USASI
Model release

Laguna S 2.1

Release in the Laguna family · version S 2.1

Maintained by Poolside1

Laguna S 2.1 is a mixture-of-experts model with 118B total and about 8B active parameters per token, built for agentic coding. It has 48 layers mixing global and sliding-window attention, 256 routed experts plus one shared expert, and a 1,048,576-token context window, with reasoning that can be switched on or off per request.1

Last reviewedEntry updated Documented release Jul 21, 2026

Availability and license

Overall availability

Public

Weights download from Hugging Face without an access gate. Also served through the Poolside API and OpenRouter.17

Availability is separate from permission: read the license before using or redistributing.

OpenMDW-1.1 grants broad use rights and places no restrictions on outputs. It requires keeping the license and notices when redistributing, and ends the rights of anyone who sues claiming the materials infringe a patent or copyright. The model card also asks users to follow Poolside's Acceptable Use Policy.21

Model-disclosure tier

Computed from the checklist below using USASI rubric v0.1. An editorial category, not a certification.
Model-disclosure tier (USASI rubric v0.1): Open-weight

The model parameters for this release can be downloaded by the public. License terms may still restrict use, redistribution, or commercial use.

The weights are under a license that is not on the rubric's OSI-approved list. Read its terms before use.

How tiers are computed

Public materials checklist

Items for a model under USASI rubric v0.1. Unknown means unassessed or insufficient evidence.
Public materials checklist for Laguna S 2.1
ItemStatusNotes and evidence
WeightsCan the general public download the model parameters for this release?PublicBF16 weights are in the ungated repository; FP8, NVFP4, INT4, and GGUF variants are published as separate repositories.1
Inference codeIs code for running the model published?PublicThe repository includes modeling code (modeling_laguna.py), and the model card documents vLLM, SGLang, TensorRT-LLM, llama.cpp, and Ollama.13
Training codeIs the code used to train the model published?UnknownNot assessed.
Training-data informationPublic = the training data itself can be obtained. Partial = composition or sources are documented without full access.PartialThe release blog says S 2.1 was pre-trained on exactly the same data as Laguna XS 2.1 and describes post-training task sources (open-source repositories, internally synthesized tasks, and tasks acquired from external data vendors) at a high level. The pre-training data composition is not described for this release, and the data is not released.4
Training recipeAre the training configuration and procedure documented in enough detail to follow?PartialThe release blog describes the training at a high level: a scale-up of the Laguna XS family with training-code fixes and small recipe changes, an SFT stage partly using synthetic data, and reinforcement learning run in FP8 precision. The blog does not give hyperparameters or training configurations.4
Evaluation materialsPublic = evaluation code or prompts that let others re-run the evaluations are published. Partial = results only.PartialThe model card publishes benchmark results, and Poolside publishes full evaluation trajectories.15

What it is useful for

Poolside documents it for long-running coding and research tasks with extended tool use, and for running an open-weight model locally on high-memory hardware.6

Run and use notes

Documented facts only. No hardware or performance claims are made without a cited source and stated assumptions.
  • The model card states that the BF16 checkpoint is roughly 236GB of weights and needs multiple GPUs, and that quantized variants reduce this. Its vLLM and SGLang examples use tensor parallelism of 4.1
  • llama.cpp support uses Poolside's llama.cpp fork (laguna branch); the model card notes that base support is under review upstream.1

Organization context

Provenance and derivatives

Poolside states that it trains its models from scratch on its own data and infrastructure. The model card describes Laguna S 2.1 as sharing the Laguna family architecture recipe with Laguna XS 2.1 and Laguna M.1.71

Other releases in the Laguna family

  • Laguna XS 2.1Model-disclosure tier (USASI rubric v0.1): Open-weight

Laguna family overview

U.S. eligibility

Project eligibility rests on documented governing or maintaining entities, not on contributors.

Eligible · basis: U.S. headquarters

Developed and published by Poolside, Inc., which states that it is headquartered in San Francisco and trains its models from scratch on its own data and infrastructure. See the poolside organization record for the assessment of its French presence.71

Assessed Sep 29, 2026

Sources

  1. 1.
    poolside/Laguna-S-2.1 model card (external site: huggingface.co)

    Poolside · Model card · accessed Sep 29, 2026

  2. 2.
  3. 3.
    Laguna-S-2.1 repository file listing (external site: huggingface.co)

    Hugging Face · Repository · accessed Sep 29, 2026

  4. 4.
    Introducing Laguna S 2.1 (external site: poolside.ai)

    Poolside · Announcement · published Jul 21, 2026 · accessed Sep 29, 2026

  5. 5.
  6. 6.
    Model release notes (external site: docs.poolside.ai)

    Poolside · Release notes · accessed Sep 29, 2026

  7. 7.
    Poolside releases Laguna S 2.1, the West's most capable open-weight model (external site: globenewswire.com)

    Poolside via GlobeNewswire · Announcement · published Jul 21, 2026 · accessed Sep 29, 2026

This listing is not an endorsement, a safety assessment, or a federal approval.

Support Us

Help keep USASI useful.

Optional. No USASI account required. Payment takes place on the linked provider’s website (Buy Me a Coffee).

About supporting this project