Laguna M.1

+ contribute

Laguna M.1 is an open-weights language model from Poolside, released April 2026. Its published size is 225B parameters (23B active per token) and a 262k-token context window. Licence: apache-2.0.

Catalogue identity notes

Official Poolside API documented in model card. Model card (poolside/Laguna-M.1 @2bf8a4a): '225B total with 23B activated per token', Apache 2.0. Epoch model_metadata.csv date 2026-04-28 (accessibility blank). Arena entry 'laguna-m.1' (poolside, Apache 2.0), first listed 2026-06-15.

67.0±1.8#113 of 719 LLMsfrom 4 benchmark results across 2 sources

$ how it compares

The LLMs ranked either side of Laguna M.1, out of 828 with a score, then more from Poolside.

#	model	score	where	RAM	released
128	Claude Opus 4.1 Anthropic	67±1	comparison only		2025-08
129	Kimi K2 Thinking Moonshot AI	67±1	api $1.07/M +local	~160GB	2025-11
130	Laguna M.1 Poolside	67±2	api price unknown +local	~135GB	2026-04
131	Qwen3.7 Flash Alibaba	67±1	api $0.055/M		2026-07
132	Step 3.7 Flash (198B-A11B) StepFun	67±1	api $0.44/M +local	~104GB	2026-05
	more from Poolside
156	Laguna XS 2.1 (33B-A3B) Poolside	66±2	local	~21GB	2026-06
172	Laguna XS.2 Poolside	65±2	local	~21GB	2026-04

see all LLMs · find the ones that fit your machine

$ what it's good at

agent tasks█···█······█ #1 of 3 · 46% of its score · 4 tests

test	result	vs the others in its run	difficulty	counts	why
SWE-bench Verified lab	74.6% ✎	▁▁▁▁▁▁▂▄█▆▁▁ beats 97/131	hard · avg 27%	▇▇▇▇▇▇▇ 18%	sharp · at its level · small run
Terminal-Bench 2.0 lab	45.8% ✎	▂▂▅▅████▆▂▃▃ beats 16/36	very hard · avg 11%	▇▇▇▇▇▇ 16%	at its level · small run
SWE-bench Multilingual lab	63.1% ✎	▁··▁▃▂▅▇█▃▃▁ beats 25/60	hard · avg 27%	▇▇▇▇▇ 12%	at its level · small run
SWE-bench Pro lab	49.2% ✎	▅▃▃·▃·▅▅▅█▃▃ beats 3/15		—	not counted yet: no other model in the same run to compare it with

coding▁▁▁▃▆██▇▆▄▃▁ #113 of 458 · 83% of its score · 4 tests

Beats Qwen3.5 Plus, Gemini 2.5 Pro, Kimi K2 Thinking here, though they rank higher overall. Trails Llama 3.1 Nemotron Ultra 253B v1, Solar Pro 4, Laguna XS 2.1 (33B-A3B) here, though they rank lower overall.

test	result	vs the others in its run	difficulty	counts	why
Arena WebDev (Code Arena)	1348.1 ✎	▁▂▄▃▅█▄▇▆▄▁▁ beats 27/119	avg 981	▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 53%	sharp
SWE-bench Verified lab	74.6% ✎	▁▁▁▁▁▁▂▄█▆▁▁ beats 97/131	hard · avg 27%	▇▇▇▇▇▇▇ 18%	sharp · at its level · small run
SWE-bench Multilingual lab	63.1% ✎	▁··▁▃▂▅▇█▃▃▁ beats 25/60	hard · avg 27%	▇▇▇▇▇ 12%	at its level · small run
SWE-bench Pro lab	49.2% ✎	▅▃▃·▃·▅▅▅█▃▃ beats 3/15		—	not counted yet: no other model in the same run to compare it with

$ where to run it

Through an API

api · price unknown · 262k context · huggingface.co ↗

llama.cpp · recommended

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 ↗
Run Laguna M.1 · needs ~136.1 GB · from huggingface.co/linuxid10t
chat in the terminal
llama cli -hf linuxid10t/Laguna-M.1-GGUF:Q4_K_M
Or start a local server and open the address it prints (http://localhost:9931)
llama serve -hf linuxid10t/Laguna-M.1-GGUF:Q4_K_M

LM Studio

version

Install LM Studio · Open the app once before using the lms command.
download it (macOS / Windows / Linux) ↗
Run Laguna M.1 · needs ~136.1 GB · from huggingface.co/linuxid10t
open in LM Studio ↗
Or download it in the terminal
lms get https://huggingface.co/linuxid10t/Laguna-M.1-GGUF@Q4_K_M -y
Then run lms ls to see its name, and lms chat followed by that name

MLX (Mac)

version

Install MLX (Mac) · Apple silicon Macs only, text only.
with uv
uv tool install mlx-lm
or
pip install mlx-lm
Run Laguna M.1 · needs ~127 GB, Mac only · from huggingface.co/mlx-community
chat in the terminal
mlx_lm.chat --model mlx-community/Laguna-M.1-4bit
Or start an OpenAI-compatible server at http://localhost:8080/v1
mlx_lm.server --model mlx-community/Laguna-M.1-4bit

Other ways to run it

version

Run it as published · needs ~451.6 GB, NVIDIA only · from huggingface.co/poolside (official)
pip install 'vllm>=0.21.0' && vllm serve --model poolside/Laguna-M.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 · LMArena leaderboard dataset 53%, Poolside — Laguna M.1/XS.2 Te… 46%

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

source	results	share of the score	licence
LMArena leaderboard dataset	1	▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 53%	CC BY 4.0
Poolside — Laguna M.1/XS.2 Technical Report · lab-reported	3	▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 46%	CC BY-SA 4.0
prior · pull toward the middle		▇ 1%
weighted average		= 67.0

not counted (1)

poolside/Laguna-M.1 model card

SWE-bench Pro [correct]

49.2%

fewer than three models have this test yet, or this source ran it for this model alone

$ improve this page

Update model information Add a place to run it Add a test result Propose a benchmark Correct a benchmark score Edit 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 2026-10-11 02:20 UTC · sources and licences · json