Laguna S 2.1 TPS calculator

Open weights Poolside 118B parameters July 2026

Each card below is assessed against this model at the context length and minimum quality you choose. Speed is an estimate for a single request, calculated from the card's memory bandwidth and the size of the model once compressed.

Calculated for this model

43 cards that can run it

818 cards we hold specifications for

Smallest card that fits

Radeon Instinct MI200

64 GB · Q3_K_M · 68.8 tok/s

Fastest card

B200

160 tok/s · 180 GB

Which GPUs can run Laguna S 2.1?

Set the inputs, read the answer

Context length tokens

A longer conversation needs more memory, which can push this model off smaller cards.

Minimum quality

Hides cards that would only fit the model by compressing it below this point.

Search cards

Card memory

Also show cards that cannot run it

43 cards match

Calculating

					Needs	Quantisation	Fit
160 tok/s 96–255 · low confidence	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	119.6 GB	Q8_0	Comfortable
160 tok/s 96–255 · low confidence	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	119.6 GB	Q8_0	Comfortable
155 tok/s 93–247 · low confidence	H100 SXM5 80 GB NVIDIA	80 GB	3,360 GB/s	Oct 2022	64.7 GB	Q4_K_M	Tight
155 tok/s 93–247 · low confidence	H800 SXM5 NVIDIA	80 GB	3,360 GB/s	Mar 2023	64.7 GB	Q4_K_M	Tight
148 tok/s 89–237 · low confidence	Radeon Instinct MI300 AMD	128 GB	6,550 GB/s	Jan 2023	92.1 GB	Q6_K	Comfortable
140 tok/s 84–224 · low confidence	H100 NVL 94 GB NVIDIA	94 GB	3,940 GB/s	Mar 2023	78.4 GB	Q5_K_M	Tight
127 tok/s 76–204 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	119.6 GB	Q8_0	Comfortable
127 tok/s 76–204 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	119.6 GB	Q8_0	Comfortable
120 tok/s 72–193 · low confidence	Radeon Instinct MI300A AMD	128 GB	5,325 GB/s	Dec 2023	92.1 GB	Q6_K	Comfortable
120 tok/s 72–191 · low confidence	H100 PCIe 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	78.4 GB	Q5_K_M	Tight
120 tok/s 72–191 · low confidence	H100 SXM5 94 GB NVIDIA	94 GB	3,360 GB/s	Mar 2023	78.4 GB	Q5_K_M	Tight
120 tok/s 72–191 · low confidence	H100 SXM5 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	78.4 GB	Q5_K_M	Tight
109 tok/s 65–174 · low confidence	H100 SXM5 64 GB NVIDIA	64 GB	2,020 GB/s	Mar 2023	50.9 GB	Q3_K_M	Tight
97.5 tok/s 59–156 · low confidence	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	119.6 GB	Q8_0	Tight
97.5 tok/s 59–156 · low confidence	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	119.6 GB	Q8_0	Tight
93.9 tok/s 56–150 · low confidence	A100 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Nov 2020	64.7 GB	Q4_K_M	Tight
93.9 tok/s 56–150 · low confidence	A100X NVIDIA	80 GB	2,040 GB/s	Jun 2021	64.7 GB	Q4_K_M	Tight
93.9 tok/s 56–150 · low confidence	A800 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Aug 2022	64.7 GB	Q4_K_M	Tight
93.9 tok/s 56–150 · low confidence	H100 CNX NVIDIA	80 GB	2,040 GB/s	Mar 2023	64.7 GB	Q4_K_M	Tight
93.9 tok/s 56–150 · low confidence	H100 PCIe 80 GB NVIDIA	80 GB	2,040 GB/s	Oct 2022	64.7 GB	Q4_K_M	Tight
93.9 tok/s 56–150 · low confidence	H800 PCIe 80 GB NVIDIA	80 GB	2,040 GB/s	Mar 2023	64.7 GB	Q4_K_M	Tight
93.3 tok/s 56–149 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	119.6 GB	Q8_0	Comfortable
89.3 tok/s 54–143 · low confidence	A100 PCIe 80 GB NVIDIA	80 GB	1,940 GB/s	Jun 2021	64.7 GB	Q4_K_M	Tight
89.3 tok/s 54–143 · low confidence	A800 PCIe 80 GB NVIDIA	80 GB	1,940 GB/s	Nov 2022	64.7 GB	Q4_K_M	Tight
82.8 tok/s 50–133 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	119.6 GB	Q8_0	Comfortable

Speeds are estimates for a single request — one conversation at a time — calculated from memory bandwidth, model size and quantisation. Real throughput varies with the inference runtime and its version. Figures published by hardware vendors measure many simultaneous requests and are much higher.

On record

Full specification

Everything on record for this model. Most of it describes how it was trained rather than how it runs — useful context for judging how much work went into it, and how it compares with models built at a different scale.

Origin

Who built this model, where, and when it was published.

Organisation: Poolside
Organisation type: Industry
Country: United States of America
Published: 21 July 2026

What it does

The problem areas the model was built for. A model can carry several of each.

Domain: Language
Task: Code generation, Language modeling/generation

Size

How large the model is and how much data it was trained on. Parameters are the figure that decides whether it fits on a given graphics card.

Parameters: 118B
Training data: tokens

Availability

Whether you can obtain the model and run it on your own hardware, which is what decides if any of the graphics-card figures on this page apply.

Weights: Open — downloadable
Model access: Open weights (unrestricted)

The extremes

The ten fastest GPUs that run Laguna S 2.1

Ranked by estimated tokens per second, newest card first where speeds tie. Because generation is bound by memory bandwidth, this ordering follows bandwidth rather than any gaming benchmark.

