INSAIT-Institute · First MLX build 5 Jun 2026
MamayLM-Gemma-3-27B-IT-v2.0
MLX
TextVision gemma
A 27B parameter vision and text model from INSAIT-Institute, with one MLX build at fp16.
- Parameters
- 27B From Hugging Face
- Quantisation
- fp16 MamayLM-Gemma-3-27B-IT-v2.0-mlx-fp16
- Memory needed
- 63 GB Estimate, unified memory
- Download
- 54.0 GB Weights, estimated
- Downloads
- 38 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 63 GB at fp16
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/MamayLM-Gemma-3-27B-IT-v2.0-mlx-fp16 --image photo.jpg --prompt "Describe this image"MLX builds
1 on mlx-community| MamayLM-Gemma-3-27B-IT-v2.0-mlx-fp16 | fp16 | 54.0 GB | 63 GB | 38 |
|---|
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.