TII · First MLX build 18 Dec 2024
Falcon3-Mamba-7B-Instruct
MLX
Text falcon-llm-license
A 7.3B parameter text generation model from TII, with 3 MLX builds, from 4-bit to 8-bit.
- Parameters
- 7.3B From Hugging Face
- Quantisation
- 8-bit Falcon3-Mamba-7B-Instruct-8bits
- Memory needed
- 11 GB Estimate, unified memory
- Download
- 7.7 GB Weights, estimated
- Downloads
- 56 This build, last 30 days
- Task
- Text generation Text
- MLX builds
- 3 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/Falcon3-Mamba-7B-Instruct-8bits --prompt "Hello"MLX builds
3 on mlx-community| Falcon3-Mamba-7B-Instruct-4bits | 4-bit | 4.1 GB | 7 GB | 46 |
|---|---|---|---|---|
| Falcon3-Mamba-7B-Instruct-8bits | 8-bit | 7.7 GB | 11 GB | 56 |
| Falcon3-Mamba-7B-Instruct | Unstated | 14.5 GB | 19 GB | 38 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.