aisingapore · First MLX build 21 Feb 2026
Gemma-SEA-LION-v4-27B-IT
MLX
Text gemma
A 27B parameter text generation model from aisingapore, with one MLX build at bf16.
- Parameters
- 27B From Hugging Face
- Quantisation
- bf16 Gemma-SEA-LION-v4-27B-IT-bf16
- Memory needed
- 63 GB Estimate, unified memory
- Download
- 54.0 GB Weights, estimated
- Downloads
- 28 This build, last 30 days
- Task
- Text generation Text
- MLX builds
- 1 On mlx-community
- Devices
- Mac Apple silicon
Memory
Will it fit?Needs about 63 GB at bf16
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/Gemma-SEA-LION-v4-27B-IT-bf16 --prompt "Hello"MLX builds
1 on mlx-community| Gemma-SEA-LION-v4-27B-IT-bf16 | bf16 | 54.0 GB | 63 GB | 28 |
|---|
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.