Hcompany · First MLX build 2 Apr 2026
Holo3-35B-A3B
MLX
TextVision apache-2.0
A 35B parameter vision and text model from Hcompany, with one MLX build at 8-bit.
- Parameters
- 35B From Hugging Face
- Quantisation
- 8-bit Holo3-35B-A3B-8bit
- Memory needed
- 46 GB Estimate, unified memory
- Download
- 38.6 GB Weights, estimated
- Downloads
- 49 This build, last 30 days
- Task
- Vision and text Text, Vision
- MLX builds
- 1 On mlx-community
- Devices
- Mac Apple silicon
Memory
Will it fit?Needs about 46 GB at 8-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-vlm$ pip install -U mlx-vlm
$ python -m mlx_vlm.generate --model mlx-community/Holo3-35B-A3B-8bit --image photo.jpg --prompt "Describe this image"MLX builds
1 on mlx-community| Holo3-35B-A3B-8bit | 8-bit | 38.6 GB | 46 GB | 49 |
|---|
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.