Downloads · 30 days
30
18% of all-time downloads
CAT-Thinking-8B-MLX-8bit
mlx-community/CAT-Thinking-8B-MLX-8bit
CAT-Thinking-8B-MLX-8bit is a text generation model from mlx-community. 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.
How to use<br git clone https://github.com/ml-explore/mlx-lm (mlx-lm==0.31.3)
All-time downloads
163
Public
Parameters
8.2B
17.4 GB on disk
Likes
1
Public
Repo makeup
Click a slice to open those files.
.safetensors8.7 GB · 100%
Parameter types
How the weights are stored.
U328.2B · 100%
Try a prompt
Base models
Model card
From the Hugging Face model README
How to use<br> git clone https://github.com/ml-explore/mlx-lm (mlx-lm==0.31.3)
mlx_lm.convert --hf-path cyberagent/CAT-Thinking-8B --mlx-path ./CAT-Thinking-8B-MLX-8bit -q --q-bits 8 --trust-remote-code
mlx_lm.generate --model ./CAT-Thinking-8B-MLX-8bit --verbose True --prompt "about you" --max-tokens 1000
==========<br> Prompt: 10 tokens, 84.526 tokens-per-sec<br> Generation: 569 tokens, 72.305 tokens-per-sec<br> Peak memory: 8.853 GB
- Task
- Text Generation
- Library
- mlx
- Type
- qwen3
- License
- apache-2.0
- Languages
- en, ja
- Created
- Jun 3, 2026
- Updated
- Jun 3, 2026