Ai2 · First MLX build 24 Jun 2026
tmax-27b
MLX
Text apache-2.0
A 27B parameter text generation model from Ai2, with 3 MLX builds, from 4-bit to 8-bit.
- Parameters
- 27B From Hugging Face
- Quantisation
- 6-bit Tmax-27B-MLX-6bit
- Memory needed
- 27 GB Estimate, unified memory
- Download
- 21.9 GB Weights, estimated
- Downloads
- 29 This build, last 30 days
- Task
- Text generation Text
- MLX builds
- 3 On mlx-community
- Devices
- Mac Apple silicon
Memory
Will it fit?Needs about 27 GB at 6-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/Tmax-27B-MLX-6bit --prompt "Hello"MLX builds
3 on mlx-community| Tmax-27B-MLX-4bit | 4-bit | 15.1 GB | 19 GB | 26 |
|---|---|---|---|---|
| Tmax-27B-MLX-6bit | 6-bit | 21.9 GB | 27 GB | 29 |
| Tmax-27B-MLX-8bit | 8-bit | 28.6 GB | 34 GB | 28 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.