4-bit Open on Hugging Face
Parameters
2.2B
Weights (est.)
≈ 1.2 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/helium-1-preview-2b-4bit --prompt "Hello"
Details
- Base model
- kyutai/helium-1-preview-2b (quantized)
- Vendor
- kyutai
- Task
- Text generation
- Quantisation
- 4-bit
- Licence
- cc-by-4.0
- Downloads
- 46 in the last 30 days · 322 all time · 1 likes
- Published
- 2025-01-18 · updated 2025-01-18 (1y ago)
- Languages
- en, fr, de, it, pt, es
- Tags
- helium
Other MLX builds of kyutai/helium-1-preview-2b
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| helium-1-preview-2b-4bit (this one) | 4-bit | ≈ 1.2 GB | 8 GB+ | 46 |
| helium-1-preview-2b-8bit | 8-bit | ≈ 2.3 GB | 8 GB+ | 40 |
| helium-1-preview-2b | — | ≈ 4.3 GB | 8 GB+ | 41 |
| helium-1-preview-2b-float32 | — | ≈ 8.7 GB | 16 GB+ | 32 |