Downloads · 30 days
49
2% of all-time downloads
nightmedia/Qwen3-4B-Thinking-2507-GPT-5.1-Codex-Max-Distill-qx86-hi-mlx
Qwen3-4B-Thinking-2507-GPT-5.1-Codex-Max-Distill-qx86-hi-mlx is a text generation model from nightmedia. 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.
0.417,0.503,0.648,0.564,0.376,0.713,0.576
Downloads · 30 days
49
2% of all-time downloads
All-time downloads
2.3K
Public
Parameters
4B
3.8 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors3.8 GB · 100%
How the weights are stored.
U324B · 100%
From the Hugging Face model README
0.417,0.503,0.648,0.564,0.376,0.713,0.576
This model Qwen3-4B-Thinking-2507-GPT-5.1-Codex-Max-Distill-qx86-hi-mlx was converted to MLX format from TeichAI/Qwen3-4B-Thinking-2507-GPT-5.1-Codex-Max-Distill using mlx-lm version 0.30.0.
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("Qwen3-4B-Thinking-2507-GPT-5.1-Codex-Max-Distill-qx86-hi-mlx")
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)