poolside · First MLX build 21 Jul 2026
Laguna-S-2.1
MLX
Text openmdw-1.1
A 118B parameter text generation model from poolside, with 9 MLX builds, from 2-bit to 6-bit.
- Parameters
- 118B From Hugging Face
- Quantisation
- 4-bit Laguna-S-2.1-oQ4e
- Memory needed
- 76 GB Estimate, unified memory
- Download
- 66.2 GB Weights, estimated
- Downloads
- 1.1K This build, last 30 days
- Task
- Text generation Text
- MLX builds
- 9 On mlx-community
- Devices
- Mac Apple silicon
Memory
Will it fit?Needs about 76 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-S-2.1-oQ4e --prompt "Hello"MLX builds
9 on mlx-community| Laguna-S-2.1-oQ2e-fast | 2-bit | 36.8 GB | 44 GB | 289 |
|---|---|---|---|---|
| Laguna-S-2.1-oQ2e | 2-bit | 36.8 GB | 44 GB | 152 |
| Laguna-S-2.1-OptiQ-2bit | 2-bit | 36.8 GB | 44 GB | 132 |
| Laguna-S-2.1-oQ3e-fast | 3-bit | 51.5 GB | 60 GB | 111 |
| Laguna-S-2.1-oQ3e | 3-bit | 51.5 GB | 60 GB | 84 |
| Laguna-S-2.1-oQ4e | 4-bit | 66.2 GB | 76 GB | 1.1K |
| Laguna-S-2.1-oQ4e-fast | 4-bit | 66.2 GB | 76 GB | 176 |
| Laguna-S-2.1-oQ5e | 5-bit | 80.9 GB | 93 GB | 92 |
| Laguna-S-2.1-oQ6e | 6-bit | 95.6 GB | 109 GB | 195 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.