Poolside Laguna XS 2.1 — local AI model by Poolside

Written by Jakub Rusinowski · Last updated

Poolside's July 2026 open-weight coding model, and one of the few frontier-grade agentic coders small enough to run on a single consumer GPU. Laguna XS 2.1 is a 33B-total / 3B-active Mixture-of-Experts built for long-horizon software work — the 2.1 point release lifted SWE-Bench Verified from 69.9% to 70.9% and SWE-bench Multilingual from 57.7% to 63.1%. Architecturally it mixes sliding-window and global attention 3:1 across 40 layers, with sigmoid per-head gating and an FP8 KV cache, which is how it holds a 256K context without a datacenter behind it.

Poolside Hugging Face

Variants

The smallest Poolside Laguna XS 2.1 variant needs about 21 GB of VRAM at Q4_K_M — quantized weights plus framework overhead, before any KV cache.

ModelVRAM
Laguna XS 2.1 33B-A3B →
33B (3B active)
~20.7 GB

Memory is quantized weights plus overhead at Q4_K_M, from the same engine as the GPU & VRAM checker.

How to run Poolside Laguna XS 2.1 locally

Install Ollama, then pull the tag.

ollama run poolside-laguna

Pick a size above for its own VRAM figure, speed estimate and install command.

Licence

OpenMDW-1.1Commercial use permitted

Commercial use permitted. No usage restrictions beyond attribution.

Applies to: Laguna XS 2.1 33B-A3B

Recommended GPU

The cheapest catalogued GPU that runs Poolside Laguna XS 2.1 locally (min 21 GB VRAM) is the AMD Radeon RX 7900 XTX (24 GB).

Affiliate disclosure: Some links on this page are affiliate links — if you buy through them, LLM Configurator may earn a commission at no extra cost to you. As an Amazon Associate, LLM Configurator earns from qualifying purchases.
AMD Radeon RX 7900 XTX 24GB
24 GB VRAM · 355 W board power
2026 prices are volatile — check the current listing.

Can I run Poolside Laguna XS 2.1 on my GPU?

Poolside Laguna XS 2.1 — frequently asked questions

How much VRAM does Poolside Laguna XS 2.1 need?

Poolside Laguna XS 2.1 needs about 21 GB VRAM at Q4_K_M quantization for its smallest variant. Variants: Laguna XS 2.1 33B-A3B (21 GB, Q4_K_M). On Apple Silicon, unified memory counts toward this requirement.

Can I run Poolside Laguna XS 2.1 on an RTX 4090 (24 GB)?

Yes — Poolside Laguna XS 2.1 runs on an RTX 4090 (24 GB) and other 24 GB cards such as the RTX 3090. Smaller variants also fit comfortably on 8–16 GB GPUs at Q4_K_M.

What quantization should I use for Poolside Laguna XS 2.1?

Q4_K_M is the best balance of quality and VRAM for Poolside Laguna XS 2.1 in most cases. Choose Q8_0 for near-lossless quality if you have spare VRAM, or smaller quants (Q3/Q2) only when memory is tight.

How do I run Poolside Laguna XS 2.1 with Ollama?

Poolside Laguna XS 2.1 has no local Ollama tag — the published tag is cloud-hosted, so running it sends your prompts to a hosted GPU rather than your own machine.