Google · First MLX build 21 May 2025
medgemma-27b-text-it
MLX
Text health-ai-developer-foundations
A 28B parameter text generation model from Google, with 4 MLX builds, from 4-bit to bf16.
- Parameters
- 28B From Hugging Face
- Quantisation
- 4-bit medgemma-27b-text-it-4bit
- Memory needed
- 20 GB Estimate, unified memory
- Download
- 16.0 GB Weights, estimated
- Downloads
- 229 This build, last 30 days
- Task
- Text generation Text
- MLX builds
- 4 On mlx-community
- Devices
- Mac Apple silicon
Memory
Will it fit?Needs about 20 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 · mlx-lm$ pip install -U mlx-lm
$ mlx_lm.generate --model mlx-community/medgemma-27b-text-it-4bit --prompt "Hello"MLX builds
4 on mlx-community| medgemma-27b-text-it-4bit | 4-bit | 16.0 GB | 20 GB | 229 |
|---|---|---|---|---|
| medgemma-27b-text-it-6bit | 6-bit | 23.1 GB | 28 GB | 69 |
| medgemma-27b-text-it-8bit | 8-bit | 30.2 GB | 36 GB | 156 |
| medgemma-27b-text-it-bf16 | bf16 | 56.8 GB | 66 GB | 167 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.