8-bit Open on Hugging Face
Parameters
16B
Weights (est.)
≈ 17.3 GB
Mac memory (est.)
24 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/LLaDA2.0-mini-8bit --prompt "Hello"
Details
- Base model
- inclusionAI/LLaDA2.0-mini (quantized)
- Vendor
- inclusionAI
- Task
- Text generation
- Quantisation
- 8-bit
- Licence
- apache-2.0
- Downloads
- 26 in the last 30 days · 350 all time · 0 likes
- Published
- 2025-11-26 · updated 2025-11-26 (11mo ago)
- Tags
- llada2_moe, dllm, diffusion, text_generation, custom_code
Other MLX builds of inclusionAI/LLaDA2.0-mini
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| LLaDA2.0-mini-4bit | 4-bit | ≈ 9.2 GB | 16 GB+ | 50 |
| LLaDA2.0-mini-6bit | 6-bit | ≈ 13.2 GB | 24 GB+ | 29 |
| LLaDA2.0-mini-8bit (this one) | 8-bit | ≈ 17.3 GB | 24 GB+ | 26 |