Gemma-SEA-LION-v4-27B-IT TPS calculator

Open weights AI Singapore 27B parameters August 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 of 818 cards that can run it

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 Gemma-SEA-LION-v4-27B-IT?

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

107–151

B200 NVIDIA 180 GB 8,000 GB/s Jan 2024 29.0 GB Q8_0 Comfortable
125 tok/s

107–151

B300 NVIDIA 288 GB 8,000 GB/s Sep 2025 29.0 GB Q8_0 Comfortable
100 tok/s

60–160 · low confidence

Radeon Instinct MI350X AMD 288 GB 8,190 GB/s Jan 2025 29.0 GB Q8_0 Comfortable
100 tok/s

60–160 · low confidence

Radeon Instinct MI355X AMD 288 GB 8,190 GB/s Jan 2025 29.0 GB Q8_0 Comfortable
80.1 tok/s

48–128 · low confidence

Radeon Instinct MI300 AMD 128 GB 6,550 GB/s Jan 2023 29.0 GB Q8_0 Comfortable
76.7 tok/s

65–92

H200 NVL NVIDIA 141 GB 4,890 GB/s Nov 2024 29.0 GB Q8_0 Comfortable
76.7 tok/s

65–92

H200 SXM 141 GB NVIDIA 141 GB 4,890 GB/s Nov 2024 29.0 GB Q8_0 Comfortable
73.4 tok/s

44–117 · low confidence

Radeon Instinct MI325X AMD 256 GB 6,000 GB/s Oct 2024 29.0 GB Q8_0 Comfortable
65.2 tok/s

39–104 · low confidence

Radeon Instinct MI300A AMD 128 GB 5,325 GB/s Dec 2023 29.0 GB Q8_0 Comfortable
65.2 tok/s

39–104 · low confidence

Radeon Instinct MI300X AMD 192 GB 5,325 GB/s Dec 2023 29.0 GB Q8_0 Comfortable
65.2 tok/s

39–104 · low confidence

Radeon Instinct MI308X AMD 192 GB 5,325 GB/s Dec 2023 29.0 GB Q8_0 Comfortable
61.8 tok/s

53–74

H100 NVL 94 GB NVIDIA 94 GB 3,940 GB/s Mar 2023 29.0 GB Q8_0 Comfortable
52.7 tok/s

45–63

H100 PCIe 96 GB NVIDIA 96 GB 3,360 GB/s Mar 2023 29.0 GB Q8_0 Comfortable
52.7 tok/s

45–63

H100 SXM5 80 GB NVIDIA 80 GB 3,360 GB/s Oct 2022 29.0 GB Q8_0 Comfortable
52.7 tok/s

45–63

H100 SXM5 94 GB NVIDIA 94 GB 3,360 GB/s Mar 2023 29.0 GB Q8_0 Comfortable
52.7 tok/s

45–63

H100 SXM5 96 GB NVIDIA 96 GB 3,360 GB/s Mar 2023 29.0 GB Q8_0 Comfortable
52.7 tok/s

45–63

H800 SXM5 NVIDIA 80 GB 3,360 GB/s Mar 2023 29.0 GB Q8_0 Comfortable
47.8 tok/s

41–57

Tesla V100 SXM2 16 GB NVIDIA 16 GB 1,130 GB/s Nov 2019 13.3 GB Q3_K_M Tight
42.6 tok/s

36–51

DRIVE A100 PROD NVIDIA 32 GB 1,870 GB/s May 2020 22.7 GB Q6_K Comfortable
42.6 tok/s

36–51

GRID A100A NVIDIA 32 GB 1,870 GB/s May 2020 22.7 GB Q6_K Comfortable
40.8 tok/s

35–49

GeForce RTX 5090 NVIDIA 32 GB 1,790 GB/s Jan 2025 22.7 GB Q6_K Comfortable
40.8 tok/s

35–49

GeForce RTX 5090 D NVIDIA 32 GB 1,790 GB/s Jan 2025 22.7 GB Q6_K Comfortable
40.6 tok/s

35–49

GeForce RTX 5080 NVIDIA 16 GB 960 GB/s Jan 2025 13.3 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 29.0 GB Q8_0 Comfortable
40.1 tok/s

