TxGemma 27B TPS calculator

Open weights Google DeepMind,Google Research 27B 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

241 cards that can run it

818 cards we hold specifications for

Smallest card that fits

Xeon Phi 7120P

16 GB · Q3_K_M · 9.7 tok/s

Fastest card

B200

125 tok/s · 180 GB

Which GPUs can run TxGemma 27B?

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
125 tok/s 107–151	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	30.1 GB	Q8_0	Comfortable
125 tok/s 107–151	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	30.1 GB	Q8_0	Comfortable
100 tok/s 60–160 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	30.1 GB	Q8_0	Comfortable
100 tok/s 60–160 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	30.1 GB	Q8_0	Comfortable
80.1 tok/s 48–128 · low confidence	Radeon Instinct MI300 AMD	128 GB	6,550 GB/s	Jan 2023	30.1 GB	Q8_0	Comfortable
76.7 tok/s 65–92	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	30.1 GB	Q8_0	Comfortable
76.7 tok/s 65–92	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	30.1 GB	Q8_0	Comfortable
73.4 tok/s 44–117 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	30.1 GB	Q8_0	Comfortable
65.2 tok/s 39–104 · low confidence	Radeon Instinct MI300A AMD	128 GB	5,325 GB/s	Dec 2023	30.1 GB	Q8_0	Comfortable
65.2 tok/s 39–104 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	30.1 GB	Q8_0	Comfortable
65.2 tok/s 39–104 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	30.1 GB	Q8_0	Comfortable
61.8 tok/s 53–74	H100 NVL 94 GB NVIDIA	94 GB	3,940 GB/s	Mar 2023	30.1 GB	Q8_0	Comfortable
52.7 tok/s 45–63	H100 PCIe 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	30.1 GB	Q8_0	Comfortable
52.7 tok/s 45–63	H100 SXM5 80 GB NVIDIA	80 GB	3,360 GB/s	Oct 2022	30.1 GB	Q8_0	Comfortable
52.7 tok/s 45–63	H100 SXM5 94 GB NVIDIA	94 GB	3,360 GB/s	Mar 2023	30.1 GB	Q8_0	Comfortable
52.7 tok/s 45–63	H100 SXM5 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	30.1 GB	Q8_0	Comfortable
52.7 tok/s 45–63	H800 SXM5 NVIDIA	80 GB	3,360 GB/s	Mar 2023	30.1 GB	Q8_0	Comfortable
47.8 tok/s 41–57	Tesla V100 SXM2 16 GB NVIDIA	16 GB	1,130 GB/s	Nov 2019	14.4 GB	Q3_K_M	Tight
42.6 tok/s 36–51	DRIVE A100 PROD NVIDIA	32 GB	1,870 GB/s	May 2020	23.8 GB	Q6_K	Comfortable
42.6 tok/s 36–51	GRID A100A NVIDIA	32 GB	1,870 GB/s	May 2020	23.8 GB	Q6_K	Comfortable
40.8 tok/s 35–49	GeForce RTX 5090 NVIDIA	32 GB	1,790 GB/s	Jan 2025	23.8 GB	Q6_K	Comfortable
40.8 tok/s 35–49	GeForce RTX 5090 D NVIDIA	32 GB	1,790 GB/s	Jan 2025	23.8 GB	Q6_K	Comfortable
40.6 tok/s 35–49	GeForce RTX 5080 NVIDIA	16 GB	960 GB/s	Jan 2025	14.4 GB	Q3_K_M	Tight
40.1 tok/s 24–64 · low confidence	Radeon Instinct MI250 AMD	128 GB	3,280 GB/s	Nov 2021	30.1 GB	Q8_0	Comfortable
40.1 tok/s 24–64 · low confidence	Radeon Instinct MI250X AMD	128 GB	3,280 GB/s	Nov 2021	30.1 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, Chat, Question answering, Protein question answering, Protein function prediction, Language modeling/generation
Base model: Gemma 2 27B

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: 27B
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: 2.1 × 10²⁴ FLOP
How it was established: Operation counting
Fine-tuning compute: 1.1 × 10²² 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.

Likely above 10²³ FLOP: Yes
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 27B

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 27B

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

125 tok/s

With 27B parameters, TxGemma 27B lands in the range a serious desktop card can handle once the weights are compressed. 241 of the cards we track can run it.

At the low end, a Xeon Phi 7120P handles it — 16 GB, at Q3_K_M, for about 9.7 tokens per second.

