TII · First MLX build 17 Dec 2024
Falcon3-10B-Instruct
MLX
Text falcon-llm-license
A 10B parameter text generation model from TII, with 4 MLX builds, from 3-bit to 8-bit.
- Parameters
- 10B From Hugging Face
- Quantisation
- 4-bit Falcon3-10B-Instruct-4bit
- Memory needed
- 9 GB Estimate, unified memory
- Download
- 5.8 GB Weights, estimated
- Downloads
- 225 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 9 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/Falcon3-10B-Instruct-4bit --prompt "Hello"MLX builds
4 on mlx-community| Falcon3-10B-Instruct-3bit | 3-bit | 4.5 GB | 8 GB | 29 |
|---|---|---|---|---|
| Falcon3-10B-Instruct-4bit | 4-bit | 5.8 GB | 9 GB | 225 |
| Falcon3-10B-Instruct-6bit | 6-bit | 8.4 GB | 12 GB | 29 |
| Falcon3-10B-Instruct-8bit | 8-bit | 10.9 GB | 15 GB | 43 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.