LatitudeGames · First MLX build 20 Feb 2025
Wayfarer-Large-70B-Llama-3.3
MLX
Text llama3.3
A 71B parameter text generation model from LatitudeGames, with 2 MLX builds, from 3-bit to 4-bit.
- Parameters
- 71B From Hugging Face
- Quantisation
- 4-bit Wayfarer-Large-70B-Llama-3.3-4bit
- Memory needed
- 47 GB Estimate, unified memory
- Download
- 39.7 GB Weights, estimated
- Downloads
- 101 This build, last 30 days
- Task
- Text generation Text
- 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 · mlx-lm$ pip install -U mlx-lm
$ mlx_lm.generate --model mlx-community/Wayfarer-Large-70B-Llama-3.3-4bit --prompt "Hello"MLX builds
2 on mlx-community| Wayfarer-Large-70B-Llama-3.3-3bit | 3-bit | 30.9 GB | 37 GB | 53 |
|---|---|---|---|---|
| Wayfarer-Large-70B-Llama-3.3-4bit | 4-bit | 39.7 GB | 47 GB | 101 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.