4-bit Open on Hugging Face
Parameters
4.5B
Weights (est.)
≈ 3.0 GB
Mac memory (est.)
8 GB+
Size is estimated from the parameter count and quantisation. Memory allows a fifth extra for context plus 2 GB for the system; long contexts need more.
Run it
With mlx-lm on an Apple silicon Mac:
pip install mlx-lmmlx_lm.generate --model mlx-community/AREX-Turbo-4bit --prompt "Hello"
Details
- Base model
- BAAI/AREX-Turbo (quantized)
- Vendor
- BAAI
- Task
- Text generation
- Quantisation
- 4-bit
- Licence
- apache-2.0
- Downloads
- 71 in the last 30 days · 395 all time · 2 likes
- Published
- 2026-07-28 · updated 2026-07-28 (3mo ago)
- Languages
- en
- Tags
- qwen3_5, agent, deep-research, reasoning, tool-use, long-context, qwen3.5, dense, image-text-to-text
Other MLX builds of BAAI/AREX-Turbo
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| AREX-Turbo-4bit (this one) | 4-bit | ≈ 3.0 GB | 8 GB+ | 71 |
| AREX-Turbo-6bit | 6-bit | ≈ 4.1 GB | 8 GB+ | 51 |
| AREX-Turbo-8bit | 8-bit | ≈ 5.1 GB | 8 GB+ | 65 |