MLX Community · First MLX build 21 Jan 2025
mamba2-2.7b
MLX
A 2.7B parameter model, with 3 MLX builds, from 4-bit to 8-bit.
- Parameters
- 2.7B From Hugging Face
- Quantisation
- 4-bit mamba2-2.7b-4bit
- Memory needed
- 3 GB Estimate, unified memory
- Download
- 363 MB Weights, estimated
- Downloads
- 13 This build, last 30 days
- Task
- —
- MLX builds
- 3 On mlx-community
- Devices
- Mac Apple silicon
Memory
Will it fit?Needs about 3 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/mamba2-2.7b-4bitMLX builds
3 on mlx-community| mamba2-2.7b-4bit | 4-bit | 363 MB | 3 GB | 13 |
|---|---|---|---|---|
| mamba2-2.7b-8bit | 8-bit | 891 MB | 3 GB | 9 |
| mamba2-2.7b | Unstated | 5.4 GB | 9 GB | 11 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.