MLX Community · First MLX build 16 Apr 2024
nanoLLaVA
MLX
apache-2.0
A 1.1B parameter model, with 2 MLX builds at 4-bit.
- Parameters
- 1.1B From Hugging Face
- Quantisation
- Unstated nanoLLaVA
- Memory needed
- 5 GB Estimate, unified memory
- Download
- 2.1 GB Weights, estimated
- Downloads
- 54 This build, last 30 days
- Task
- —
- MLX builds
- 2 On mlx-community
- Devices
- Mac Apple silicon
Memory
Will it fit?Needs about 5 GB at Unstated
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/nanoLLaVAMLX builds
2 on mlx-community| nanoLLaVA-4bit | 4-bit | 1.4 GB | 4 GB | 34 |
|---|---|---|---|---|
| nanoLLaVA | Unstated | 2.1 GB | 5 GB | 54 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.