kyutai · First MLX build 18 Jan 2025
helium-1-preview-2b
MLX
Text cc-by-4.0
A 2.2B parameter text generation model from kyutai, with 4 MLX builds, from 4-bit to 8-bit.
- Parameters
- 2.2B From Hugging Face
- Quantisation
- 4-bit helium-1-preview-2b-4bit
- Memory needed
- 4 GB Estimate, unified memory
- Download
- 1.2 GB Weights, estimated
- Downloads
- 45 This build, last 30 days
- Task
- Text generation Text
- MLX builds
- 4 On mlx-community
- Devices
- Mac Apple silicon
Memory
Will it fit?Needs about 4 GB at 4-bit
8 GB
16 GB
24 GB
32 GB
64 GB
128 GB
Fits with headroomTight, close other appsWon’t fit
Estimated from the size of the weights, plus a fifth for context and working memory and 2 GB for macOS and your apps. Long contexts need more.
Run it
Terminal · mlx-lm$ pip install -U mlx-lm
$ mlx_lm.generate --model mlx-community/helium-1-preview-2b-4bit --prompt "Hello"MLX builds
4 on mlx-community| helium-1-preview-2b-4bit | 4-bit | 1.2 GB | 4 GB | 45 |
|---|---|---|---|---|
| helium-1-preview-2b-8bit | 8-bit | 2.3 GB | 5 GB | 39 |
| helium-1-preview-2b | Unstated | 4.3 GB | 7 GB | 40 |
| helium-1-preview-2b-float32 | Unstated | 8.7 GB | 12 GB | 31 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.