Downloads · 30 days
513
7% of all-time downloads
tejones36/Qwen-3.8-27B-Uncensored-mlx-mixed_3_6
Qwen-3.8-27B-Uncensored-mlx-mixed_3_6 is a image-text-to-text model from tejones36. 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 repository contains Apple Silicon-optimized weights for junafinity/Qwen-3.8-27B-Uncensored converted to MLX format using mlx-vlm.
Downloads · 30 days
513
7% of all-time downloads
All-time downloads
7.3K
Public
Parameters
27.4B
14.8 GB on disk
Likes
6
Public
Click a slice to open those files.
.safetensors14.7 GB · 100%
How the weights are stored.
U3226.9B · 98%
From the Hugging Face model README
This repository contains Apple Silicon-optimized weights for junafinity/Qwen-3.8-27B-Uncensored converted to MLX format using mlx-vlm.
mlx-vlm--quant-predicate mixed_3_6mixed_3_6)The mixed_3_6 quantization recipe dynamically allocates bit-width across model layers:
Ensure you have mlx-vlm installed:
pip install -U mlx-vlm
mlx_vlm.generate \
--model tejones36/Qwen-3.8-27B-Uncensored-mlx-mixed_3_6 \
--prompt "Explain the concept of speculative decoding in MLX." \
--max-tokens 512 \
--verbose
mlx_vlm.generate \
--model tejones36/Qwen-3.8-27B-Uncensored-mlx-mixed_3_6 \
--image "/path/to/image.png" \
--prompt "Describe the visual details and composition of this image." \
--max-tokens 512
Launch the server (e.g., on port 2077):
mlx_vlm.server \
--model tejones36/Qwen-3.8-27B-Uncensored-mlx-mixed_3_6 \
--port 2077
curl:curl http://localhost:2077/v1/chat/completions \
-H "Content-Type: application/json" \
-d '{
"model": "tejones36/Qwen-3.8-27B-Uncensored-mlx-mixed_3_6",
"messages": [
{"role": "user", "content": "Server check: confirm operational status."}
],
"max_tokens": 128,
"temperature": 0.3
}'
from mlx_vlm import load, generate
from mlx_vlm.prompt_utils import apply_chat_template
from mlx_vlm.utils import load_config
model_path = "tejones36/Qwen-3.8-27B-Uncensored-mlx-mixed_3_6"
# 1. Load quantized model and multimodal processor
model, processor = load(model_path)
config = load_config(model_path)
# 2. Format prompt using model chat template
prompt = "Write a concise technical summary of mixed-bit quantization advantages."
formatted_prompt = apply_chat_template(processor, config, prompt)
# 3. Generate response
output = generate(
model,
processor,
prompt=formatted_prompt,
max_tokens=512,
verbose=True
)
print(output)