MedGemma 27B TPS calculator

Open weights Google 27B parameters May 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 MedGemma 27B?

Set the inputs, read the answer

A longer conversation needs more memory, which can push this model off smaller cards.

Hides cards that would only fit the model by compressing it below this point.

241 cards match

Calculating
Needs Quantisation Fit
125 tok/s

75–201 · low confidence

B200 NVIDIA 180 GB 8,000 GB/s Jan 2024 29.6 GB Q8_0 Comfortable
125 tok/s

75–201 · low confidence

B300 NVIDIA 288 GB 8,000 GB/s Sep 2025 29.6 GB Q8_0 Comfortable
100 tok/s

60–160 · low confidence

Radeon Instinct MI350X AMD 288 GB 8,190 GB/s Jan 2025 29.6 GB Q8_0 Comfortable
100 tok/s

60–160 · low confidence

Radeon Instinct MI355X AMD 288 GB 8,190 GB/s Jan 2025 29.6 GB Q8_0 Comfortable
80.1 tok/s

48–128 · low confidence

Radeon Instinct MI300 AMD 128 GB 6,550 GB/s Jan 2023 29.6 GB Q8_0 Comfortable
76.7 tok/s

46–123 · low confidence

H200 NVL NVIDIA 141 GB 4,890 GB/s Nov 2024 29.6 GB Q8_0 Comfortable
76.7 tok/s

46–123 · low confidence

H200 SXM 141 GB NVIDIA 141 GB 4,890 GB/s Nov 2024 29.6 GB Q8_0 Comfortable
73.4 tok/s

44–117 · low confidence

Radeon Instinct MI325X AMD 256 GB 6,000 GB/s Oct 2024 29.6 GB Q8_0 Comfortable
65.2 tok/s

39–104 · low confidence

Radeon Instinct MI300A AMD 128 GB 5,325 GB/s Dec 2023 29.6 GB Q8_0 Comfortable
65.2 tok/s

39–104 · low confidence

Radeon Instinct MI300X AMD 192 GB 5,325 GB/s Dec 2023 29.6 GB Q8_0 Comfortable
65.2 tok/s

39–104 · low confidence

Radeon Instinct MI308X AMD 192 GB 5,325 GB/s Dec 2023 29.6 GB Q8_0 Comfortable
61.8 tok/s

37–99 · low confidence

H100 NVL 94 GB NVIDIA 94 GB 3,940 GB/s Mar 2023 29.6 GB Q8_0 Comfortable
52.7 tok/s

32–84 · low confidence

H100 PCIe 96 GB NVIDIA 96 GB 3,360 GB/s Mar 2023 29.6 GB Q8_0 Comfortable
52.7 tok/s

32–84 · low confidence

H100 SXM5 80 GB NVIDIA 80 GB 3,360 GB/s Oct 2022 29.6 GB Q8_0 Comfortable
52.7 tok/s

32–84 · low confidence

H100 SXM5 94 GB NVIDIA 94 GB 3,360 GB/s Mar 2023 29.6 GB Q8_0 Comfortable
52.7 tok/s

32–84 · low confidence

H100 SXM5 96 GB NVIDIA 96 GB 3,360 GB/s Mar 2023 29.6 GB Q8_0 Comfortable
52.7 tok/s

32–84 · low confidence

H800 SXM5 NVIDIA 80 GB 3,360 GB/s Mar 2023 29.6 GB Q8_0 Comfortable
47.8 tok/s

29–77 · low confidence

Tesla V100 SXM2 16 GB NVIDIA 16 GB 1,130 GB/s Nov 2019 13.9 GB Q3_K_M Tight
42.6 tok/s

26–68 · low confidence

DRIVE A100 PROD NVIDIA 32 GB 1,870 GB/s May 2020 23.3 GB Q6_K Comfortable
42.6 tok/s

26–68 · low confidence

GRID A100A NVIDIA 32 GB 1,870 GB/s May 2020 23.3 GB Q6_K Comfortable
40.8 tok/s

24–65 · low confidence

GeForce RTX 5090 NVIDIA 32 GB 1,790 GB/s Jan 2025 23.3 GB Q6_K Comfortable
40.8 tok/s

