PaliGemma 2 3B Mix 224 TPS calculator

Open weights Google 2.9B parameters February 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 · 18.3 tok/s

Fastest card

B200

1,160 tok/s · 180 GB

Which GPUs can run PaliGemma 2 3B Mix 224?

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
1,160 tok/s 696–1,857 · low confidence	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	3.8 GB	Q8_0	Comfortable
1,160 tok/s 696–1,857 · low confidence	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	3.8 GB	Q8_0	Comfortable
927 tok/s 556–1,483 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	3.8 GB	Q8_0	Comfortable
927 tok/s 556–1,483 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	3.8 GB	Q8_0	Comfortable
741 tok/s 445–1,186 · low confidence	Radeon Instinct MI300 AMD	128 GB	6,550 GB/s	Jan 2023	3.8 GB	Q8_0	Comfortable
709 tok/s 426–1,135 · low confidence	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	3.8 GB	Q8_0	Comfortable
709 tok/s 426–1,135 · low confidence	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	3.8 GB	Q8_0	Comfortable
679 tok/s 407–1,086 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	3.8 GB	Q8_0	Comfortable
602 tok/s 361–964 · low confidence	Radeon Instinct MI300A AMD	128 GB	5,325 GB/s	Dec 2023	3.8 GB	Q8_0	Comfortable
602 tok/s 361–964 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	3.8 GB	Q8_0	Comfortable
602 tok/s 361–964 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	3.8 GB	Q8_0	Comfortable
571 tok/s 343–914 · low confidence	H100 NVL 94 GB NVIDIA	94 GB	3,940 GB/s	Mar 2023	3.8 GB	Q8_0	Comfortable
487 tok/s 292–780 · low confidence	H100 PCIe 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	3.8 GB	Q8_0	Comfortable
487 tok/s 292–780 · low confidence	H100 SXM5 80 GB NVIDIA	80 GB	3,360 GB/s	Oct 2022	3.8 GB	Q8_0	Comfortable
487 tok/s 292–780 · low confidence	H100 SXM5 94 GB NVIDIA	94 GB	3,360 GB/s	Mar 2023	3.8 GB	Q8_0	Comfortable
487 tok/s 292–780 · low confidence	H100 SXM5 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	3.8 GB	Q8_0	Comfortable
487 tok/s 292–780 · low confidence	H800 SXM5 NVIDIA	80 GB	3,360 GB/s	Mar 2023	3.8 GB	Q8_0	Comfortable
371 tok/s 223–594 · low confidence	Radeon Instinct MI250 AMD	128 GB	3,280 GB/s	Nov 2021	3.8 GB	Q8_0	Comfortable
371 tok/s 223–594 · low confidence	Radeon Instinct MI250X AMD	128 GB	3,280 GB/s	Nov 2021	3.8 GB	Q8_0	Comfortable
309 tok/s 186–495 · low confidence	Data Center GPU Max 1550 Intel	128 GB	3,280 GB/s	Jan 2023	3.8 GB	Q8_0	Comfortable
303 tok/s 182–484 · low confidence	Data Center GPU Max Subsystem Intel	128 GB	3,210 GB/s	Jan 2023	3.8 GB	Q8_0	Comfortable
296 tok/s 178–473 · low confidence	A100 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Nov 2020	3.8 GB	Q8_0	Comfortable
296 tok/s 178–473 · low confidence	A100X NVIDIA	80 GB	2,040 GB/s	Jun 2021	3.8 GB	Q8_0	Comfortable
296 tok/s 178–473 · low confidence	A800 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Aug 2022	3.8 GB	Q8_0	Comfortable
296 tok/s 178–473 · low confidence	H100 CNX NVIDIA	80 GB	2,040 GB/s	Mar 2023	3.8 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
Organisation type: Industry
Country: United States of America
Published: 19 February 2025
Authors: Omar Sanseviero, Andreas Steiner

What it does

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

Domain: Vision, Multimodal, Language
Task: Image captioning, Visual question answering, Object detection, Image segmentation, Object recognition, Character recognition (OCR)
Base model: Gemma 2 2B,SigLIP 400M

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: 2.9B
Training data: 256,000,000,000 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: 4 × 10²² FLOP
How it was established: Hardware,Operation counting
Fine-tuning compute: 4.3 × 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 v5e
Chips used: 256
Wall-clock time: 72 hours
Power draw: 113.1 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 (non-commercial)
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: Introducing PaliGemma 2 mix: A vision-language model for multiple tasks
Last updated: 28 November 2025

The extremes

The ten fastest GPUs that run PaliGemma 2 3B Mix 224

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 PaliGemma 2 3B Mix 224

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

Tesla C1080

Memory needed

3.1 GB

Fastest

1,160 tok/s

PaliGemma 2 3B Mix 224 is small enough at 2.9B parameters that hardware is rarely the obstacle — 818 of the cards we track can run it, including cards several years old.

At the low end, a Tesla C1080 handles it — 4 GB, at Q6_K, for about 18.3 tokens per second.

The quickest result comes from a B200 at around 1,160 tokens per second — its 8,000 GB/s of bandwidth is what buys that.

Where it came from

PaliGemma 2 3B Mix 224 was published by Google, in United States of America, in February 2025. industry is the category the publisher falls under.

It works in Vision, Multimodal, Language, and is recorded as doing image captioning, Visual question answering, Object detection, Image segmentation, Object recognition, Character recognition (OCR).

