// poolside Laguna · Text LLM
Laguna-M.1: VRAM & local deployment
225B total · 23B active (MoE) parameters. About 153 GB at 4-bit and 498 GB at BF16 with one 8K-token request.
released 2026-06-15licence: Commercial OKmemory figures are estimates
01Specs
| Publisher | poolside · poolside |
|---|---|
| Family / series | poolside Laguna · Laguna-M.1 |
| Type | Text LLM (text-generation) |
| Parameters | 225B total · 23B active (MoE) Source: official model card“225B total parameters and 23B activated parameters per token” |
| Context length | 256K tokens (262,144)max_position_embeddings in config.json |
| Architecture | 70 layers · GQA · MoE |
| Released weights | BF16 · 452 GBdownload |
| Licence | Apache-2.0 · Commercial OKPermissive licence (Apache-2.0 / MIT / CC-BY / OpenMDW): commercial use allowed. |
| Released | 2026-06-15 (Hugging Face repo created) |
02How much VRAM it needs (estimate)
Total = weights + 10% + 0.5GB overhead + KV cache for one request (FP16 KV). More concurrent users multiply the KV column.
| Precision | Weights | Total @ 8K | Total @ 32K | Total @ 128K | Smallest GPU | Mac |
|---|---|---|---|---|---|---|
| BF16 / FP16 (original) | 450 GB | 498 GB | 505 GB | 533 GB | 8 × H100 (640GB) | — |
| FP8 / INT8 / Q8_0 | 239 GB | 266 GB | 273 GB | 301 GB | 4 × RTX PRO 6000 (384GB) | Mac 512GB |
| 4-bit (Q4_K_M / AWQ / GPTQ-Int4) | 136 GB | 153 GB | 160 GB | 188 GB | 4 × RTX PRO 6000 (384GB) | Mac 256GB |
KV cache per request: 8K 2.4 GB · 32K 9.4 GB · 128K 37.6 GB
Bits per weight: BF16 16, FP8 8.5, 4-bit 4.85. “Fits” = total ≤ 90% of memory; Mac GPU can use ~2/3 of unified memory (≤36GB) or ~3/4 (larger). For MoE, all experts must be in memory, so size by total parameters. Method →
03How to run it
Only runtimes the publisher or the runtime’s official library names for this model.
- vLLM — mentioned in the official model card
- SGLang — mentioned in the official model card
- Transformers — mentioned in the official model card
- TensorRT-LLM — mentioned in the official model card
04Official repositories & quantised builds
4 official repo(s) from poolside.
- Laguna-M.1 main
- Laguna-M.1-NVFP4 NVFP4
- Laguna-M.1-FP8 FP8
- Laguna-M.1-base Base
05Other poolside Laguna models
All 4 →| Model | Params | 4-bit total | Released |
|---|---|---|---|
| Laguna-S-2.1 | 118B / 8B | 79.7 GB | 2026-07-13 |
| Laguna-XS-2.1 | 33B / 3B | 22.9 GB | 2026-06-20 |
| Laguna-XS.2 | 33B / 3B | 22.9 GB | 2026-04-23 |
06Sources
Data checked 2026-07-14. Parameters, context and licence are copied from the official repository; memory figures are our estimates.