4-bit Open on Hugging Face
Parameters
226B
Weights (est.)
≈ 127 GB
Mac memory (est.)
192 GB+
Size is estimated from the parameter count and quantisation. Memory allows a fifth extra for context plus 2 GB for the system; long contexts need more.
Run it
With mlx-lm on an Apple silicon Mac:
pip install mlx-lmmlx_lm.generate --model mlx-community/Laguna-M.1-nvfp4 --prompt "Hello"
Details
- Base model
- poolside/Laguna-M.1 (quantized)
- Vendor
- poolside
- Task
- Text generation
- Quantisation
- 4-bit
- Licence
- apache-2.0
- Downloads
- 26 in the last 30 days · 335 all time · 0 likes
- Published
- 2026-06-18 · updated 2026-06-18 (4mo ago)
- Tags
- laguna, laguna-m.1, vllm, sglang, bf16, custom_code
Other MLX builds of poolside/Laguna-M.1
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| Laguna-M.1-4bit | 4-bit | ≈ 127 GB | 192 GB+ | 51 |
| Laguna-M.1-mxfp4 | MXFP4 | ≈ 127 GB | 192 GB+ | 44 |
| Laguna-M.1-nvfp4 (this one) | 4-bit | ≈ 127 GB | 192 GB+ | 26 |
| Laguna-M.1-5bit | 5-bit | ≈ 155 GB | 192 GB+ | 25 |
| Laguna-M.1-6bit | 6-bit | ≈ 183 GB | 256 GB+ | 31 |
| Laguna-M.1-8bit | 8-bit | ≈ 240 GB | 512 GB+ | 25 |
| Laguna-M.1-mxfp8 | MXFP8 | ≈ 240 GB | 512 GB+ | 18 |
| Laguna-M.1-bf16 | bf16 | ≈ 452 GB | 512 GB+ | 22 |