GenSLM TPS calculator

Open weights University of Chicago,NVIDIA,Harvard University,Cerebras Systems,Technical University of Munich,California Institute of Technology 25B parameters October 2022

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

241 cards that can run it

818 cards we hold specifications for

Smallest card that fits

Xeon Phi 7120P

16 GB · IQ4_XS · 9.5 tok/s

Fastest card

B200

136 tok/s · 180 GB

Which GPUs can run GenSLM?

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

241 cards match

Calculating

					Needs	Quantisation	Fit
136 tok/s 81–217 · low confidence	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	27.5 GB	Q8_0	Comfortable
136 tok/s 81–217 · low confidence	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	27.5 GB	Q8_0	Comfortable
108 tok/s 65–173 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	27.5 GB	Q8_0	Comfortable
108 tok/s 65–173 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	27.5 GB	Q8_0	Comfortable
86.6 tok/s 52–138 · low confidence	Radeon Instinct MI300 AMD	128 GB	6,550 GB/s	Jan 2023	27.5 GB	Q8_0	Comfortable
82.8 tok/s 50–133 · low confidence	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	27.5 GB	Q8_0	Comfortable
82.8 tok/s 50–133 · low confidence	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	27.5 GB	Q8_0	Comfortable
79.3 tok/s 48–127 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	27.5 GB	Q8_0	Comfortable
70.4 tok/s 42–113 · low confidence	Radeon Instinct MI300A AMD	128 GB	5,325 GB/s	Dec 2023	27.5 GB	Q8_0	Comfortable
70.4 tok/s 42–113 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	27.5 GB	Q8_0	Comfortable
70.4 tok/s 42–113 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	27.5 GB	Q8_0	Comfortable
66.8 tok/s 40–107 · low confidence	H100 NVL 94 GB NVIDIA	94 GB	3,940 GB/s	Mar 2023	27.5 GB	Q8_0	Comfortable
56.9 tok/s 34–91 · low confidence	H100 PCIe 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	27.5 GB	Q8_0	Comfortable
56.9 tok/s 34–91 · low confidence	H100 SXM5 80 GB NVIDIA	80 GB	3,360 GB/s	Oct 2022	27.5 GB	Q8_0	Comfortable
56.9 tok/s 34–91 · low confidence	H100 SXM5 94 GB NVIDIA	94 GB	3,360 GB/s	Mar 2023	27.5 GB	Q8_0	Comfortable
56.9 tok/s 34–91 · low confidence	H100 SXM5 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	27.5 GB	Q8_0	Comfortable
56.9 tok/s 34–91 · low confidence	H800 SXM5 NVIDIA	80 GB	3,360 GB/s	Mar 2023	27.5 GB	Q8_0	Comfortable
47.0 tok/s 28–75 · low confidence	Tesla V100 SXM2 16 GB NVIDIA	16 GB	1,130 GB/s	Nov 2019	14.4 GB	IQ4_XS	Tight
43.3 tok/s 26–69 · low confidence	Radeon Instinct MI250 AMD	128 GB	3,280 GB/s	Nov 2021	27.5 GB	Q8_0	Comfortable
43.3 tok/s 26–69 · low confidence	Radeon Instinct MI250X AMD	128 GB	3,280 GB/s	Nov 2021	27.5 GB	Q8_0	Comfortable
40.5 tok/s 24–65 · low confidence	GeForce RTX 5090 D V2 NVIDIA	24 GB	1,340 GB/s	Aug 2025	18.7 GB	Q5_K_M	Tight
39.9 tok/s 24–64 · low confidence	GeForce RTX 5080 NVIDIA	16 GB	960 GB/s	Jan 2025	14.4 GB	IQ4_XS	Tight
37.3 tok/s 22–60 · low confidence	Tesla V100 DGXS 16 GB NVIDIA	16 GB	897 GB/s	Mar 2018	14.4 GB	IQ4_XS	Tight
37.3 tok/s 22–60 · low confidence	Tesla V100 PCIe 16 GB NVIDIA	16 GB	897 GB/s	Jun 2017	14.4 GB	IQ4_XS	Tight
37.3 tok/s 22–60 · low confidence	Tesla V100 SXM2 16 GB NVIDIA	16 GB	897 GB/s	Jun 2017	14.4 GB	IQ4_XS	Tight

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: University of Chicago,NVIDIA,Harvard University,Cerebras Systems,Technical University of Munich,California Institute of Technology
Organisation type: Academia,Industry,Academia,Industry,Academia,Academia
Country: United States of America, Germany
Published: 11 October 2022
Authors: Maxim Zvyagin, Alexander Brace, Kyle Hippe, Yuntian Deng, Bin Zhang, Cindy Orozco Bohorquez, Austin Clyde, Bharat Kale, Danilo Perez-Rivera, Heng Ma, Carla M. Mann, Michael Irvin, J. Gregory Pauloski, Logan Ward, Valerie Hayot, Murali Emani, Sam Foreman, Zhen Xie, Diangen Lin, Maulik Shukla, Weili Nie, Josh Romero, Christian Dallago, Arash Vahdat, Chaowei Xiao, Thomas Gibbs, Ian Foster, James J. D…

What it does

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

Domain: Biology
Task: Protein or nucleotide language model (pLM/nLM)
Numerical format: FP16

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: 25B
Training data: 225,280,000,000 tokens

Training compute

The arithmetic performed to train the model, measured in floating-point operations. It is a measure of what the training run cost, not of how fast the finished model answers you.

Training compute: 1.4 × 10²¹ FLOP
How it was established: Reported

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)
Training code: Open source

How it is classified

Labels the source dataset applies when tracking notable models, and how confident it is in the entry.

