Models / poolside/ Laguna XS 2.1

Laguna XS 2.1

poolside · released Jun 20, 2026 · poolside/Laguna-XS-2.1

Input: text. Output: text.InputOutput
Type
Open weightsopenmdw-1.1
Params
33.4B
Context
262K

about 197K words of context · download allowed, licence restricts use

Our take

Written Aug 2, 2026

Laguna XS 2.1 is a 33.4-billion-parameter text model from poolside with a 262,144-token request limit and a restricted open licence. It is aimed at code and reasoning tasks, though no benchmark scores have been measured to back that positioning.

Who should pick it

Pick this for long-document work where you need open weights and a quarter-million-token request limit, or when you want vendor-native hosting at a known throughput. Skip it if you need measured quality data, a permissive licence, or multimodal input.

The case for it

  • Identical pricing across both tracked hosts removes provider-arbitrage complexity.
  • 262,144-token request limit is unusually long for a 33-billion-parameter open model.

The case against it

  • No benchmark scores in our data — chat, coding, reasoning and math quality are all unverified.
  • Throughput is thin: only one host discloses speed, the other is unverified in our data.
  • OpenMDW 1.1 licence is open-restricted, less permissive than Apache 2.0.
00

How good is it?

We hold no score for this model.

We look for every model we track on every board we watch, and none of them has turned up Laguna XS 2.1 — so there is no intelligence, coding, agentic or writing score to show you, not a low one, none.

The boards we watch →

01

Can you run it yourself?

Fits in memory
weights load entirely on the card
Spills to system RAM
some weights offload; much slower
Too large
will not load even with offload
est
size is calculated; the verdict could change by 10%

Comfortable fit

A card many people ownFits in memory

GeForce RTX 4090 · 24 GB

Weights at Q4_K_M20.3 / 24 GBmeasured
Spare memory0.4 GB spare
Usable context4K of 262K
Decode speed34 tok/sest

Room to spare. 0.4 GB spare means a 10% error in the size would not change the answer.

One step upFits in memory

GeForce RTX 5090 · 32 GB

Weights at Q4_K_M20.3 / 32 GBmeasured
Spare memory8.4 GB spare
Usable context33K of 262K
Decode speed60 tok/sest

Room to spare. 8.4 GB spare means a 10% error in the size would not change the answer.

On a MacFits in memory

Apple M1 Pro (16-core GPU) · 32 GB

Weights at Q4_K_M20.3 / 32 GBmeasured
Spare memory1.6 GB spare
Usable context8K of 262K
Decode speed6 tok/sest

Room to spare. 1.6 GB spare means a 10% error in the size would not change the answer.

Your hardware
Checking your profile…

Memory use by level

Against a 24 GB card.

BF16
66.9 GBmeasured
Too large
Q4_K_M
recommended
20.3 GBmeasured
Fits in memory
Q5_K_M
24.7 GBest
Spills to system RAM
Q8_0
35.6 GBmeasured
Too large

Check against your own machine → · All 71 devices, with every size →

02

Or rent it from someone else

Cheapest published offer

Cheapest of 2 live listings. Picked at the widest standard context we hold, within one quantisation slice, so the numbers beside it are a price one host actually charges.

per 1M tokens
$0.060 in / $0.12 out
Context served
262K
Throughput
Not measured
Current provider offers with price, context and prompt-privacy answers
ProviderIn / out per 1M tokensContextThroughputTrains on promptsLogs promptsZero retention
OpenRouter$0.060 / $0.12262Knot measuredUnknownUnknownUnknown
Poolsidefp8$0.060 / $0.12262K196 tok/sNoYesunknown periodUnknown

Across the 2 listings we hold: 1 say they do not train on prompts, 0 say they do and 1 do not say. 0 appear in the zero-retention registry we check; the rest are unknown to us rather than confirmed either way.

What each host's API supports

From the parameter list each endpoint publishes. Streaming is omitted: nothing we hold reports it, for any model.

Supported
Not supported
Not published
host gave no parameter list
API features per host
ProviderTool callingJSON outputStrict schema
OpenRouter
Poolsidefp8

Tool calling: 2 of 2 listings say yes. JSON output: 0 of 2 listings say yes, 2 say no. Strict schema: 0 of 2 listings say yes, 2 say no.

03

When we formed this view

Dates behind this page

Jul 26, 2026ListedListed on LLMapfirst indexed by our pipeline
Jun 20, 2026AnnouncedLaguna XS 2.1 announced by poolside

Prices last checked 3d ago

What we do not know about this model yet

  • No board we watch has turned up a score, so we hold no quality figures at all.
  • Nothing we hold says whether an endpoint streams, so we do not show it either way.
  • 1 of 2 listings do not say whether they train on prompts.
04

Licence and identifiers

What the licence allowsopenmdw-1.1, what it allows commercially, and the identifiers you need to pull this model — its Hugging Face repo, our slug and a machine-readable card.

Licence

openmdw-1.1

restricted_openCustom licence — review the terms

License tag "openmdw-1.1" imported from Hugging Face; terms pending curation.

Identifiers

Architecture
Mixture of experts
Modality record
text->text
Catalogue slug
poolside-laguna-xs-2-1

Machine-readable model card (omc.json) →

Something wrong on this page? Tell us