Downloads · 30 days
8
5% of all-time downloads
CheapResearch-4B-Thinking-mlx-8Bit
mku64/CheapResearch-4B-Thinking-mlx-8Bit
CheapResearch-4B-Thinking-mlx-8Bit is a machine learning model from mku64. 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. The card lists the license as mit.
The Model mku64/CheapResearch-4B-Thinking-mlx-8Bit was converted to MLX format from cheapresearch/CheapResearch-4B-Thinking using mlx-lm version 0.26.4.
All-time downloads
173
Public
Parameters
4B
4.3 GB on disk
Likes
1
Public
Repo makeup
Click a slice to open those files.
.safetensors4.3 GB · 100%
Parameter types
How the weights are stored.
U324B · 100%
Base models
Model card
From the Hugging Face model README
mku64/CheapResearch-4B-Thinking-mlx-8Bit
The Model mku64/CheapResearch-4B-Thinking-mlx-8Bit was converted to MLX format from cheapresearch/CheapResearch-4B-Thinking using mlx-lm version 0.26.4.
Use with mlx
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("mku64/CheapResearch-4B-Thinking-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)
- Library
- mlx
- Type
- qwen3
- License
- mit
- Created
- Oct 6, 2025
- Updated
- Oct 6, 2025