Foundation model: Yes
Why it is tracked: SOTA improvement
Record confidence: Confident
Citations: 114

Sources

Where this record came from and when it was last checked.

Reference: GenSLMs: Genome-scale language models reveal SARS-CoV-2 evolutionary dynamics
Last updated: 1 January 2026

The extremes

The ten fastest GPUs that run GenSLM

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 GenSLM

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

The hardware side

Minimum card

Xeon Phi 7120P

Memory needed

14.4 GB

Fastest

136 tok/s

GenSLM reaches a parameter count of 25B. That lands in the range a serious desktop card can handle once the weights are compressed. The number of cards we track that can run it: 241.

At the low end it is handled by Xeon Phi 7120P, with a memory capacity of 16 GB, running it at a compression of IQ4_XS and producing around 9.5 tokens per second.

The fastest we calculate for it is B200, generating roughly 136 tokens per second on the strength of a memory bandwidth of 8,000 GB/s.

About this model

GenSLM was published by University of Chicago,NVIDIA,Harvard University,Cerebras Systems,Technical University of Munich,California Institute of Technology, in the country recorded as United States of America, during October 2022. The publishing organisation is categorised as academia,Industry,Academia,Industry,Academia,Academia.

It works in the domain of Biology, and is recorded as performing the task of protein or nucleotide language model (pLM/nLM).

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.

How fast it runs, and why

Half the cards that hold it manage more than 18.6 tokens per second. Producing text faster than most people read it: 192 of them.

It is a dense model, so every parameter is read for every token produced. That makes speed track memory bandwidth almost exactly — a card with twice the bandwidth generates roughly twice as fast.

Memory here is estimated from size rather than computed from the architecture, which is not recorded for this model — the numbers are indicative rather than exact.

What went into building it

Training it took a computation budget of roughly 1.4 × 10²¹ FLOP. That figure measures what producing the model cost, and has no bearing on how fast it answers.

The training set ran to roughly 225,280,000,000 tokens of text.

It is tracked in the underlying dataset for one reason in particular: sOTA improvement.

Step by step

How to choose a GPU for GenSLM

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

Start from what it actually needs, which is the requirement of GenSLM, needing around 14.4 GB at a compression of IQ4_XS. Capacity is the gate — a card either holds it or it does not.
02

Match the context to your actual use

Set the context to what you will actually use. The cache grows with the conversation, and it is the usual reason a card that seemed fine stops fitting GenSLM.
03

Choose how far you will compress it

Each card runs the least-compressed copy it can hold, reaching a compression of IQ4_XS 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

Rank by throughput rather than spec sheet

Sort by speed to see how cards rank for GenSLM. It will not match a gaming ordering, because generation is bound by memory bandwidth. The card topping the list is B200, at 136 tok/s.
05

Look at the headroom, not just the fit

Tight means it loads and works with no room to raise the context later, in the case of GenSLM. 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

Check the card from the other side

Each card page repeats this sweep for every model we hold, answering what else the hardware is good for beyond GenSLM.

Answers

GenSLM — common questions

GenSLM— can I run it if it does not fit in my GPU?

Only by offloading, which is usually a false economy: the part held in system memory drags the whole thing down. The nearest miss we calculate falls short by 5.0 GB. Every figure here assumes the whole model is resident on the card.

GenSLM— would two GPUs run it faster?

A second card roughly doubles the memory available but not the generation rate. The number already able to run it alone: 241. So a second card is rarely the answer here.

GenSLM— why does the quantisation differ between cards?

Because capacity varies, so does how hard it has to be squeezed. The number of distinct levels in the table above: 5. Bigger cards get the more accurate version, and the quality floor above pins the comparison to one level.

GenSLM— 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: 81–217 tok/s on B200. The same model and card vary by thirty to fifty per cent depending on the inference software and its version.

GenSLM— what GPU do I need to run it?

The smallest card in our catalogue that holds it is Xeon Phi 7120P, with a memory capacity of 16 GB. It runs the model at a compression of IQ4_XS using about 14.4 GB, and produces roughly 9.5 tokens per second. The number of cards able to run it in total: 241.

GenSLM— how fast is it on a GPU?

It depends on the card. The quickest we calculate is B200, at about 136 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: 192.

GenSLM— how much VRAM does it need?

It needs about 14.4 GB at a compression of IQ4_XS, 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.

GenSLM— can I run it on a GPU holding 16 GB?

Yes. The card Tesla V100 SXM2 16 GB, holding 16 GB, runs it at a compression of IQ4_XS, using about 14.4 GB and generating roughly 47.0 tokens per second. The fit is tight.

GenSLM— can I run it on a GPU holding 24 GB?

Yes. The card GeForce RTX 5090 D V2, holding 24 GB, runs it at a compression of Q5_K_M, using about 18.7 GB and generating roughly 40.5 tokens per second. The fit is tight.

GenSLM— 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.

GenSLM— how many parameters does it have?

It has a parameter count of 25B. See Table 3. 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.

GenSLM— who created it?

It was published by University of Chicago,NVIDIA,Harvard University,Cerebras Systems,Technical University of Munich,California Institute of Technology, based in United States of America, an organisation categorised as academia,Industry,Academia,Industry,Academia,Academia.

GenSLM— when was it released?

It was published in October 2022. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.

GenSLM— what is it used for?

It works in the domain of Biology, and is recorded as handling the task of protein or nucleotide language model (pLM/nLM). A model can carry several of each, so these are the areas it was built for rather than a limit on what it will attempt.

GenSLM— 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.

GenSLM— how much compute was used to train it?

Training consumed around 1.4 × 10²¹ FLOP. That measures what producing the model cost and says nothing about how quickly it answers once trained — inference speed comes from memory bandwidth, not from the training budget.

Source

Original publication

Record last updated 1 January 2026

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