24–64 · low confidence

Radeon Instinct MI250X AMD 128 GB 3,280 GB/s Nov 2021 29.0 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
AI Singapore
Organisation type
Government
Country
Singapore
Published
20 August 2025
Authors
Antonyrex Sajeban, Chan Hok Teng Adwin, Cheng Zi Yi Nicholas, Choa Hsueh Mei Esther, Heng Jonathan, Huang Yuli, Hulagadri Adithya Venkatadri, Jann Railey Estrada Montalan, Kang Siow Wei Bryan, Lau Wayne, Lee Chwan Ren, Leong Wai Yi, Leong Wei Qi, Limkonchotiwat Peerat, Muhammad Ridzuan Bin Mokhtar, Nagarajan Karthik, Ng Boon Cheong Raymond, Ngee Chia Tai, Ngui Jian Gang, Nguyen Thanh Ngan, Ong Jin…

What it does

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

Domain
Multimodal, Language, Vision
Task
Language modeling/generation, Question answering, Visual question answering
Base model
Gemma 3 27B
Numerical format
BF16

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
500,000,000,000 tokens

"The training corpus for SEA-LION v4 amounts to 500 billion 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
2.3 × 10²⁴ FLOP

2.268e+24 FLOP [base model] + 8.1e+22 FLOP = 2.349e+24 FLOP

How it was established
Operation counting
Fine-tuning compute
8.1 × 10²² FLOP

6 FLOP/parameter/token * 27000000000 parameters * 500000000000 tokens = 8.1e+22 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
NVIDIA H200 SXM
Data centre
Cloud Provider: SMC H200

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
Open source

License: Gemma Terms of Use https://huggingface.co/aisingapore/Gemma-SEA-LION-v4-27B

Hugging Face
aisingapore

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
SEA-LION v4
Last updated
28 November 2025

The extremes

The ten fastest GPUs for Gemma-SEA-LION-v4-27B-IT

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 Gemma-SEA-LION-v4-27B-IT

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 13.3 GB · Q3_K_M · tight 8.5 tok/s
  2. 02 Radeon RX 7700 16 GB · needs 13.3 GB · Q3_K_M · tight 20.5 tok/s
  3. 03 Arc Pro B50 16 GB · needs 13.3 GB · Q3_K_M · tight 6.2 tok/s
  4. 04 RTX PRO 2000 Blackwell 16 GB · needs 13.3 GB · Q3_K_M · tight 12.2 tok/s
  5. 05 Ryzen Z2 Extreme GPU 16 GB · needs 13.3 GB · Q3_K_M · tight 4.2 tok/s
  6. 06 Radeon RX 9060 XT 16 GB 16 GB · needs 13.3 GB · Q3_K_M · tight 10.6 tok/s
  7. 07 GeForce RTX 5060 Ti 16 GB 16 GB · needs 13.3 GB · Q3_K_M · tight 19.0 tok/s
  8. 08 GeForce RTX 5080 Mobile 16 GB · needs 13.3 GB · Q3_K_M · tight 37.9 tok/s
  9. 09 Radeon RX 9070 16 GB · needs 13.3 GB · Q3_K_M · tight 21.3 tok/s
  10. 10 Radeon RX 9070 XT 16 GB · needs 13.3 GB · Q3_K_M · tight 21.3 tok/s

What the numbers mean

The hardware side

Minimum card

Xeon Phi 7120P

Memory needed

13.3 GB

Fastest

125 tok/s

With 27B parameters, Gemma-SEA-LION-v4-27B-IT 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

Gemma-SEA-LION-v4-27B-IT was published by AI Singapore, in Singapore, in August 2025. government is the category the publisher falls under.

It works in Multimodal, Language, Vision, and is recorded as doing language modeling/generation, Question answering, Visual question answering.

It is derived from Gemma 3 27B rather than trained from scratch, which is the usual way a specialised model is produced.

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 aisingapore 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.

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.

What went into building it

Training it took roughly 2.3 × 10²⁴ FLOP of computation, on NVIDIA H200 SXM — a measure of what producing the model cost, not of how fast it answers.

It was trained on about 500,000,000,000 tokens of text.

Step by step

How to choose a GPU for Gemma-SEA-LION-v4-27B-IT

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

    Look at what Gemma-SEA-LION-v4-27B-IT actually needs — around 13.3 GB at Q3_K_M. No amount of processing power compensates for a card that cannot hold it.

