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.
LatestPoolsideXS-2.1
PoolsideCode

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
NotableOther
Laguna-XS-2.1

Poolside has published Laguna XS 2.1, a compact language model tuned for code, on Hugging Face. The "XS" designation points to a smaller-footprint model in the Laguna line, positioned for developers who want a code assistant that can run without heavyweight infrastructure.

The model handles both code and general text generation, with code as its primary focus. Poolside is releasing it under a custom model license rather than a standard permissive one, so teams evaluating it for production should read the terms closely before building on top of it.

Why it matters

The market for code-generation models has become crowded, but smaller specialized models remain attractive for practical reasons:

  • Lower serving costs and easier self-hosting
  • Faster inference for interactive coding workflows
  • More control over data and deployment than closed APIs

Poolside, which has built its reputation around AI for software development, is signaling continued investment in open-weight releases with this launch. Detailed specifications such as parameter count and context length were not spelled out in the release record, so developers will want to consult the model card directly for benchmarks and hardware requirements before committing.

Sources

  • poolside/Laguna-XS-2.1

    Hugging Face

    Visit
OlderLIFT: A Qwen3.5-Based VLM for PDF-to-JSON ExtractionDatalab To · Vision-Language · 4 months agoNewerOrnith-1.0-35B brings a mid-size MoE to agentic codingDeepreinforce Ai · Text / LLM · 4 months ago

Get the model

Hugging Face

Specs

Context window262K tokens
Size66.9 GB
PrecisionBF16
ArchitectureLagunaForCausalLM
LicenseOTHER
Downloads802.8K
Likes263

Can you run it?

Runs on a 24 GB GPU at 4-bit.

  • BF16 (as published)

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

    69.2 GB
  • 8-bit

    48 GB GPU (RTX 6000) or 2×24 GB · 64 GB Mac

    37.9 GB
  • 4-bit

    24 GB GPU (RTX 3090 / 4090) · 32 GB Mac

    22.4 GB
Your machine
  • 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-S-2.1
Poolside/CodeWorkstation GPU

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
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