The Open Weights
LatestModelsLeaderboardsCompanies
Subscribe
The Open Weights

The daily record of open-source AI. New model releases, leaderboards, and what's coming next — written for people who ship.

Refreshed every 12 hours

Discover

  • Latest releases
  • New today
  • Trending models

Browse

  • All models
  • Companies
  • Categories
  • Leaderboards

About

  • About
  • Editorial policy
  • Hardware estimates
  • RSS feed
  • llms.txt
  • Newsletter

© 2026 The Open Weights. An independent publication.

PrivacyTermsSMSAggregated by Claude · curated by humans.
LatestPoolsideS-2.1
PoolsideCode

Poolside releases Laguna-S-2.1 coding model

The AI coding startup puts a version of its Laguna family on Hugging Face under the permissive OpenMDW license.

Jul 13, 2026
NotableOther
Laguna-S-2.1

Poolside, a startup building AI systems for software development, has published Laguna-S-2.1 on Hugging Face. It is a code-oriented language model, part of the company's Laguna line, released under the OpenMDW license.

The listing keeps details lean. Poolside has not attached a parameter count, context length, or benchmark figures to the release, so the model's exact scale and capabilities remain unspecified on the public repository. What is clear is the intended focus: code generation and text tasks that support software work.

Why it matters

Poolside has largely built its reputation as a well-funded, relatively private player in the AI coding space. Putting a Laguna model on Hugging Face — rather than gating it behind an API alone — signals a willingness to let developers inspect and experiment with its work directly.

The choice of license is notable too:

  • OpenMDW is a permissive, model-oriented license designed for openly distributed weights.
  • It lowers the friction for developers who want to evaluate the model without restrictive commercial terms.

For teams weighing open coding models, Laguna-S-2.1 is worth a look, though the sparse documentation means real judgment will come from hands-on testing. Interested users can find the weights and any accompanying notes on the model's Hugging Face page.

Sources

  • poolside/Laguna-S-2.1

    Hugging Face

    Visit
OlderAlibaba's OvisOCR2 turns page images into MarkdownATH MaaS · Vision-Language · 4 months agoNewerBoogu-Image-0.1 Brings Unified Multimodal to Open SourceUnknown · Any-to-Any · 4 months ago

Get the model

Hugging Face

Specs

Context window1.0M tokens
Size235.1 GB
PrecisionBF16
ArchitectureLagunaForCausalLM
LicenseOTHER
Downloads654.4K
Likes1.1K

Can you run it?

Needs a workstation GPU (96 GB) at 4-bit.

  • BF16 (as published)

    4×H100 80 GB · 512 GB Mac Studio

    237.7 GB
  • 8-bit

    H200 141 GB or 2×80 GB · 192 GB Mac Studio

    127.7 GB
  • 4-bit

    80 GB GPU (A100 / H100) · 128 GB Mac Studio

    73.4 GB
Your machine
GGUF builds
  • Mixture-of-experts: every expert must be loaded, so memory follows total parameters, not the active slice.
  • KV cache sized for 8,192 tokens of context; longer prompts need proportionally more.

Based on Hugging Face weights metadata. Assumes an 8K context and ~1 GB runtime overhead; actual needs vary. How we estimate


Modalities

CodeText / LLM

The Weekly Weights

Every open release that mattered, one email a week.

0 comments

No comments yet. Be the first to weigh in.

More from Poolside

All Poolside releases →
Laguna-XS-2.1
Poolside/CodeConsumer GPU

Poolside releases Laguna XS 2.1 code model

The compact, code-focused language model arrives on Hugging Face under an open model license.

Jun 20, 2026
Laguna-M.1
Poolside/Text / LLMMulti-GPU server

Poolside Releases Laguna-M.1, an Open MoE Model

The AI coding startup steps into open weights with an Apache-2.0 mixture-of-experts model built for text and code.

Jun 15, 2026

More in Code

All Code →
MiniMax-M3.1-Flash
MiniMax/Vision-LanguageMulti-GPU server

MiniMax Debuts M3.1 Flash, a Multimodal MoE Model

The new release pairs a mixture-of-experts design with agentic, coding, and video-understanding abilities in a single open model.

Oct 17, 2026
Meta AI/Code

Meta's Muse Spark Open Targets Agentic Coding

The open-weight model pairs a million-token context window with a focus on long-horizon code tasks.

Oct 15, 2026
Meta AI/Any-to-Any

Meta's Muse Spark Open Targets Agentic Coding

The new open-weight model pairs a million-token context window with Meta's bet on long-horizon coding agents.

Oct 15, 2026