  2. 02

    Set the context length you will work at

    Longer conversations cost memory on top of what the weights need. Move the slider to your real working length before trusting any row for Gemma-SEA-LION-v4-27B-IT.

  3. 03

    Choose how far you will compress it

    Compression is what makes Gemma-SEA-LION-v4-27B-IT 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

    Rank by throughput rather than spec sheet

    Ranking by tokens per second for Gemma-SEA-LION-v4-27B-IT follows memory bandwidth, not core counts, which is why the B200 tops it at 125 tok/s.

  5. 05

    Read the fit column last

    Tight means Gemma-SEA-LION-v4-27B-IT 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.

  6. 06

    See what else that card runs

    Each card page repeats this sweep for every model we hold. It answers what else the hardware is good for, beyond Gemma-SEA-LION-v4-27B-IT.

Answers

Gemma-SEA-LION-v4-27B-IT — common questions

01

What is Gemma-SEA-LION-v4-27B-IT used for?

Gemma-SEA-LION-v4-27B-IT works in Multimodal, Language, Vision, and is recorded as handling language modeling/generation, Question answering, Visual question answering. 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.

02

Where can I download Gemma-SEA-LION-v4-27B-IT?

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

03

How much compute was used to train Gemma-SEA-LION-v4-27B-IT?

Around 2.3 × 10²⁴ FLOP, on NVIDIA H200 SXM. 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.

04

Can I run Gemma-SEA-LION-v4-27B-IT if it does not fit in my GPU?

It can be split between the card and system memory, but Gemma-SEA-LION-v4-27B-IT generates painfully slowly that way — the nearest miss we calculate is short by 5.6 GB. Nothing on this page assumes offloading.

05

Would two GPUs run Gemma-SEA-LION-v4-27B-IT faster?

Two cards buy memory rather than speed. That matters for Gemma-SEA-LION-v4-27B-IT only if one card cannot hold it — 241 can, so a second adds little.

06

Why does the quantisation differ between cards for Gemma-SEA-LION-v4-27B-IT?

A larger card holds a more accurate copy. Across the cards that run Gemma-SEA-LION-v4-27B-IT, 5 compression levels are used; the floor control above pins it to one.

07

How accurate are these Gemma-SEA-LION-v4-27B-IT speed estimates?

These are estimates with real error bars. The fastest result here, 107–151 tok/s on the B200, could reasonably land anywhere in its published range depending on which runtime you use.

08

What GPU do I need to run Gemma-SEA-LION-v4-27B-IT?

The smallest card in our catalogue that holds Gemma-SEA-LION-v4-27B-IT is the Xeon Phi 7120P, with 16 GB of memory. It runs the model at Q3_K_M using about 13.3 GB, and produces roughly 9.7 tokens per second. 241 cards in total can run it.

09

How fast is Gemma-SEA-LION-v4-27B-IT 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 Gemma-SEA-LION-v4-27B-IT clear that.

10

How much VRAM does Gemma-SEA-LION-v4-27B-IT need?

About 13.3 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.

11

Can I run Gemma-SEA-LION-v4-27B-IT on a 16 GB GPU?

Yes. A Tesla V100 SXM2 16 GB with 16 GB runs it at Q3_K_M, using about 13.3 GB and generating roughly 47.8 tokens per second — a tight fit.

12

Can I run Gemma-SEA-LION-v4-27B-IT on a 24 GB GPU?

Yes. A GeForce RTX 5090 D V2 with 24 GB runs it at Q5_K_M, using about 19.5 GB and generating roughly 37.5 tokens per second — a tight fit.

13

Is Gemma-SEA-LION-v4-27B-IT open source?

Its weights are published, so Gemma-SEA-LION-v4-27B-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.

14

How many parameters does Gemma-SEA-LION-v4-27B-IT have?

Gemma-SEA-LION-v4-27B-IT has 27B parameters. 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.

15

Who created Gemma-SEA-LION-v4-27B-IT?

Gemma-SEA-LION-v4-27B-IT was published by AI Singapore, based in Singapore, categorised as government.

16

When was Gemma-SEA-LION-v4-27B-IT released?

Gemma-SEA-LION-v4-27B-IT was published in August 2025.

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