The smallest GPUs that still run Laguna S 2.1

The cheapest route in, by memory capacity. A tight fit runs the model but leaves nothing spare for a longer conversation.

What the numbers mean

What it takes to run this model

Minimum card

Radeon Instinct MI200

Memory needed

50.9 GB

Fastest

160 tok/s

Laguna S 2.1 reaches a parameter count of 118B. That puts it above consumer hardware, into the range where a card is bought for this purpose rather than repurposed for it. The number of cards we track that can hold it: 43.

The smallest card that holds it is Radeon Instinct MI200, with a memory capacity of 64 GB, running it at a compression of Q3_K_M and producing around 68.8 tokens per second.

Top of the range is B200, generating roughly 160 tokens per second on the strength of a memory bandwidth of 8,000 GB/s.

Background

Laguna S 2.1 was published by Poolside, in the country recorded as United States of America, during July 2026. The publishing organisation is categorised as industry.

It works in the domain of Language, and is recorded as performing the task of code generation, Language modeling/generation.

The weights being open is what puts this page in the calculator rather than only in the catalogue: it is a model you can actually hold.

Reading the throughput figures

Half the cards that hold it manage more than 93.3 tokens per second. Producing text faster than most people read it: 41 of them.

Because it routes each token through a subset of its weights, it produces text at the pace of a much smaller model. The catch is memory: all of it still has to fit, so the speed is a bonus rather than a discount on hardware.

Without the attention layout on record, the memory column is an approximation. It is close enough to choose hardware by, and least reliable at long context.

Step by step

How to choose a GPU for Laguna S 2.1

The table above has already assessed every card we hold specifications for against this model. Getting to your answer takes six steps.

01

Read the memory figure first

The table lists every card able to hold Laguna S 2.1, needing around 50.9 GB at a compression of Q3_K_M. No amount of processing power compensates for a card that cannot hold it.
02

Set the context length you will work at

Longer conversations cost memory on top of what the weights need. Move the slider to your real working length before trusting any row for Laguna S 2.1.
03

Choose how far you will compress it

Compression is what makes a model fit smaller cards, at some cost in accuracy, reaching a compression of Q3_K_M on the smallest card that fits. Setting a minimum quality drops the cards that only manage it by squeezing further than you would want, and holds the comparison at one level.
04

Sort by speed

Sort by speed to see how cards rank for Laguna S 2.1. It will not match a gaming ordering, because generation is bound by memory bandwidth. The card topping the list is B200, at 160 tok/s.
05

Read the fit column last

A tight fit runs, but leaves nothing spare for a longer conversation, in the case of Laguna S 2.1. Comfortable means you can grow the context later. That difference matters more than a few tokens per second, so buy for comfortable if you expect to.
06

Open the card you have settled on

Every card name links to its own page, which runs the same calculation across the whole model catalogue. A card is usually bought for more than one model, so it is worth a look before buying for Laguna S 2.1.

Answers

Laguna S 2.1 — common questions

Laguna S 2.1— how accurate are these speed estimates?

These are estimates with real error bars, and any of them could reasonably land anywhere in its published range depending on which runtime you use. The fastest result here: 96–255 tok/s on B200. The same model and card vary by thirty to fifty per cent depending on the inference software and its version.

Laguna S 2.1— what GPU do I need to run it?

The smallest card in our catalogue that holds it is Radeon Instinct MI200, with a memory capacity of 64 GB. It runs the model at a compression of Q3_K_M using about 50.9 GB, and produces roughly 68.8 tokens per second. The number of cards able to run it in total: 43.

Laguna S 2.1— how fast is it on a GPU?

It depends on the card. The quickest we calculate is B200, at about 160 tokens per second; the slowest that still runs it manages considerably less. Reading speed is around ten tokens per second, and the number of cards clearing that: 41.

Laguna S 2.1— how much VRAM does it need?

It needs about 50.9 GB at a compression of Q3_K_M, which is what the smallest card that runs it uses. Less compression needs more: the figures in the memory column above are recalculated for each card, because each one holds the least-compressed version it can.

Laguna S 2.1— is it open source?

Its weights are published, so it can be downloaded and run on your own hardware. Note that open weights is not the same as open source in the full sense — it says nothing about the training data, the training code, or the commercial terms attached.

Laguna S 2.1— how many parameters does it have?

It has a parameter count of 118B. 118B MoE, 8B active. That figure is the total, and it is what decides how much memory the model needs — roughly half a gigabyte per billion at the compression most people use.

Laguna S 2.1— who created it?

It was published by Poolside, based in United States of America, an organisation categorised as industry.

Laguna S 2.1— when was it released?

It was published in July 2026.

Laguna S 2.1— what is it used for?

It works in the domain of Language, and is recorded as handling the task of code generation, Language modeling/generation. These are the areas it was designed around; they describe intent rather than a hard boundary.

Laguna S 2.1— where can I download it?

The weights are published, though we do not hold a repository link for it. This site calculates hardware requirements rather than hosting model files.

Laguna S 2.1— can I run it if it does not fit in my GPU?

It can be split between the card and system memory, but it generates painfully slowly that way. The nearest miss we calculate falls short by 21.5 GB. Every figure here assumes the whole model is resident on the card.

Laguna S 2.1— would two GPUs run it faster?

Two cards buy memory rather than speed, which matters only if one card cannot hold it. The number that can: 43. So a second card is rarely the answer here.

Laguna S 2.1— why does the quantisation differ between cards?

Each card is shown running the least-compressed copy it can hold. The number of distinct compression levels across the cards that fit it: 5. Bigger cards get the more accurate version, and the quality floor above pins the comparison to one level.

The other direction

Looking at it from the other side?

This page starts from the model. If you already own a card and want to know everything it will run, start from the hardware instead.

All AI models