24–65 · low confidence

GeForce RTX 5090 D NVIDIA 32 GB 1,790 GB/s Jan 2025 23.3 GB Q6_K Comfortable
40.6 tok/s

24–65 · low confidence

GeForce RTX 5080 NVIDIA 16 GB 960 GB/s Jan 2025 13.9 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 29.6 GB Q8_0 Comfortable
40.1 tok/s

24–64 · low confidence

Radeon Instinct MI250X AMD 128 GB 3,280 GB/s Nov 2021 29.6 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
Organisation type
Industry
Country
United States of America
Published
20 May 2025
Authors
Andrew Sellergren, Sahar Kazemzadeh, Tiam Jaroensri, Atilla Kiraly, Madeleine Traverse, Timo Kohlberger, Shawn Xu, Fayaz Jamil, Cían Hughes, Charles Lau, Justin Chen, Fereshteh Mahvar, Liron Yatziv, Tiffany Chen, Bram Sterling, Stefanie Anna Baby, Susanna Maria Baby, Jeremy Lai, Samuel Schmidgall, Lu Yang, Kejia Chen, Per Bjornsson, Shashir Reddy, Ryan Brush, Kenneth Philbrick, Mercy Asiedu, Ines …

What it does

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

Domain
Medicine, Language, Vision, Multimodal
Task
Question answering, Language modeling/generation, Medical diagnosis, Visual question answering, Image classification
Base model
Gemma 3 27B,MedSigLIP

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

27B

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

health-ai-developer foundation https://huggingface.co/google/medgemma-27b-it

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
MedGemma Technical Report
Last updated
28 November 2025

The extremes

The ten fastest GPUs that run MedGemma 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.

  1. 01 B300 288 GB · 8,000 GB/s · Q8_0 125 tok/s
  2. 02 B200 180 GB · 8,000 GB/s · Q8_0 125 tok/s
  3. 03 Radeon Instinct MI350X 288 GB · 8,190 GB/s · Q8_0 100 tok/s
  4. 04 Radeon Instinct MI355X 288 GB · 8,190 GB/s · Q8_0 100 tok/s
  5. 05 Radeon Instinct MI300 128 GB · 6,550 GB/s · Q8_0 80.1 tok/s
  6. 06 H200 NVL 141 GB · 4,890 GB/s · Q8_0 76.7 tok/s
  7. 07 H200 SXM 141 GB 141 GB · 4,890 GB/s · Q8_0 76.7 tok/s
  8. 08 Radeon Instinct MI325X 256 GB · 6,000 GB/s · Q8_0 73.4 tok/s
  9. 09 Radeon Instinct MI300A 128 GB · 5,325 GB/s · Q8_0 65.2 tok/s
  10. 10 Radeon Instinct MI300X 192 GB · 5,325 GB/s · Q8_0 65.2 tok/s

The smallest GPUs that still run MedGemma 27B

The cheapest route in, by memory capacity. A tight fit runs the model but leaves nothing spare for a longer conversation.

  1. 01 Ryzen AI Z2 Extreme GPU 16 GB · needs 13.9 GB · Q3_K_M · tight 8.5 tok/s
  2. 02 Radeon RX 7700 16 GB · needs 13.9 GB · Q3_K_M · tight 20.5 tok/s
  3. 03 Arc Pro B50 16 GB · needs 13.9 GB · Q3_K_M · tight 6.2 tok/s
  4. 04 RTX PRO 2000 Blackwell 16 GB · needs 13.9 GB · Q3_K_M · tight 12.2 tok/s
  5. 05 Ryzen Z2 Extreme GPU 16 GB · needs 13.9 GB · Q3_K_M · tight 4.2 tok/s
  6. 06 Radeon RX 9060 XT 16 GB 16 GB · needs 13.9 GB · Q3_K_M · tight 10.6 tok/s
  7. 07 GeForce RTX 5060 Ti 16 GB 16 GB · needs 13.9 GB · Q3_K_M · tight 19.0 tok/s
  8. 08 GeForce RTX 5080 Mobile 16 GB · needs 13.9 GB · Q3_K_M · tight 37.9 tok/s
  9. 09 Radeon RX 9070 16 GB · needs 13.9 GB · Q3_K_M · tight 21.3 tok/s
  10. 10 Radeon RX 9070 XT 16 GB · needs 13.9 GB · Q3_K_M · tight 21.3 tok/s

What the numbers mean

Hardware requirements in practice

Minimum card

Xeon Phi 7120P

Memory needed

13.9 GB

Fastest

125 tok/s

With 27B parameters, MedGemma 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.

