fp16 Open on Hugging Face
Parameters
8.0B
Weights (est.)
≈ 16.0 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/LLaDA-8B-Instruct-mlx-fp16 --prompt "Hello"
Details
- Base model
- GSAI-ML/LLaDA-8B-Instruct (finetune)
- Vendor
- GSAI-ML
- Task
- Text generation
- Quantisation
- fp16
- Licence
- mit
- Downloads
- 16 in the last 30 days · 424 all time · 1 likes
- Published
- 2025-03-12 · updated 2025-03-12 (1y ago)
- Tags
- llada, custom_code
Other MLX builds of GSAI-ML/LLaDA-8B-Instruct
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| LLaDA-8B-Instruct-mlx-4bit | 4-bit | ≈ 4.5 GB | 8 GB+ | 52 |
| LLaDA-8B-Instruct-mlx-8bit | 8-bit | ≈ 8.5 GB | 16 GB+ | 28 |
| LLaDA-8B-Instruct-mlx-fp16 (this one) | fp16 | ≈ 16.0 GB | 24 GB+ | 16 |