Are the weights open and can I run Laguna S 2.1 locally?

Yes, weights are available on Hugging Face under the OpenMDW-1.1 licence, which permits commercial use and modification without asking permission. The BF16 checkpoint needs roughly 236GB of GPU memory, so you will need multiple GPUs; GGUF, FP8, NVFP4 and INT4 quantized variants are also available to reduce that requirement.

What does Laguna S 2.1 cost and what is its context window?

Via the API it is $0.09 per million input tokens and $0.18 per million output tokens, with a 1,048,576-token context window. If you use the free tier, Poolside may use your inputs and outputs to improve the model.

How does Laguna S 2.1 compare to the rest of the Laguna series?

It sits between Laguna XS 2.1 (33B total, 3B active) and Laguna M.1 (225B total, 23B active), sharing the same architecture family and compatible with the same inference engines: vLLM, SGLang, Transformers, TRT-LLM and llama.cpp.

▲

26.3%

this week

Laguna S 2.1

9008°

#llm #poolside #reasoning #coding #agents #long context

Run this model

Offers / Ads

OpenRouter Terminal / API

Pay per token

Chat with this model in the browser or call it from your code with one API key.

Poolside | 1,048,576 token context | $0.09/M input, $0.18/M output. Laguna S 2.1 is the latest coding agent model from PoolsideOpens in new tab. Laguna S 2.1 is a 118B total parameter model with 8B active parameters, scoring 70.2% on Terminal-Bench 2.1 and 40.4% on DeepSWE, making it one of the strongest coding models in its category. Open-weight under the OpenMDW-1.1 license. Laguna S 2.1 is designed for software engineering and agentic coding use cases, and you are responsible for confirming that it is appropriate for your intended application. Laguna S 2.1 is subject to the OpenMDW-1.1…Poolside | 1,048,576 token context | $0.09/M input, $0.18/M output. Laguna S 2.1 is the latest coding agent model from PoolsideOpens in new tab. Laguna S 2.1 is a 118B total parameter model with 8B active parameters, scoring 70.2% on Terminal-Bench 2.1 and 40.4% on DeepSWE, making it one of the strongest coding models in its category. Open-weight under the OpenMDW-1.1 license. Laguna S 2.1 is designed for software engineering and agentic coding use cases, and you are responsible for confirming that it is appropriate for your intended application. Laguna S 2.1 is subject to the OpenMDW-1.1 LicenseOpens in new tab, and should be used consistently with Poolside's Acceptable Use PolicyOpens in new tab. We advise against circumventing Laguna S 2.1 safety guardrails without implementing substantially equivalent mitigations appropriate for your use case. Please report security vulnerabilities or safety concerns to [email protected]. If you are using Laguna S 2.1 for free, we may use your inputs and outputs to train and improve our models.

Guides for this model

Best local LLM by use case (October 2026): the right open model for every job

How much VRAM do I actually need for local AI?

What is a GGUF file? Quantized models explained (Q4, Q8, fp8, NF4)

How to Install Ollama and Run a Local AI (Windows, Mac, Linux)

All guides

Captain's notes

Written by Captain, the house editor

Notes from 2026-10-13

Laguna S 2.1 is a 118B-parameter Mixture-of-Experts coding model from Poolside, with only 8B parameters active per token. It is built for agentic software engineering and long-horizon coding tasks, with a 1M-token context window and native reasoning between tool calls. Open weights under the permissive OpenMDW-1.1 licence make it a serious option for teams who want to self-host a frontier-class coding agent.

Known for

Strong agentic coding results: 70.2% on Terminal-Bench 2.1, 40.4% on DeepSWE
1,048,576-token context window for large codebases and long-horizon tasks
Native interleaved reasoning between tool calls, controllable per request
Fully permissive OpenMDW-1.1 licence: commercial use, modification, no permission needed
Quantized variants available: FP8, NVFP4, INT4 and GGUF for flexible deployment

Watch out for

BF16 weights require roughly 236GB across multiple GPUs; quantized variants ease this but add trade-offs.
Free-tier usage allows Poolside to use your inputs and outputs for model training.
Benchmarks are self-reported by Poolside; third-party scores are marked as such and comparisons vary by evaluator.

Best for

Prompts to try

Debug a failing test suite

I have a Python FastAPI service. The integration tests pass locally but fail in CI with a 422 Unprocessable Entity on POST /orders. The request body is identical in both environments. Walk through the most likely causes, write a diagnostic script I can run in CI to log the raw request and validation errors, and suggest fixes.

