Gemma 3 QAT 12B TPS calculator

Open weights Google DeepMind 12B 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

509 cards that can run it

818 cards we hold specifications for

Smallest card that fits

Xeon Phi 5110P

8 GB · Q3_K_M · 19.8 tok/s

Fastest card

B200

282 tok/s · 180 GB

Which GPUs can run Gemma 3 QAT 12B?

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

509 cards match

Calculating

					Needs	Quantisation	Fit
282 tok/s 240–339	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	13.6 GB	Q8_0	Comfortable
282 tok/s 240–339	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	13.6 GB	Q8_0	Comfortable
225 tok/s 135–361 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	13.6 GB	Q8_0	Comfortable
225 tok/s 135–361 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	13.6 GB	Q8_0	Comfortable
180 tok/s 108–289 · low confidence	Radeon Instinct MI300 AMD	128 GB	6,550 GB/s	Jan 2023	13.6 GB	Q8_0	Comfortable
173 tok/s 147–207	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	13.6 GB	Q8_0	Comfortable
173 tok/s 147–207	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	13.6 GB	Q8_0	Comfortable
165 tok/s 99–264 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	13.6 GB	Q8_0	Comfortable
147 tok/s 88–235 · low confidence	Radeon Instinct MI300A AMD	128 GB	5,325 GB/s	Dec 2023	13.6 GB	Q8_0	Comfortable
147 tok/s 88–235 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	13.6 GB	Q8_0	Comfortable
147 tok/s 88–235 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	13.6 GB	Q8_0	Comfortable
142 tok/s 121–170	CMP 170HX 8 GB NVIDIA	8 GB	1,490 GB/s	Sep 2021	6.6 GB	Q3_K_M	Tight
139 tok/s 118–167	H100 NVL 94 GB NVIDIA	94 GB	3,940 GB/s	Mar 2023	13.6 GB	Q8_0	Comfortable
127 tok/s 108–153	CMP 170HX 10 GB NVIDIA	10 GB	1,560 GB/s	Sep 2021	8.0 GB	Q4_K_M	Tight
119 tok/s 101–142	H100 PCIe 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	13.6 GB	Q8_0	Comfortable
119 tok/s 101–142	H100 SXM5 80 GB NVIDIA	80 GB	3,360 GB/s	Oct 2022	13.6 GB	Q8_0	Comfortable
119 tok/s 101–142	H100 SXM5 94 GB NVIDIA	94 GB	3,360 GB/s	Mar 2023	13.6 GB	Q8_0	Comfortable
119 tok/s 101–142	H100 SXM5 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	13.6 GB	Q8_0	Comfortable
119 tok/s 101–142	H800 SXM5 NVIDIA	80 GB	3,360 GB/s	Mar 2023	13.6 GB	Q8_0	Comfortable
90.3 tok/s 54–144 · low confidence	Radeon Instinct MI250 AMD	128 GB	3,280 GB/s	Nov 2021	13.6 GB	Q8_0	Comfortable
90.3 tok/s 54–144 · low confidence	Radeon Instinct MI250X AMD	128 GB	3,280 GB/s	Nov 2021	13.6 GB	Q8_0	Comfortable
75.3 tok/s 45–120 · low confidence	Data Center GPU Max 1550 Intel	128 GB	3,280 GB/s	Jan 2023	13.6 GB	Q8_0	Comfortable
73.6 tok/s 44–118 · low confidence	Data Center GPU Max Subsystem Intel	128 GB	3,210 GB/s	Jan 2023	13.6 GB	Q8_0	Comfortable
73.1 tok/s 62–88	RTX A5000-8Q NVIDIA	8 GB	768 GB/s	Apr 2021	6.6 GB	Q3_K_M	Tight
72.0 tok/s 61–86	A100 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Nov 2020	13.6 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: Google DeepMind
Organisation type: Industry
Country: United States of America
Published: 18 April 2025

What it does

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

Domain: Language, Vision, Multimodal
Task: Language modeling/generation, Question answering, Translation, Chat, Quantitative reasoning, Visual question answering, Code generation
Base model: Gemma 3 12B

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: 12B
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 (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: Gemma 3 QAT Models: Bringing state-of-the-Art AI to consumer GPUs
Last updated: 28 November 2025

The extremes

The ten fastest GPUs that run Gemma 3 QAT 12B

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 Gemma 3 QAT 12B

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 5110P

Memory needed

6.6 GB

Fastest

282 tok/s

Gemma 3 QAT 12B reaches a parameter count of 12B. That is small enough that hardware is rarely the obstacle, including on cards several years old. The number of cards we track that can run it: 509.

