MLX Community · First MLX build 15 Nov 2024
falcon-mamba-7b-8bit-instruct
MLX
Text falcon-mamba-7b-license
A 7.3B parameter text generation model, with one MLX build at 8-bit.
- Parameters
- 7.3B From Hugging Face
- Quantisation
- 8-bit falcon-mamba-7b-8bit-instruct
- Memory needed
- 11 GB Estimate, unified memory
- Download
- 7.7 GB Weights, estimated
- Downloads
- 41 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 11 GB at 8-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/falcon-mamba-7b-8bit-instruct --prompt "Hello"MLX builds
1 on mlx-community| falcon-mamba-7b-8bit-instruct | 8-bit | 7.7 GB | 11 GB | 41 |
|---|
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.