TAAFT
Free mode
100% free
Freemium
Free Trial
Deals
Companies
poolside
Models
Laguna XS 2

Laguna XS 2

By poolside
Laguna XS.2 is an Apache 2.0 agentic coding model built for local long-horizon software tasks rather than general chat. The model card says it has 33B total parameters with 3B activated per token, 40 layers, 256 experts plus 1 shared expert, and a mixed attention layout with 30 sliding-window-attention layers and 10 global-attention layers, using a 512-token sliding window and a 131,072-token context window. It is designed for preserved interleaved reasoning between tool calls, uses FP8 KV cache for lower memory per token, and is positioned as compact enough to run on a Mac with 36 GB RAM.
New Multimodal Gen 3
Released: April 28, 2026

Overview

Laguna XS.2 is poolside’s open 33B MoE coding model for agentic software work on local machines. It uses 3B activated parameters per token, supports native reasoning with interleaved thinking around tool calls, and is designed for long-horizon coding with low KV-cache requirements and Mac-friendly deployment.

💻Coding🐞Debugging🤖Agents🤔Logical reasoning💻Software engineer assistance

About poolside

poolside is a foundation-model company building AI for software engineering. It develops proprietary frontier models (Malibu, Point, and the open-weight Laguna XS.2) plus a full agentic platform — IDE/TUI integrations, multi-agent systems, and connectors — deployed on-prem, in customer VPCs, or in air-gapped environments. Targets large enterprises and the U.S. defense industrial base. Mission stated as building AGI via software engineering as the strategic beachhead.

Industry: Artificial Intelligence
Company Size: 322
Location: San Francisco, California, US
Website: poolside.ai
View Company Profile

Tools using Laguna XS 2

No tools found for this model yet.

Related Models

Last updated: May 3, 2026
0 AIs selected
Clear selection
#
Name
Task