whatmodel.sh / Laguna XS 2.1 (33B-A3B)

Laguna XS 2.1 (33B-A3B)

+ contribute
Update model informationAdd a place to run itAdd a test resultPropose a benchmarkCorrect a benchmark scoreEdit data on GitHub

Laguna XS 2.1 (33B-A3B) is an open-weights language model from Poolside, released June 2026. Its published size is 33B parameters (3B active per token) and a 262k-token context window. Licence: openmdw-1.1.

Catalogue identity notes

Poolside's Laguna XS 2.1 (poolside/Laguna-XS-2.1 @c5f3626, created 2026-06-20, licence openmdw-1.1); successor of the catalogued Laguna XS.2 (apache-2.0), which its card prints as a bold same-lab row.

Model information sources

Release date ↗ · Weights licence ↗

Card: '33B total parameters and 3B activated' (safetensors metadata 33,442,617,088).

65.6±2.4#137 of 719 LLMsfrom 4 benchmark results across 1 source

$ how it compares

The LLMs ranked either side of Laguna XS 2.1 (33B-A3B), out of 828 with a score, then more from Poolside.

#modelscorewhereRAMreleased
154MiniMax-M2.1 MiniMax66±1local~79GB2025-12
155Nemotron Cascade 2 30B-A3B NVIDIA66±1local~20GB2026-03
156Laguna XS 2.1 (33B-A3B) Poolside66±2local~21GB2026-06
157LongCat-Flash-Chat (560B-A27B) Meituan66±1local~333GB2025-08
158o3-mini OpenAI65±1api $1.93/M2025-01
more from Poolside
130Laguna M.1 Poolside67±2api price unknown +local~135GB2026-04
172Laguna XS.2 Poolside65±2local~21GB2026-04

see all LLMs · find the ones that fit your machine

$ what it's good at

agent tasks█···█······█ #2 of 3 · 97% of its score · 4 tests
testresultvs the others in its rundifficultycountswhy
SWE-bench Verified lab70.9% ✎▁▁▁▁▁▁▂▄█▆▁▁ beats 82/131hard · avg 27%▇▇▇▇▇▇▇▇▇▇▇▇▇ 32%sharp · at its level · small run
Terminal-Bench 2.0 lab37.5% ✎▂▂▅▅████▆▂▃▃ beats 11/36very hard · avg 11%▇▇▇▇▇▇▇▇▇▇▇ 28%at its level · small run
SWE-bench Multilingual lab63.1% ✎▁··▁▃▂▅▇█▃▃▁ beats 24/60hard · avg 28%▇▇▇▇▇▇▇▇▇▇▇ 28%at its level · small run
SWE-bench Pro lab47.6% ✎▅▃▃·▃·▅▅▅█▃▃ beats 2/15hard · avg 30%▇▇▇▇ 10%blunt · at its level · small run
coding▁▁▁▃▆██▇▆▄▃▁ #107 of 458 · 69% of its score · 3 tests

Beats Grok 4.3, Qwen3.5 Plus, DeepSeek V3.2 here, though they rank higher overall. Trails Llama 3.1 Nemotron Ultra 253B v1, Solar Pro 4 here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
SWE-bench Verified lab70.9% ✎▁▁▁▁▁▁▂▄█▆▁▁ beats 82/131hard · avg 27%▇▇▇▇▇▇▇▇▇▇▇▇▇ 32%sharp · at its level · small run
SWE-bench Multilingual lab63.1% ✎▁··▁▃▂▅▇█▃▃▁ beats 24/60hard · avg 28%▇▇▇▇▇▇▇▇▇▇▇ 28%at its level · small run
SWE-bench Pro lab47.6% ✎▅▃▃·▃·▅▅▅█▃▃ beats 2/15hard · avg 30%▇▇▇▇ 10%blunt · at its level · small run

$ where to run it

llama.cpp · recommended

  1. Install llama.cpp · Homebrew and winget installs name the commands llama-cli and llama-server instead.
    macOS / Linux
    curl -LsSf https://llama.app/install.sh | sh
    Windows
    irm https://llama.app/install.ps1 | iex

    other ways to install ↗

  2. Run Laguna XS 2.1 (33B-A3B) · needs ~20.3 GB · from huggingface.co/poolside (official)
    chat in the terminal
    llama cli -hf poolside/Laguna-XS-2.1-GGUF:Q4_K_M
  3. Or start a local server and open the address it prints (http://localhost:9931)
    llama serve -hf poolside/Laguna-XS-2.1-GGUF:Q4_K_M

LM Studio

version

  1. Install LM Studio · Open the app once before using the lms command.

    download it (macOS / Windows / Linux) ↗

  2. Run Laguna XS 2.1 (33B-A3B) · needs ~20.3 GB · from huggingface.co/poolside (official)

    open in LM Studio ↗

  3. Or download it in the terminal
    lms get https://huggingface.co/poolside/Laguna-XS-2.1-GGUF@Q4_K_M -y
  4. Then run lms ls to see its name, and lms chat followed by that name

Ollama

version

  1. Install Ollama

    download it (macOS / Windows) ↗

    Linux
    curl -fsSL https://ollama.com/install.sh | sh
  2. Run Laguna XS 2.1 (33B-A3B) · needs ~20 GB · from ollama.com
    chat in the terminal
    ollama run laguna-xs-2.1:q4_K_M

MLX (Mac)

version

  1. Install MLX (Mac) · Apple silicon Macs only, text only.
    with uv
    uv tool install mlx-lm
    or
    pip install mlx-lm
  2. Run Laguna XS 2.1 (33B-A3B) · needs ~18.8 GB, Mac only · from huggingface.co/mlx-community
    chat in the terminal
    mlx_lm.chat --model mlx-community/Laguna-XS-2.1-4bit
  3. Or start an OpenAI-compatible server at http://localhost:8080/v1
    mlx_lm.server --model mlx-community/Laguna-XS-2.1-4bit

Other ways to run it

  1. Run it as published · needs ~66.89 GB, NVIDIA only · from huggingface.co/poolside (official)
    pip install 'vllm>=0.21.0' && vllm serve --model poolside/Laguna-XS-2.1 --tool-call-parser poolside_v1 --reasoning-parser poolside_v1 --enable-auto-tool-choice --served-model-name laguna --default-chat-template-kwargs '{"enable_thinking": true}'

Official weights and documentation: huggingface.co/poolside ↗

$ how the score was worked out · Poolside vendor-reported benc… 97%

Each result implies a score on its own, after adjusting for how hard its test is and who ran it. The score is their weighted average, with a small pull toward the middle for thinly tested models. Each test's weight is its counts column above; here it's added up by who ran the tests. How it works

sourceresultsshare of the scorelicence
Poolside vendor-reported benchmark scores for its own Laguna models (Hugging Face model cards) · lab-reported4▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 97%Factual vendor-reported score (not licensed content)
prior · pull toward the middle▇ 3%
weighted average= 65.6

$ improve this page

Update model informationAdd a place to run itAdd a test resultPropose a benchmarkCorrect a benchmark scoreEdit data on GitHub

Use a short GitHub form or edit the data through a pull request. Every number needs a source; here's which ones we can use.

data updated · sources and licences · json