MLX Community · First MLX build 3 Jun 2025
Holo1-7B
MLX
TextVision apache-2.0
A 8.3B parameter vision and text model, with 5 MLX builds, from 3-bit to 8-bit.
- Parameters
- 8.3B From Hugging Face
- Quantisation
- 6-bit Holo1-7B-6bit
- Memory needed
- — GB Estimate, unified memory
- Download
- — Weights, estimated
- Downloads
- 36 This build, last 30 days
- Task
- Vision and text Text, Vision
- MLX builds
- 5 On mlx-community
- Devices
- Mac Apple silicon
Memory
Hugging Face does not list a weights size for this build, so there is no memory estimate.
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-vlm$ pip install -U mlx-vlm
$ python -m mlx_vlm.generate --model mlx-community/Holo1-7B-6bit --image photo.jpg --prompt "Describe this image"MLX builds
5 on mlx-community| Holo1-7B-3bit | 3-bit | 4.7 GB | 8 GB | 23 |
|---|---|---|---|---|
| Holo1-7B-bf16 | bf16 | 16.6 GB | 21 GB | 28 |
| Holo1-7B-6bit | 6-bit | — | — | 36 |
| Holo1-7B-4bit | 4-bit | — | — | 25 |
| Holo1-7B-8bit | 8-bit | — | — | 25 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.