It builds on Gemma 2 2B,SigLIP 400M, which is why it shares that model's general shape and size.

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. It is published under the google organisation on Hugging Face.

Understanding the speeds

The median result is around 36.8 tokens per second; 783 cards produce text faster than most people read it.

Every weight participates in every token here, so bandwidth is the whole story: the ranking below is effectively a ranking of memory throughput.

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.

How it was trained

Training it took roughly 4 × 10²² FLOP of computation, on Google TPU v5e — a measure of what producing the model cost, not of how fast it answers.

It was trained on about 256,000,000,000 tokens of text.

Step by step

How to choose a GPU for PaliGemma 2 3B Mix 224

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 PaliGemma 2 3B Mix 224 — around 3.1 GB at Q6_K. That figure, not the card's headline performance, is what decides whether it runs.
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 PaliGemma 2 3B Mix 224 can slip off a card that handles short questions easily.
03

Set a quality floor

The quantisation column varies by card, because a bigger card holds a more accurate copy of PaliGemma 2 3B Mix 224 — Q6_K on the smallest card that fits. Set a floor to hold the comparison at one level.
04

Compare tokens per second, not specifications

The speed ordering for PaliGemma 2 3B Mix 224 is effectively an ordering by memory bandwidth, which is why the B200 tops it at 1,160 tok/s.
05

Read the fit column last

Tight means PaliGemma 2 3B Mix 224 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

Open the card you have settled on

Following a card through to its own page shows every other model it can hold, which is the question that follows once PaliGemma 2 3B Mix 224 is settled.

Answers

PaliGemma 2 3B Mix 224 — common questions

Who created PaliGemma 2 3B Mix 224?

PaliGemma 2 3B Mix 224 was published by Google, based in United States of America, categorised as industry.

When was PaliGemma 2 3B Mix 224 released?

PaliGemma 2 3B Mix 224 was published in February 2025.

What is PaliGemma 2 3B Mix 224 used for?

PaliGemma 2 3B Mix 224 works in Vision, Multimodal, Language, and is recorded as handling image captioning, Visual question answering, Object detection, Image segmentation, Object recognition, Character recognition (OCR). 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 PaliGemma 2 3B Mix 224?

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 PaliGemma 2 3B Mix 224?

Around 4 × 10²² FLOP, on Google TPU v5e. 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 PaliGemma 2 3B Mix 224 if it does not fit in my GPU?

It can be split between the card and system memory, but PaliGemma 2 3B Mix 224 generates painfully slowly that way. Nothing on this page assumes offloading.

Would two GPUs run PaliGemma 2 3B Mix 224 faster?

Two cards buy memory rather than speed. That matters for PaliGemma 2 3B Mix 224 only if one card cannot hold it — 818 can, so a second adds little.

Why does the quantisation differ between cards for PaliGemma 2 3B Mix 224?

Because capacity varies, so does how hard PaliGemma 2 3B Mix 224 has to be squeezed — 2 distinct levels appear in the table above. Set a minimum quality to compare at one.

How accurate are these PaliGemma 2 3B Mix 224 speed estimates?

Every figure is derived from memory bandwidth and model size, not benchmarked. That is why each is published as a range such as 696–1,857 tok/s on the B200 rather than a single number.

What GPU do I need to run PaliGemma 2 3B Mix 224?

The smallest card in our catalogue that holds PaliGemma 2 3B Mix 224 is the Tesla C1080, with 4 GB of memory. It runs the model at Q6_K using about 3.1 GB, and produces roughly 18.3 tokens per second. 818 cards in total can run it.

How fast is PaliGemma 2 3B Mix 224 on a GPU?

It depends on the card. The quickest we calculate is a B200 at about 1,160 tokens per second; the slowest that still runs it manages considerably less. Reading speed is around ten tokens per second, and 783 of the cards that can run PaliGemma 2 3B Mix 224 clear that.

How much VRAM does PaliGemma 2 3B Mix 224 need?

About 3.1 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 PaliGemma 2 3B Mix 224 on a 8 GB GPU?

Yes. A CMP 170HX 8 GB with 8 GB runs it at Q8_0, using about 3.8 GB and generating roughly 216 tokens per second — a comfortable fit.

Can I run PaliGemma 2 3B Mix 224 on a 12 GB GPU?

Yes. A GeForce RTX 3080 Ti with 12 GB runs it at Q8_0, using about 3.8 GB and generating roughly 132 tokens per second — a comfortable fit.

Can I run PaliGemma 2 3B Mix 224 on a 16 GB GPU?

Yes. A Tesla V100 SXM2 16 GB with 16 GB runs it at Q8_0, using about 3.8 GB and generating roughly 164 tokens per second — a comfortable fit.

Can I run PaliGemma 2 3B Mix 224 on a 24 GB GPU?

Yes. A GeForce RTX 5090 D V2 with 24 GB runs it at Q8_0, using about 3.8 GB and generating roughly 194 tokens per second — a comfortable fit.

Is PaliGemma 2 3B Mix 224 open source?

Its weights are published, so PaliGemma 2 3B Mix 224 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 PaliGemma 2 3B Mix 224 have?

PaliGemma 2 3B Mix 224 has 2.9B parameters. https://huggingface.co/google/paligemma-3b-mix-224. 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.

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