Plan a refactor across files

I need to migrate a Node.js Express app from CommonJS require() to ES module import/export syntax. The project has about 40 files, uses Jest for tests, and has a few dynamic require() calls. Give me a step-by-step migration plan, flag the edge cases that break automatically, and write a shell script to handle the mechanical renames.

Agentic repo audit

Act as a senior engineer reviewing a pull request. Here is a diff of changes to a authentication module that replaces bcrypt with Argon2. Check for security regressions, incorrect parameter choices, missing error handling, and any test gaps. List each issue with file and line reference, severity, and a concrete fix.

Compare with

Laguna XS 2.1
Open-weights model
262,144 token context · $0.06/M input, $0.12/M output
GPT-6 Luna
API-only model
1,050,000 token context · $0.10/M input, $0.50/M output
Claude Opus 5.5
API-only model
1,000,000 token context · $4.00/M input, $20.00/M output
Muse Spark 1.3 Contributor
API-only model
1,048,576 token context · $0.10/M input, $0.20/M output

More text models from poolside

Questions people ask

Are the weights open and can I run Laguna S 2.1 locally?: Yes, weights are available on Hugging Face under the OpenMDW-1.1 licence, which permits commercial use and modification without asking permission. The BF16 checkpoint needs roughly 236GB of GPU memory, so you will need multiple GPUs; GGUF, FP8, NVFP4 and INT4 quantized variants are also available to reduce that requirement.
What does Laguna S 2.1 cost and what is its context window?: Via the API it is $0.09 per million input tokens and $0.18 per million output tokens, with a 1,048,576-token context window. If you use the free tier, Poolside may use your inputs and outputs to improve the model.
How does Laguna S 2.1 compare to the rest of the Laguna series?: It sits between Laguna XS 2.1 (33B total, 3B active) and Laguna M.1 (225B total, 23B active), sharing the same architecture family and compatible with the same inference engines: vLLM, SGLang, Transformers, TRT-LLM and llama.cpp.

Captain's verdict
A genuinely permissive open-weights coding agent that punches well above its active-parameter count, assuming you have the hardware to run it.

Model card on Hugging Face

Captain writes these notes from the model's own description and model card. Prices and context sizes are the provider's at the time of writing and can change.

Ranking badge

Updated Oct 22, 2026

Made this model? Show this badge on your page.

Paste it into your Hugging Face card or Civitai description.

Change colors / personalize / get code

Also ranked: #26 Hottest Text / LLM model · #26 Hottest Text / LLM text model

Not this creator?

Get your own badge

Laguna S 2.1 Popularity Trend

Heat score since 21 Jul 2026

Heat score

9,008°

This week

▲

26.3%

8,977° then, 9,008° now

This month

▲

222%

8,853° then, 9,008° now

Past year

n/a

Wasn't released/tracked

7,000°

Floor

The scale runs from 0° to 9,999°. Everything below 7,000° is kept for models no source reports on yet, which carry a stand-in number there so lists stay complete. 7,000° is where measured data begins: a model with real data but almost no downloads sits at the floor, and the measurements fill the degrees above it. The floor says nothing about the model; only the degrees above it do, and they are what separates one model from another.

+1,695°

OpenRouter tokens

4,469,209,626,464 tokens this model processed through OpenRouter in the last 30 days, prompts and answers together. Every 10,000,000 tokens count as one download in the download term, 446,920 in all; the last day's tokens join the adoption rate. Source: OpenRouter (openrouter.ai/rankings).

+313°

Adoption rate

About 14,717 downloads a day, measured between two readings of the sources, never guessed from a lifetime average. Speed weighs a quarter of the download term, so a fresh surge shows without letting a one-day spike outrank years of use.

Show detailed breakdown

Every number on this site can be checked. This model's heat score is 9,008°, and here it is built one ingredient at a time, with the running total after each: the floor, the degrees each source adds, the bonus for the kind of model and what the age of its weights takes away. The colors are the bands of the chart above. The glossary at the end defines every term.

