Salesforce · First MLX build 21 Oct 2024
xLAM-7b-fc-r
MLX
Text cc-by-nc-4.0
A 6.9B parameter text generation model from Salesforce, with one MLX build.
- Parameters
- 6.9B From Hugging Face
- Quantisation
- Unstated xLAM-7b-fc-r
- Memory needed
- 18 GB Estimate, unified memory
- Download
- 13.8 GB Weights, estimated
- Downloads
- 39 This build, last 30 days
- Task
- Text generation Text
- MLX builds
- 1 On mlx-community
- Devices
- Mac Apple silicon
Memory
Will it fit?Needs about 18 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 · mlx-lm$ pip install -U mlx-lm
$ mlx_lm.generate --model mlx-community/xLAM-7b-fc-r --prompt "Hello"MLX builds
1 on mlx-community| xLAM-7b-fc-r | Unstated | 13.8 GB | 18 GB | 39 |
|---|
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.