TII · First MLX build 5 Jan 2026
Falcon-H1R-7B
MLX
Text falcon-llm-license
A 7.6B parameter text generation model from TII, with 5 MLX builds, from 4-bit to bf16.
- Parameters
- 7.6B From Hugging Face
- Quantisation
- 4-bit Falcon-H1R-7B-4bit
- Memory needed
- 7 GB Estimate, unified memory
- Download
- 4.3 GB Weights, estimated
- Downloads
- 107 This build, last 30 days
- Task
- Text generation Text
- MLX builds
- 5 On mlx-community
- Devices
- Mac Apple silicon
Memory
Will it fit?Needs about 7 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/Falcon-H1R-7B-4bit --prompt "Hello"MLX builds
5 on mlx-community| Falcon-H1R-7B-4bit | 4-bit | 4.3 GB | 7 GB | 107 |
|---|---|---|---|---|
| Falcon-H1R-7B-5bit | 5-bit | 5.2 GB | 8 GB | 33 |
| Falcon-H1R-7B-6bit | 6-bit | 6.2 GB | 9 GB | 51 |
| Falcon-H1R-7B-8bit | 8-bit | 8.1 GB | 12 GB | 42 |
| Falcon-H1R-7B-bf16 | bf16 | 15.2 GB | 19 GB | 41 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.