TxGemma 2B TPS calculator

Open weights Google DeepMind,Google Research 2.6B parameters April 2025

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

818 cards that can run it

818 cards we hold specifications for

Smallest card that fits

Tesla C1080

4 GB · Q6_K · 20.6 tok/s

Fastest card

B200

1,303 tok/s · 180 GB

Which GPUs can run TxGemma 2B?

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

818 cards match

Calculating

					Needs	Quantisation	Fit
1,303 tok/s 1,108–1,564	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	3.9 GB	Q8_0	Comfortable
1,303 tok/s 1,108–1,564	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	3.9 GB	Q8_0	Comfortable
1,041 tok/s 624–1,665 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	3.9 GB	Q8_0	Comfortable
1,041 tok/s 624–1,665 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	3.9 GB	Q8_0	Comfortable
832 tok/s 499–1,332 · low confidence	Radeon Instinct MI300 AMD	128 GB	6,550 GB/s	Jan 2023	3.9 GB	Q8_0	Comfortable
797 tok/s 677–956	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	3.9 GB	Q8_0	Comfortable
797 tok/s 677–956	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	3.9 GB	Q8_0	Comfortable
762 tok/s 457–1,220 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	3.9 GB	Q8_0	Comfortable
677 tok/s 406–1,083 · low confidence	Radeon Instinct MI300A AMD	128 GB	5,325 GB/s	Dec 2023	3.9 GB	Q8_0	Comfortable
677 tok/s 406–1,083 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	3.9 GB	Q8_0	Comfortable
677 tok/s 406–1,083 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	3.9 GB	Q8_0	Comfortable
642 tok/s 546–770	H100 NVL 94 GB NVIDIA	94 GB	3,940 GB/s	Mar 2023	3.9 GB	Q8_0	Comfortable
547 tok/s 465–657	H100 PCIe 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	3.9 GB	Q8_0	Comfortable
547 tok/s 465–657	H100 SXM5 80 GB NVIDIA	80 GB	3,360 GB/s	Oct 2022	3.9 GB	Q8_0	Comfortable
547 tok/s 465–657	H100 SXM5 94 GB NVIDIA	94 GB	3,360 GB/s	Mar 2023	3.9 GB	Q8_0	Comfortable
547 tok/s 465–657	H100 SXM5 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	3.9 GB	Q8_0	Comfortable
547 tok/s 465–657	H800 SXM5 NVIDIA	80 GB	3,360 GB/s	Mar 2023	3.9 GB	Q8_0	Comfortable
417 tok/s 250–667 · low confidence	Radeon Instinct MI250 AMD	128 GB	3,280 GB/s	Nov 2021	3.9 GB	Q8_0	Comfortable
417 tok/s 250–667 · low confidence	Radeon Instinct MI250X AMD	128 GB	3,280 GB/s	Nov 2021	3.9 GB	Q8_0	Comfortable
347 tok/s 208–556 · low confidence	Data Center GPU Max 1550 Intel	128 GB	3,280 GB/s	Jan 2023	3.9 GB	Q8_0	Comfortable
340 tok/s 204–544 · low confidence	Data Center GPU Max Subsystem Intel	128 GB	3,210 GB/s	Jan 2023	3.9 GB	Q8_0	Comfortable
332 tok/s 282–399	A100 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Nov 2020	3.9 GB	Q8_0	Comfortable
332 tok/s 282–399	A100X NVIDIA	80 GB	2,040 GB/s	Jun 2021	3.9 GB	Q8_0	Comfortable
332 tok/s 282–399	A800 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Aug 2022	3.9 GB	Q8_0	Comfortable
332 tok/s 282–399	H100 CNX NVIDIA	80 GB	2,040 GB/s	Mar 2023	3.9 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: Google DeepMind,Google Research
Organisation type: Industry,Industry
Country: United States of America
Published: 8 April 2025
Authors: Eric Wang, Samuel Schmidgall, Paul F. Jaeger, Fan Zhang, Rory Pilgrim, Yossi Matias, Joelle Barral, David Fleet, Shekoofeh Azizi

What it does

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

Domain: Language, Biology
Task: Protein or nucleotide language model (pLM/nLM), Protein property prediction, Small molecule property prediction, Question answering, Protein question answering, Protein function prediction, Language modeling/generation
Base model: Gemma 2 2B

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: 2.6B
Training data: tokens
Epochs: 12

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: 3.2 × 10²² FLOP
How it was established: Operation counting
Fine-tuning compute: 1 × 10²¹ FLOP

The training run

What it physically took to train: which chips, how many, for how long, and what that drew from the wall.

Training hardware: Google TPU v4
Chips used: 256
Power draw: 170.7 kW

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 (restricted use)
Training code: Unreleased
Hugging Face: google

How it is classified

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

Record confidence: Confident

Sources

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

Reference: TxGemma: Efficient and Agentic LLMs for Therapeutics
Last updated: 28 November 2025

The extremes

The ten fastest GPUs that run TxGemma 2B

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 TxGemma 2B

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

Tesla C1080

Memory needed

3.3 GB

Fastest

1,303 tok/s

TxGemma 2B is small enough at 2.6B parameters that hardware is rarely the obstacle — 818 of the cards we track can run it, including cards several years old.

The smallest card that holds it is the Tesla C1080 with 4 GB, running it at Q6_K and producing around 20.6 tokens per second.

A B200 is the fastest we calculate for it: about 1,303 tokens per second, from 8,000 GB/s of memory bandwidth.

