4-bit Open on Hugging Face
Parameters
8.1B
Weights (est.)
≈ 4.5 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/Apertus-8B-2509-4bit --prompt "Hello"
Details
- Base model
- swiss-ai/Apertus-8B-2509 (quantized)
- Vendor
- swiss-ai
- Task
- Text generation
- Quantisation
- 4-bit
- Licence
- apache-2.0
- Downloads
- 65 in the last 30 days · 1.6K all time · 1 likes
- Published
- 2025-09-03 · updated 2025-09-03 (1y ago)
- Tags
- apertus, multilingual, compliant, swiss-ai
Other MLX builds of swiss-ai/Apertus-8B-2509
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| Apertus-8B-2509-4bit (this one) | 4-bit | ≈ 4.5 GB | 8 GB+ | 65 |
| Apertus-8B-2509-bf16 | bf16 | ≈ 16.1 GB | 24 GB+ | 33 |