TII · First MLX build 10 Jun 2025
Falcon-E-3B-Instruct
MLX
Text falcon-llm-license
A 1.5B parameter text generation model from TII, with 4 MLX builds, from 6-bit to 58-bit.
- Parameters
- 1.5B From Hugging Face
- Quantisation
- 58-bit Falcon-E-3B-Instruct-1.58bit
- Memory needed
- 4 GB Estimate, unified memory
- Download
- 999 MB Weights, estimated
- Downloads
- 50 This build, last 30 days
- Task
- Text generation Text
- MLX builds
- 4 On mlx-community
- Devices
- Mac Apple silicon
Memory
Will it fit?Needs about 4 GB at 58-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-E-3B-Instruct-1.58bit --prompt "Hello"MLX builds
4 on mlx-community| Falcon-E-3B-Instruct-6bit | 6-bit | 622 MB | 3 GB | 24 |
|---|---|---|---|---|
| Falcon-E-3B-Instruct-8bit | 8-bit | 820 MB | 3 GB | 24 |
| Falcon-E-3B-Instruct-4bit | 4-bit | 839 MB | 3 GB | 35 |
| Falcon-E-3B-Instruct-1.58bit | 58-bit | 999 MB | 4 GB | 50 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.