IBM · First MLX build 28 Oct 2025
granite-4.0-h-1b
MLX
Text apache-2.0
A 1.5B parameter text generation model from IBM, with 6 MLX builds, from 3-bit to bf16.
- Parameters
- 1.5B From Hugging Face
- Quantisation
- 6-bit granite-4.0-h-1b-6bit
- Memory needed
- 4 GB Estimate, unified memory
- Download
- 1.2 GB Weights, estimated
- Downloads
- 505 This build, last 30 days
- Task
- Text generation Text
- MLX builds
- 6 On mlx-community
- Devices
- Mac Apple silicon
Memory
Will it fit?Needs about 4 GB at 6-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/granite-4.0-h-1b-6bit --prompt "Hello"MLX builds
6 on mlx-community| granite-4.0-h-1b-3bit | 3-bit | 641 MB | 3 GB | 27 |
|---|---|---|---|---|
| granite-4.0-h-1b-4bit | 4-bit | 823 MB | 3 GB | 268 |
| granite-4.0-h-1b-5bit | 5-bit | 1.0 GB | 4 GB | 23 |
| granite-4.0-h-1b-6bit | 6-bit | 1.2 GB | 4 GB | 505 |
| granite-4.0-h-1b-8bit | 8-bit | 1.6 GB | 4 GB | 37 |
| granite-4.0-h-1b-bf16 | bf16 | 2.9 GB | 6 GB | 25 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.