Ai2 · First MLX build 27 Jan 2026
SERA-32B
MLX
Text apache-2.0
A 33B parameter text generation model from Ai2, with 4 MLX builds, from 4-bit to 8-bit.
- Parameters
- 33B From Hugging Face
- Quantisation
- 4-bit SERA-32B-4bit
- Memory needed
- 23 GB Estimate, unified memory
- Download
- 18.4 GB Weights, estimated
- Downloads
- 29 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 23 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/SERA-32B-4bit --prompt "Hello"MLX builds
4 on mlx-community| SERA-32B-4bit | 4-bit | 18.4 GB | 23 GB | 29 |
|---|---|---|---|---|
| SERA-32B-5bit | 5-bit | 22.5 GB | 28 GB | 15 |
| SERA-32B-6bit | 6-bit | 26.6 GB | 32 GB | 16 |
| SERA-32B-8bit | 8-bit | 34.8 GB | 41 GB | 17 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.