HPAI-BSC · First MLX build 5 Dec 2024
Llama3.1-Aloe-Beta-8B
MLX
Text llama3.1
A 8B parameter question answering model from HPAI-BSC, with one MLX build at 4-bit.
- Parameters
- 8B From Hugging Face
- Quantisation
- 4-bit Llama3.1-Aloe-Beta-8B
- Memory needed
- 8 GB Estimate, unified memory
- Download
- 4.5 GB Weights, estimated
- Downloads
- 38 This build, last 30 days
- Task
- Question answering Text
- MLX builds
- 1 On mlx-community
- Devices
- Mac Apple silicon
Memory
Will it fit?Needs about 8 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/Llama3.1-Aloe-Beta-8BMLX builds
1 on mlx-community| Llama3.1-Aloe-Beta-8B | 4-bit | 4.5 GB | 8 GB | 38 |
|---|
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.