At the low end it is handled by Xeon Phi 5110P, with a memory capacity of 8 GB, running it at a compression of Q3_K_M and producing around 19.8 tokens per second.

The fastest we calculate for it is B200, generating roughly 282 tokens per second on the strength of a memory bandwidth of 8,000 GB/s.

Background

Gemma 3 QAT 12B was published by Google DeepMind, in the country recorded as United States of America, during April 2025. The publishing organisation is categorised as industry.

It works in the domain of Language, Vision, Multimodal, and is recorded as performing the task of language modeling/generation, Question answering, Translation, Chat, Quantitative reasoning, Visual question answering, Code generation.

It builds on Gemma 3 12B. That is the usual way a specialised model is produced.

Published weights mean the model runs on your machine rather than someone else's, which is what makes the hardware question below answerable at all. On Hugging Face it is published under the organisation google.

Reading the throughput figures

The median result is around 21.2 tokens per second. Exceeding reading speed outright: 455 of them.

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

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

Step by step

How to choose a GPU for Gemma 3 QAT 12B

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 Gemma 3 QAT 12B, needing around 6.6 GB at a compression of 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, because at long context a card that handles short questions easily can be dropped by Gemma 3 QAT 12B.
03

Set a quality floor

The quantisation column varies by card, because a bigger card holds a more accurate copy, 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

Rank by throughput rather than spec sheet

Sort by speed to see how cards rank for Gemma 3 QAT 12B. It will not match a gaming ordering, because generation is bound by memory bandwidth. The card topping the list is B200, at 282 tok/s.
05

Check the fit verdict before buying

The fit column separates cards that just manage it from those with room to spare, in the case of Gemma 3 QAT 12B. 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

See what else that card runs

Each card page repeats this sweep for every model we hold, answering what else the hardware is good for beyond Gemma 3 QAT 12B.

Answers

Gemma 3 QAT 12B — common questions

Gemma 3 QAT 12B— 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 Q8_0, using about 13.6 GB and generating roughly 47.3 tokens per second. The fit is comfortable.

Gemma 3 QAT 12B— 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.

Gemma 3 QAT 12B— how many parameters does it have?

It has a parameter count of 12B. 12B. 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.

Gemma 3 QAT 12B— who created it?

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

Gemma 3 QAT 12B— when was it released?

It was published in April 2025.

Gemma 3 QAT 12B— what is it used for?

It works in the domain of Language, Vision, Multimodal, and is recorded as handling the task of language modeling/generation, Question answering, Translation, Chat, Quantitative reasoning, Visual question answering, Code generation. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.

Gemma 3 QAT 12B— where can I download it?

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

Gemma 3 QAT 12B— 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 2.6 GB. Every figure here assumes the whole model is resident on the card.

Gemma 3 QAT 12B— 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: 509. So a second card is rarely the answer here.

Gemma 3 QAT 12B— 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: 4. Bigger cards get the more accurate version, and the quality floor above pins the comparison to one level.

Gemma 3 QAT 12B— how accurate are these speed estimates?

Every figure is derived from memory bandwidth and model size, not benchmarked, which is why each is published as a range rather than a single number. One example: 240–339 tok/s on B200. The same model and card vary by thirty to fifty per cent depending on the inference software and its version.

Gemma 3 QAT 12B— what GPU do I need to run it?

The smallest card in our catalogue that holds it is Xeon Phi 5110P, with a memory capacity of 8 GB. It runs the model at a compression of Q3_K_M using about 6.6 GB, and produces roughly 19.8 tokens per second. The number of cards able to run it in total: 509.

Gemma 3 QAT 12B— how fast is it on a GPU?

It depends on the card. The quickest we calculate is B200, at about 282 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: 455.

Gemma 3 QAT 12B— how much VRAM does it need?

It needs about 6.6 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.

Gemma 3 QAT 12B— can I run it on a GPU holding 8 GB?

Yes. The card CMP 170HX 8 GB, holding 8 GB, runs it at a compression of Q3_K_M, using about 6.6 GB and generating roughly 142 tokens per second. The fit is tight.

Gemma 3 QAT 12B— can I run it on a GPU holding 12 GB?

Yes. The card GeForce RTX 3080 Ti, holding 12 GB, runs it at a compression of Q5_K_M, using about 9.4 GB and generating roughly 57.5 tokens per second. The fit is tight.

Gemma 3 QAT 12B— 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 Q8_0, using about 13.6 GB and generating roughly 39.9 tokens per second. The fit is tight.

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