Google · First MLX build 27 Aug 2024
gemma-2-2b
MLX
gemma
A 2.6B parameter model from Google, with 2 MLX builds at 4-bit.
- Parameters
- 2.6B From Hugging Face
- Quantisation
- 4-bit dolphin-2.9.4-gemma2-2b-4bit
- Memory needed
- 4 GB Estimate, unified memory
- Download
- 1.5 GB Weights, estimated
- Downloads
- 32 This build, last 30 days
- Task
- —
- MLX builds
- 2 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 · Hugging Face CLI$ pip install -U huggingface_hub
$ hf download mlx-community/dolphin-2.9.4-gemma2-2b-4bitMLX builds
2 on mlx-community| dolphin-2.9.4-gemma2-2b-4bit | 4-bit | 1.5 GB | 4 GB | 32 |
|---|---|---|---|---|
| dolphin-2.9.4-gemma2-2b-mlx | Unstated | 5.2 GB | 8 GB | 23 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.