1
Start at the floor.
Why 7,000° and not zero: the scale runs from 0° to 9,999°, and the part below 7,000° is reserved for models no source reports on yet, which carry a stand-in number there so the lists stay complete and never outrank a model with data. 7,000° is where measured data begins. A model with real data but almost no downloads sits here; everything that follows is measurement, and the room above the floor holds ten tenfold steps in downloads at 300° each. The floor is the same for every model, so it decides nothing; the degrees above it do.
7,000°
running total
2
Add the downloads.
446,920 download-equivalents in all, from OpenRouter tokens. Ten times the downloads adds the same 300°, so size matters but never runs away with the score.
+1,695°
8,695°
running total
3
Add the adoption rate.
About 14,717 downloads a day right now, measured between two readings, at a quarter of the weight.
+313°
9,008°
running total
=
The heat score.
Where this model stands on every list of this site. Nothing else adjusts it.
9,008°

Glossary: the terms used here

Heat score: One number for how much a model is used and wanted right now, from 0° to 9,999°. Every list on this site that says hottest is sorted by it and nothing else.
Floor: The 7,000° every model with real data starts from. The scale runs from 0° to 9,999°; the part below the floor is reserved for stand-ins (models without data), so that a model with data always ranks above one without. The floor is the same for everyone and decides nothing; the degrees above it are the measurement.
Download-equivalents: Everything the score treats as a download, added up: downloads themselves, each torrent seeder as 1,000, each AI Horde image and each run on a generation site as one.
Log scale: Counting by tens, not by ones: going from 1,000 to 10,000 downloads adds the same degrees as going from 10,000 to 100,000. It keeps giants from crowding out everything else.
Likes: Thumbs up and likes from every source, worth half a download each on the log scale.
Adoption rate: How many downloads a day a model gets right now, from the difference between two readings of a source. A quarter of the weight of the download term.
Measured and estimated: Measured means two readings of a source exist and the difference is real. Estimated means only today's total is known and the past is spread over the model's life; the site says which one it is showing.
Seeder: Someone who keeps a copy of the weights online for others to download over a torrent, or a hosted mirror doing the same. Each one counts as 1,000 downloads.
AI Horde: A volunteer network that generates images for free on donated computers. The number of images it has made with a model is public, and each counts as one download.
Generation sites: Sites that host their own copies of a model and let people generate with it, such as PixAI, SeaArt and Yodayo. Their downloads count like Civitai's and each generation run as one download.
OpenRouter tokens: A text model served through an API, such as Claude or GPT, has no weights to download, so its usage is measured in tokens: the pieces of text it read and wrote through OpenRouter, a gateway many apps use, over the last 30 days. Every 10,000,000 tokens count as one download. Source: OpenRouter (openrouter.ai/rankings), CC BY 4.0.
Full model (checkpoint): The weights themselves, the file that generates on its own. It gets a bonus because add-ons depend on it.
LoRA and embedding: Small add-on files that steer someone else's weights toward a style, a character or a concept. They cannot run alone.
Family and weights: The base a model is built on, such as SD 1.5, SDXL, Flux or Wan. Every model inherits the release date of its family's weights.
Age: Degrees taken off for how long ago the family's weights came out: 150° a year, up to 750°. It keeps old downloads that had years to pile up from freezing the top of the list.
Family boost: A small, bounded nudge for LoRAs of a family this site is pushing forward right now, always listed in the breakdown.
Stand-in score: A stable number below the floor given to a model no source reports on yet, so lists stay complete. It never ranks above a model with data.
New! (grace period): A model less than 7 days old shows New! instead of a score and holds no place in the rankings. Its score is computed from day one, but a model one day old grows faster than anything, so without the wait the week's #1 would always be whatever came out yesterday rather than what held up for a week.
Trend: How a model's growth over a period compares with the typical model's growth over the same period. Faster than typical reads as a rise, slower as a fall.
Typical model: The middle of the catalog: half the models with a figure grew faster over the period, half slower.

How this model's popularity has moved against the rest of the catalog: its growth in downloads, likes and usage over each period, measured against the typical model's growth over the same period, with its heat score at the time. Above the typical growth reads as a rise, below it as a fall. The past is reconstructed from today's totals, the model's first day and its measured download speed where two readings exist; a model that did not exist at the start of a period shows n/a.

Similar Models

Qwen3 Coder 30B A3B Instruct

Mistral Small 3.1 24B

TEXT / LLM

AI Models for Image, Video & Text Generation

Laguna S 2.1 is a text model for the Text / LLM family listed on ModelTrends.ai, a read-only catalog of open source AI image, video and text models. Compare it with other Text / LLM models and check its heat score to see how it is trending.

More Text / LLM models llm poolside reasoning coding agents long context local

Browse by Model Family