At the other end, a B200 generates roughly 125 tokens per second on it, on the strength of 8,000 GB/s of memory bandwidth.

Background

TxGemma 27B was published by Google DeepMind,Google Research, in United States of America, in April 2025. It comes out of 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, Chat, Question answering, Protein question answering, Protein function prediction, Language modeling/generation.

Its starting point was Gemma 2 27B — 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.

Reading the throughput figures

Across every card that can run it, the middle of the range is about 19.0 tokens per second, and 196 of them clear the ten tokens per second that roughly matches reading speed.

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.

Because the architecture is recorded, the memory column is derived rather than estimated.

How it was trained

Training it took roughly 2.1 × 10²⁴ FLOP of computation, on Google TPU v4 — a measure of what producing the model cost, not of how fast it answers.

Step by step

How to choose a GPU for TxGemma 27B

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

01

Start from the memory column

Look at what TxGemma 27B actually needs — around 14.4 GB at Q3_K_M. No amount of processing power compensates for a card that cannot hold it.
02

Decide how long your conversations run

The conversation occupies memory too, and grows as it goes. Set the slider to the length you expect: at long context TxGemma 27B can slip off a card that handles short questions easily.
03

Decide how much compression you will accept

Each card runs the least-compressed copy it can hold — Q3_K_M on the smallest card that fits. Setting a floor drops the cards that only manage TxGemma 27B by squeezing it further than you would want.
04

Compare tokens per second, not specifications

Ranking by tokens per second for TxGemma 27B follows memory bandwidth, not core counts, which is why the B200 tops it at 125 tok/s.
05

Look at the headroom, not just the fit

A tight fit runs TxGemma 27B but leaves nothing spare for a longer conversation; comfortable has headroom. If you expect to grow the context, buy for comfortable.
06

Check the card from the other side

Each card page repeats this sweep for every model we hold. It answers what else the hardware is good for, beyond TxGemma 27B.

Answers

TxGemma 27B — common questions

What GPU do I need to run TxGemma 27B?

The smallest card in our catalogue that holds TxGemma 27B is the Xeon Phi 7120P, with 16 GB of memory. It runs the model at Q3_K_M using about 14.4 GB, and produces roughly 9.7 tokens per second. 241 cards in total can run it.

How fast is TxGemma 27B on a GPU?

It depends on the card. The quickest we calculate is a B200 at about 125 tokens per second; the slowest that still runs it manages considerably less. Reading speed is around ten tokens per second, and 196 of the cards that can run TxGemma 27B clear that.

How much VRAM does TxGemma 27B need?

About 14.4 GB at Q3_K_M 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 27B on a 16 GB GPU?

Yes. A Tesla V100 SXM2 16 GB with 16 GB runs it at Q3_K_M, using about 14.4 GB and generating roughly 47.8 tokens per second — a tight fit.

Can I run TxGemma 27B on a 24 GB GPU?

Yes. A GeForce RTX 5090 D V2 with 24 GB runs it at Q5_K_M, using about 20.6 GB and generating roughly 37.5 tokens per second — a tight fit.

Is TxGemma 27B open source?

Its weights are published, so TxGemma 27B 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 27B have?

TxGemma 27B has 27B parameters. 27B. 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 27B?

TxGemma 27B was published by Google DeepMind,Google Research, based in United States of America, categorised as industry,Industry.

When was TxGemma 27B released?

TxGemma 27B was published in April 2025.

What is TxGemma 27B used for?

TxGemma 27B works in Language, Biology, and is recorded as handling protein or nucleotide language model (pLM/nLM), Protein property prediction, Small molecule property prediction, Chat, Question answering, Protein question answering, Protein function prediction, Language modeling/generation. 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.

Where can I download TxGemma 27B?

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 27B?

Around 2.1 × 10²⁴ 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 27B 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 27B is rarely worth using — the nearest miss we calculate is short by 6.7 GB. Every figure here assumes the whole model is on the card.

Would two GPUs run TxGemma 27B faster?

Capacity adds across cards; throughput does not. Since 241 of the cards we track already hold TxGemma 27B on their own, a second card is rarely the answer here.

Why does the quantisation differ between cards for TxGemma 27B?

A larger card holds a more accurate copy. Across the cards that run TxGemma 27B, 5 compression levels are used; the floor control above pins it to one.

How accurate are these TxGemma 27B speed estimates?

They are calculated from specifications rather than measured, and each carries a range — 107–151 tok/s on the B200, for instance. The same model and card vary by thirty to fifty per cent depending on the inference software and its version.

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