Aiqre

Model library / poolside

Laguna-S-2.1

Laguna S 2.1 is a 118 billion-parameter mixture-of-experts model for agentic coding with long-context support.

117.6B

Parameters in total

1,048,576

Context length in tokens, as published

219 GiB

Weights at the released precision

openmdw-1.1

Licence declared on the repository

Overview

What this model is.

Laguna S 2.1 is a 118 billion total-parameter mixture-of-experts language model released by poolside. It uses a token-choice router with softplus gating over 256 routed experts plus one shared expert, grouped-query attention, and a mixed global and sliding-window attention layout. The model is targeted at software engineering and agentic coding, offering native interleaved reasoning and tool-calling capabilities.

In practice the model comprises 48 layers, 12 global and 36 sliding-window attention layers, and activates roughly 8 billion parameters per token. It supports a 1,048,576-token context window. The BF16 checkpoint occupies about 236 GB, requiring multiple GPUs, while quantised variants reduce memory needs. It is released under the permissive OpenMDW-1.1 licence, allowing unrestricted commercial use.

Specification

The published shape.

Repositorypoolside/Laguna-S-2.1
Publisherpoolside
Published13 July 2026
ArchitectureLagunaForCausalLM
Model typelaguna
Parameters117,561,977,600
Layers48
Hidden size3,072
Attention heads48, 8 key/value heads
Context length1,048,576 tokens
Vocabulary100,352 tokens
Weight formatbfloat16
Licenceopenmdw-1.1

Memory

How much VRAM the weights need.

Parameter count multiplied by the bytes each format uses. The key-value cache comes on top.

PrecisionWeightsNotes
bf16219.0 GiBFull precision as released
fp8109.5 GiB8-bit, near-lossless on most models
int454.7 GiB4-bit, smallest footprint

The cache costs 192 KiB per token at 16-bit, so the full 1,048,576-token context of one request needs about 192.0 GiB. Concurrency multiplies that number, not the weights.

That figure is an upper bound: this model uses sliding-window attention with a 512-token window on some layers, so long requests cache less than this.

Hardware

Which card runs it.

At the released precision, with 90% of the card given to the server and 2.5 GiB kept for the runtime. The context column is what is left for the cache on that setup.

GPUCards neededFree for cacheContext it holds
RTX 4090 24GB more than 8
RTX 5090 32GB more than 8
L40S 48GB 8 106.6 GiB about 582,307 tokens
A100 80GB 4 59.0 GiB about 322,348 tokens
H100 80GB 4 59.0 GiB about 322,348 tokens
RTX PRO 6000 96GB 4 116.6 GiB about 636,921 tokens
H200 141GB 2 29.8 GiB about 162,877 tokens

Serving

Running it yourself.

A vLLM launch line for the shape above. Check the model card for a runtime the publisher recommends.

vllm serve poolside/Laguna-S-2.1 \
  --tensor-parallel-size 8 \
  --max-model-len 581632 \
  --gpu-memory-utilization 0.90

Questions

The things people ask about this model.

How much GPU memory does Laguna-S-2.1 need?

The weights take about 219 GiB at the released precision. No single card in the table above holds that, so it needs several GPUs or a lower precision.

What licence does Laguna-S-2.1 use?

The repository declares openmdw-1.1. Read the licence text before commercial use: the name alone does not tell you what is allowed.

How long a context does it support?

The configuration allows 1,048,576 tokens. Whether the whole window is usable depends on the memory left for the cache, which the hardware table works out per card.

Can I use it through an API instead of hosting it?

This page is a reference, and Aiqre does not serve this model today. We deploy open-weight models on dedicated EU hardware on request, so if you want an OpenAI-compatible endpoint for it, email [email protected] with the model name and roughly what volume you expect.

Also in the library

Related models.

inclusionAI/Ling-3.0-flash-Fin

Ling-3.0-flash-Fin is a 127.5 billion-parameter finance-enhanced language model for long-context financial research and analysis.

inclusionAI/Ling-3.0-flash

Ling-3.0-flash is a 127.5 B parameter hybrid-linear language model from inclusionAI for reasoning and long-context applications.

Hosting

Want this model on a dedicated EU GPU?

Tell us the model and roughly what volume you expect. We reply with a price and an OpenAI-compatible endpoint, with your prompts never stored.