Laguna S 2.1
poolside · released Jul 13, 2026 · poolside/Laguna-S-2.1
- Type
- Open weightsopenmdw-1.1
- Params
- 118B
- Context
- 1M
about 786K words of context · download allowed, licence restricts use
Our take
Written Aug 2, 2026Laguna S 2.1 is a 118-billion-parameter text model from poolside with a one-million-token request limit and a restricted open licence. It is built for very long documents, though no quality scores have been published yet.
Choose this when you need to process text documents of one million tokens or more, and when the OpenMDW 1.1 licence terms fit your use case. Pick the faster poolside tier if latency matters more than a modest output premium. Skip it if you need measured quality data, multimodal input, or a permissive licence like Apache or MIT.
The case for it
- One-million-token request limit — the only figure we hold for this model, and extremely long among models with disclosed length.
- Three hosted offers with competitive relative pricing in its class, including a faster tier at 15 tokens per second.
The case against it
- No benchmark scores in our data, so there is no measured quality or speed data to validate performance claims.
- The slower tier at 6 tokens per second costs nearly as much as the 15 tokens per second tier, making it poor value.
- Only three tracked offers, with throughput unverified on one of them.
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 S 2.1 — so there is no intelligence, coding, agentic or writing score to show you, not a low one, none.
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%
GeForce RTX 4090 · 24 GB
Too large for this card. The weights do not fit even with part of them offloaded to system memory.
Apple M1 Pro (16-core GPU) · 32 GB
Too large for this card. The weights do not fit even with part of them offloaded to system memory.
Comfortable fit
Apple M2 Ultra (76-core GPU) · 192 GB
Room to spare. 43.5 GB spare means a 10% error in the size would not change the answer.
Memory use by level
Against a 24 GB card.
Check against your own machine → · All 71 devices, with every size →
Or rent it from someone else
Cheapest of 3 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
- $0.090 in / $0.18 out
- Context served
- 1M
- Throughput
- Not measured
| Provider | In / out per 1M tokens | Context | Throughput | Trains on prompts | Logs prompts | Zero retention |
|---|---|---|---|---|---|---|
| OpenRouter | $0.090 / $0.18 | 1M | not measured | Unknown | Unknown | Unknown |
| Poolsidefp4 | $0.090 / $0.18 | 1M | 14 tok/s | No | Yesunknown period | Unknown |
| Poolsidebf16 | $0.10 / $0.20 | 1M | 15 tok/s | No | Yesunknown period | Unknown |
Across the 3 listings we hold: 2 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
| Provider | Tool calling | JSON output | Strict schema |
|---|---|---|---|
| OpenRouter | ✓ | ✗ | ✗ |
| Poolsidefp4 | ✓ | ✗ | ✗ |
| Poolsidebf16 | ✓ | ✗ | ✗ |
Tool calling: 3 of 3 listings say yes. JSON output: 0 of 3 listings say yes, 3 say no. Strict schema: 0 of 3 listings say yes, 3 say no.
When we formed this view
Dates behind this page
Prices last checked 35h 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 3 listings do not say whether they train on prompts.
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-S-2.1
- Architecture
- Mixture of experts
- Modality record
- text->text
- Catalogue slug
- poolside-laguna-s-2-1