qwen3.8-27B-Uncensored-MTP-mlx-8Bit
Swift-Qwen3.8-27B-Uncensored-MTP-mlx-8Bit is a image-text-to-text model from kylar. 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 transformers. The card lists the license as other.
Created from: https://huggingface.co/spaces/mlx-community/mlx-my-repo
All-time downloads
815
Public
Parameters
26.9B
28.6 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors28.6 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
kylar/Swift-Qwen3.8-27B-Uncensored-MTP-mlx-8Bit
Created from: https://huggingface.co/spaces/mlx-community/mlx-my-repo
The Model kylar/Swift-Qwen3.8-27B-Uncensored-MTP-mlx-8Bit was converted to MLX format from ajgazin/Swift-Qwen3.8-27B-Uncensored-MTP using mlx-lm version 0.31.2.
Use with mlx
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("kylar/Swift-Qwen3.8-27B-Uncensored-MTP-mlx-8Bit")
prompt="hello"
if hasattr(tokenizer, "apply_chat_template") and tokenizer.chat_template is not None:
messages = [{"role": "user", "content": prompt}]
prompt = tokenizer.apply_chat_template(
messages, tokenize=False, add_generation_prompt=True
)
response = generate(model, tokenizer, prompt=prompt, verbose=True)
- Task
- Image-Text-to-Text
- Library
- transformers
- Type
- qwen3_5
- License
- other
- Created
- Sep 17, 2026
- Updated
- Sep 17, 2026