The entry point is the Xeon Phi 7120P: 16 GB of memory, Q3_K_M compression, roughly 9.7 tokens per second.

A B200 is the fastest we calculate for it: about 125 tokens per second, from 8,000 GB/s of memory bandwidth.

About this model

MedGemma 27B was published by Google, in United States of America, in May 2025. The organisation is categorised as industry.

It works in Medicine, Language, Vision, Multimodal, and is recorded as doing question answering, Language modeling/generation, Medical diagnosis, Visual question answering, Image classification.

Its starting point was Gemma 3 27B,MedSigLIP — 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.

How fast it runs, and why

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.

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.

Step by step

How to choose a GPU for MedGemma 27B

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

  1. 01

    Start from the memory column

    Every card here has been checked against MedGemma 27B — around 13.9 GB at Q3_K_M. Capacity is the gate — a card either holds it or it does not.

  2. 02

    Decide how long your conversations run

    Longer conversations cost memory on top of what the weights need. Move the slider to your real working length before trusting any row for MedGemma 27B.

  3. 03

    Set a quality floor

    Compression is what makes MedGemma 27B fit smaller cards, at some cost in accuracy — Q3_K_M on the smallest card that fits. A minimum quality removes the ones that go too far.

  4. 04

    Compare tokens per second, not specifications

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

  5. 05

    Check the fit verdict before buying

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

  6. 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 MedGemma 27B is settled.

Answers

MedGemma 27B — common questions

01

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

Yes. A GeForce RTX 5090 D V2 with 24 GB runs it at Q5_K_M, using about 20.2 GB and generating roughly 37.5 tokens per second — a tight fit.

02

Is MedGemma 27B open source?

Its weights are published, so MedGemma 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.

03

How many parameters does MedGemma 27B have?

MedGemma 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.

04

Who created MedGemma 27B?

MedGemma 27B was published by Google, based in United States of America, categorised as industry.

05

When was MedGemma 27B released?

MedGemma 27B was published in May 2025.

06

What is MedGemma 27B used for?

MedGemma 27B works in Medicine, Language, Vision, Multimodal, and is recorded as handling question answering, Language modeling/generation, Medical diagnosis, Visual question answering, Image classification. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.

07

Where can I download MedGemma 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.

08

Can I run MedGemma 27B if it does not fit in my GPU?

Only by offloading, which is usually a false economy: the part in system memory drags the whole thing down — the nearest miss we calculate is short by 6.2 GB. Our figures for MedGemma 27B assume it is fully resident.

09

Would two GPUs run MedGemma 27B faster?

Two cards buy memory rather than speed. That matters for MedGemma 27B only if one card cannot hold it — 241 can, so a second adds little.

10

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

Each card is shown running the least-compressed copy it can hold, and MedGemma 27B appears at 5 different compression levels across the cards that fit it. Bigger cards get the more accurate version.

11

How accurate are these MedGemma 27B speed estimates?

These are estimates with real error bars. The fastest result here, 75–201 tok/s on the B200, could reasonably land anywhere in its published range depending on which runtime you use.

12

What GPU do I need to run MedGemma 27B?

The smallest card in our catalogue that holds MedGemma 27B is the Xeon Phi 7120P, with 16 GB of memory. It runs the model at Q3_K_M using about 13.9 GB, and produces roughly 9.7 tokens per second. 241 cards in total can run it.

13

How fast is MedGemma 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 MedGemma 27B clear that.

14

How much VRAM does MedGemma 27B need?

About 13.9 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.

15

Can I run MedGemma 27B on a 16 GB GPU?

Yes. A Tesla V100 SXM2 16 GB with 16 GB runs it at Q3_K_M, using about 13.9 GB and generating roughly 47.8 tokens per second — a tight 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