Laguna XS 2.1
poolside · released Jun 20, 2026 · poolside/Laguna-XS-2.1
- Type
- Open weightsopenmdw-1.1
- Params
- 33.4B
- Context
- 262K
active per word not recorded by us · about 197K words of context · download allowed, licence restricts use
Our take
Written Sep 17, 2026Laguna XS 2.1 is a text model you can download and run yourself, or reach through one of two hosts. Nothing in our data measures how well it writes, reasons or codes, so treat it as a candidate to trial on work you can check.
Use it for text-only work where you can judge the output yourself, or when a long report or a stack of documents needs to go into one request without being split up first. The licence puts conditions on commercial use and redistribution, so read it before you build on it. Skip it if you need measured coding, reasoning or chat quality before committing, or if you need a host with a measured serving speed.
The case for it
- A long report or a stack of documents fits beside the question in one request, though reliable recall across all of it is unverified in our data.
- Both hosts list the same rate, so the host you pick does not change the bill.
The case against it
- No benchmark scores are supplied, so nothing here says how well it writes, reasons or codes; a trial on your own work is the only way to judge it.
- The licence puts conditions on commercial use and redistribution (OpenMDW 1.1), so it needs reading before you build on it.
- Neither offer carries a measured speed, so price alone cannot tell you which host responds faster.
How good is it?
We hold no score for this model.
So there is no figure here for everyday use, coding, agent work or writing. That is a gap in our data, not a low score.
Can you run it yourself?
Comfortable fit
GeForce RTX 4090 · 24 GB
Room to spare. 0.4 GB spare means a 10% error in the size would not change the answer.
GeForce RTX 5090 · 32 GB
Room to spare. 8.4 GB spare means a 10% error in the size would not change the answer.
Apple M1 Pro (16-core GPU) · 32 GB
Room to spare. 1.6 GB spare means a 10% error in the size would not change the answer.
Memory use by level
Against a 24 GB card.
What is quantisation? →This model on every device we track71 devicesThe Q4 build most people download, on each device: what the weights come to, how much context the memory leaves, and whether it runs. Smallest device that runs it first.
Check against your own machine → · Where to rent it hosted →
Or rent it from someone else
Prices checked 2 hours ago — each listing carries its own date.
- per 1M tokens
- $0.060 in / $0.12 out
- Context served
- 262K
- Throughput
- Not measured
| Provider | In / out per 1M tokens | Context | Throughput | Trains on prompts | Logs prompts | Zero retention |
|---|---|---|---|---|---|---|
| OpenRouterOpenRouter's own listing | $0.060 / $0.12checked 2 hours ago | 262K | not measured | Unknown | Unknown | Unknown |
| Poolsidefp8Through OpenRouter | $0.060 / $0.12checked 2 hours ago | 262K33K max reply | 118 tok/s | No | Yesunknown period | Unknown |
Across the 2 listings we hold: 1 says it does not train on prompts, 0 say they do and 1 does not say. 0 appear in the zero-retention registry we check; the rest are unknown to us.
What each host's API supports
From the parameter list each endpoint publishes. Streaming is omitted: nothing we hold reports it, for any model.
| Provider | Tool calling | JSON output | Strict schema |
|---|---|---|---|
| OpenRouterOpenRouter's own listing | ✓ | ✗ | ✗ |
| Poolsidefp8Through OpenRouter | ✓ | ✗ | ✗ |
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.
When we formed this view
Recent changes
What moved
first indexed by our pipelineEach date is the day we first saw the change, or the day the maker announced it.
What we do not know about this model yet
- No independent board has scored it, so we hold no quality figures at all.
- We do not hold the active parameter count for it, so how much of it runs on any one token is unknown to us.
- Nothing we hold says whether an endpoint streams, so we do not show it either way.
- 1 of 2 listings does not say whether it trains on prompts.
- We hold no batch or off-peak rate for any of its listings.
- We hold a decode speed for it, but no prompt-processing (prefill) figure, so how long the input side of a job takes is unknown to us.
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
License tag "openmdw-1.1" imported from Hugging Face; terms pending curation.
Identifiers
- Hugging Face
- poolside/Laguna-XS-2.1
- Architecture
- Mixture of experts
- Takes in, gives back
- Text in, text out
- Catalogue slug
- poolside-laguna-xs-2-1