MLX Community · First MLX build 25 Apr 2024
dolphin-2.9-llama3-70b
MLX
llama3
A 71B parameter model, with 2 MLX builds, from 4-bit to 8-bit.
- Parameters
- 71B From Hugging Face
- Quantisation
- 4-bit dolphin-2.9-llama3-70b-4bit
- Memory needed
- 47 GB Estimate, unified memory
- Download
- 39.7 GB Weights, estimated
- Downloads
- 752 This build, last 30 days
- Task
- —
- MLX builds
- 2 On mlx-community
- Devices
- Mac Apple silicon
Memory
Will it fit?Needs about 47 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-llama3-70b-4bitMLX builds
2 on mlx-community| dolphin-2.9-llama3-70b-4bit | 4-bit | 39.7 GB | 47 GB | 752 |
|---|---|---|---|---|
| dolphin-2.9-llama3-70b-8bit | 8-bit | 75.0 GB | 86 GB | 132 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.