Where it came from

TxGemma 2B was published by Google DeepMind,Google Research, in United States of America, in April 2025. The organisation is categorised as industry,Industry.

It works in Language, Biology, and is recorded as doing protein or nucleotide language model (pLM/nLM), Protein property prediction, Small molecule property prediction, Question answering, Protein question answering, Protein function prediction, Language modeling/generation.

Its starting point was Gemma 2 2B — most models at this scale are adapted from an existing base rather than built from nothing.

The weights are published, so it can be downloaded and run on your own hardware indefinitely, offline, with no account attached. It is published under the google organisation on Hugging Face.

Understanding the speeds

Half the cards that hold it manage more than 41.4 tokens per second, and 786 exceed reading speed outright.

Being dense, it reads all of itself per token, which is why the ordering by speed below follows the ordering by memory bandwidth so closely.

Its attention layout is on file, so the memory figures are computed exactly rather than approximated.

What went into building it

Producing it required around 3.2 × 10²² FLOP of arithmetic, on Google TPU v4, which is a statement about the training budget rather than about inference.

Step by step

How to choose a GPU for TxGemma 2B

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 that can hold TxGemma 2B — around 3.3 GB at Q6_K. That figure, not the card's headline performance, is what decides whether it runs.
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 TxGemma 2B stops fitting a card that seemed fine.
03

Choose how far you will compress it

Compression is what makes TxGemma 2B fit smaller cards, at some cost in accuracy — Q6_K on the smallest card that fits. A minimum quality removes the ones that go too far.
04

Compare tokens per second, not specifications

The speed ordering for TxGemma 2B is effectively an ordering by memory bandwidth, which is why the B200 tops it at 1,303 tok/s.
05

Read the fit column last

Tight means TxGemma 2B loads and works, with no room to raise the context later. Comfortable means you can. The difference matters more than a few tokens per second.
06

See what else that card runs

Following a card through to its own page shows every other model it can hold, which is the question that follows once TxGemma 2B is settled.

Answers

TxGemma 2B — common questions

Can I run TxGemma 2B on a 16 GB GPU?

Yes. A Tesla V100 SXM2 16 GB with 16 GB runs it at Q8_0, using about 3.9 GB and generating roughly 184 tokens per second — a comfortable fit.

Can I run TxGemma 2B on a 24 GB GPU?

Yes. A GeForce RTX 5090 D V2 with 24 GB runs it at Q8_0, using about 3.9 GB and generating roughly 218 tokens per second — a comfortable fit.

Is TxGemma 2B open source?

Its weights are published, so TxGemma 2B 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.

How many parameters does TxGemma 2B have?

TxGemma 2B has 2.6B parameters. 2.6B. 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.

Who created TxGemma 2B?

TxGemma 2B was published by Google DeepMind,Google Research, based in United States of America, categorised as industry,Industry.

When was TxGemma 2B released?

TxGemma 2B was published in April 2025.

What is TxGemma 2B used for?

TxGemma 2B works in Language, Biology, and is recorded as handling protein or nucleotide language model (pLM/nLM), Protein property prediction, Small molecule property prediction, Question answering, Protein question answering, Protein function prediction, Language modeling/generation. These are the areas it was designed around; they describe intent rather than a hard boundary.

Where can I download TxGemma 2B?

Its weights are published under the google organisation on Hugging Face. We do not host model files — this site calculates what hardware is needed to run them.

How much compute was used to train TxGemma 2B?

Around 3.2 × 10²² FLOP, on Google TPU v4. 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.

Can I run TxGemma 2B if it does not fit in my GPU?

Partly. Layers that do not fit sit in system memory and run at a fraction of the speed, so a mostly-offloaded TxGemma 2B is rarely worth using. Every figure here assumes the whole model is on the card.

Would two GPUs run TxGemma 2B faster?

Capacity adds across cards; throughput does not. Since 818 of the cards we track already hold TxGemma 2B on their own, a second card is rarely the answer here.

Why does the quantisation differ between cards for TxGemma 2B?

Each card is shown running the least-compressed copy it can hold, and TxGemma 2B appears at 2 different compression levels across the cards that fit it. Bigger cards get the more accurate version.

How accurate are these TxGemma 2B speed estimates?

These are estimates with real error bars. The fastest result here, 1,108–1,564 tok/s on the B200, could reasonably land anywhere in its published range depending on which runtime you use.

What GPU do I need to run TxGemma 2B?

The smallest card in our catalogue that holds TxGemma 2B is the Tesla C1080, with 4 GB of memory. It runs the model at Q6_K using about 3.3 GB, and produces roughly 20.6 tokens per second. 818 cards in total can run it.

How fast is TxGemma 2B on a GPU?

It depends on the card. The quickest we calculate is a B200 at about 1,303 tokens per second; the slowest that still runs it manages considerably less. Reading speed is around ten tokens per second, and 786 of the cards that can run TxGemma 2B clear that.

How much VRAM does TxGemma 2B need?

About 3.3 GB at Q6_K compression, 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.

Can I run TxGemma 2B on a 8 GB GPU?

Yes. A CMP 170HX 8 GB with 8 GB runs it at Q8_0, using about 3.9 GB and generating roughly 243 tokens per second — a comfortable fit.

Can I run TxGemma 2B on a 12 GB GPU?

Yes. A GeForce RTX 3080 Ti with 12 GB runs it at Q8_0, using about 3.9 GB and generating roughly 149 tokens per second — a comfortable fit.

Source

Original publication

Record last updated 28 November 2025

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