Laguna M.1
poolside · released Jun 15, 2026 · poolside/Laguna-M.1
- Type
- Open weightsApache License 2.0
- Params
- 226B
- Context
- 262K
about 197K words of context
Our take
Written Aug 2, 2026Laguna M.1 is a 225.8-billion-parameter code-specialist model from poolside, released in 2026 with a permissive Apache licence and a 262,144-token request limit. It is built for web development tasks and carries identical pricing across its two tracked hosts.
Pick this for open-weights code generation where a permissive licence matters, or for web development with large repository context needs. Use it when you want vendor-agnostic hosting without price hunting. Skip it if you need image or video input, if latency-sensitive work requires measured throughput data, or if you want broader coding benchmarks beyond web development.
The case for it
- Apache 2.0 licence with 225.8 billion parameters — commercial use, fine-tuning and redistribution allowed.
- 262,144-token request limit for large code repositories.
- Identical pricing across both OpenRouter and poolside, so provider choice does not cost extra.
The case against it
- No measured throughput on either offer, leaving latency unverified.
- Text-to-text only; no image or video input, unlike multimodal code assistants.
- WebDev Elo scores vary by only 0.1289 across four evaluations, suggesting limited independent validation or a stalled leaderboard position.
How good is it?
IntelligencePuzzles, maths, exam questions
Nobody we watch has scored Laguna M.1 for this. We would take the rating from Arena Text (overall).
CodingWriting and fixing code on its own
Laguna M.1 is not on Arena Coding, which is where the rating would come from, so there is no rating here. It is on Arena Code (WebDev), in 54th of 74 with 1348.8.
AgenticPlanning, calling tools, staying on task
Nobody we watch has scored Laguna M.1 for this. We would take the rating from Arena Agent (IPS).
WritingWe do not rate this
Nobody we watch has scored this model for writing. Two boards come close and neither tests writing: Arena Creative Writing asks people which of two replies they prefer, and LiveBench Language tests whether a model understood a passage.
Every published score for this model1 scoreEvery figure we hold, from 1 board, with who ran it and a link to the source — including the boards no rating above is built on.
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 M3 Ultra (80-core GPU) · 512 GB
Room to spare. 235.6 GB spare means a 10% error in the size would not change the answer.
Memory use by level
Against a 24 GB card.
All 3 sizes here are calculated, not measured. We hold no measured file for this model, so each size comes from the parameter count and every verdict above inherits that uncertainty.
Check against your own machine → · All 71 devices, with every size →
Or rent it from someone else
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
- $0.20 in / $0.40 out
- Context served
- 262K
- Throughput
- Not measured
| Provider | In / out per 1M tokens | Context | Throughput | Trains on prompts | Logs prompts | Zero retention |
|---|---|---|---|---|---|---|
| OpenRouter | $0.20 / $0.40 | 262K | not measured | Unknown | Unknown | Unknown |
| Poolsidefp4 | $0.20 / $0.40 | 262K | not measured | No | Yesunknown period | Unknown |
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
| Provider | Tool calling | JSON output | Strict schema |
|---|---|---|---|
| OpenRouter | ✓ | ✗ | ✗ |
| Poolsidefp4 |
Tool calling: 1 of 2 listings says yes, 1 publishes no parameter list. JSON output: 0 of 2 listings say yes, 1 says no, 1 publishes no parameter list. Strict schema: 0 of 2 listings say yes, 1 says no, 1 publishes no parameter list.
When we formed this view
Dates behind this page
Prices last checked 4d ago
What we do not know about this model yet
- We hold no measured file for it, so all 3 sizes on this page are calculated from the parameter count.
- 1 of 2 listings publish no parameter list, so what their API accepts is unknown to us.
- 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.
- We hold no cached-input rate for any of its listings.
Licence and identifiers
What the licence allowsApache License 2.0, 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
Apache License 2.0
Fully permissive: commercial use, redistribution, and derivatives allowed. Requires attribution and a copy of the license. Includes an express patent grant.
Identifiers
- Hugging Face
- poolside/Laguna-M.1
- Architecture
- Mixture of experts
- Modality record
- text->text
- Catalogue slug
- poolside-laguna-m-1