unsloth · First MLX build 1 May 2026
granite-4.1-8b
MLX
A 8.8B parameter model from unsloth, with 3 MLX builds, from 4-bit to 8-bit.
- Parameters
- 8.8B From Hugging Face
- Quantisation
- 4-bit unsloth-granite-4.1-8b-mlx-oQ4
- Memory needed
- 8 GB Estimate, unified memory
- Download
- 4.9 GB Weights, estimated
- Downloads
- 47 This build, last 30 days
- Task
- —
- MLX builds
- 3 On mlx-community
- Devices
- Mac Apple silicon
Memory
Will it fit?Needs about 8 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 · Hugging Face CLI$ pip install -U huggingface_hub
$ hf download mlx-community/unsloth-granite-4.1-8b-mlx-oQ4MLX builds
3 on mlx-community| unsloth-granite-4.1-8b-mlx-oQ4 | 4-bit | 4.9 GB | 8 GB | 47 |
|---|---|---|---|---|
| unsloth-granite-4.1-8b-mlx-oQ6 | 6-bit | 7.1 GB | 10 GB | 29 |
| unsloth-granite-4.1-8b-mlx-oQ8 | 8-bit | 9.3 GB | 13 GB | 31 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.