Meta · First MLX build 16 Aug 2024
Llama-3.1-8B
MLX
llama3
A 8B parameter model from Meta, with 3 MLX builds, from 4-bit to bf16.
- Parameters
- 8B From Hugging Face
- Quantisation
- 4-bit Hermes-3-Llama-3.1-8B-4bit
- Memory needed
- 8 GB Estimate, unified memory
- Download
- 4.5 GB Weights, estimated
- Downloads
- 1.5K This build, last 30 days
- Task
- —
- MLX builds
- 3 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/Hermes-3-Llama-3.1-8B-4bitMLX builds
3 on mlx-community| Hermes-3-Llama-3.1-8B-4bit | 4-bit | 4.5 GB | 8 GB | 1.5K |
|---|---|---|---|---|
| Hermes-3-Llama-3.1-8B-8bit | 8-bit | 8.5 GB | 12 GB | 234 |
| Hermes-3-Llama-3.1-8B-bf16 | bf16 | 16.1 GB | 20 GB | 97 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.