poolside · First MLX build 18 Jun 2026
Laguna-M.1
MLX
Text apache-2.0
A 226B parameter text generation model from poolside, with 8 MLX builds, from 4-bit to bf16.
- Parameters
- 226B From Hugging Face
- Quantisation
- 4-bit Laguna-M.1-4bit
- Memory needed
- 144 GB Estimate, unified memory
- Download
- 127 GB Weights, estimated
- Downloads
- 54 This build, last 30 days
- Task
- Text generation Text
- MLX builds
- 8 On mlx-community
- Devices
- Mac Apple silicon
Memory
Will it fit?Needs about 144 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/Laguna-M.1-4bit --prompt "Hello"MLX builds
8 on mlx-community| Laguna-M.1-4bit | 4-bit | 127 GB | 144 GB | 54 |
|---|---|---|---|---|
| Laguna-M.1-mxfp4 | MXFP4 | 127 GB | 144 GB | 47 |
| Laguna-M.1-nvfp4 | 4-bit | 127 GB | 144 GB | 28 |
| Laguna-M.1-5bit | 5-bit | 155 GB | 176 GB | 28 |
| Laguna-M.1-6bit | 6-bit | 183 GB | 208 GB | 31 |
| Laguna-M.1-8bit | 8-bit | 240 GB | 271 GB | 28 |
| Laguna-M.1-mxfp8 | MXFP8 | 240 GB | 271 GB | 19 |
| Laguna-M.1-bf16 | bf16 | 452 GB | 507 GB | 24 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.