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 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 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 that run 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

Gemma-SEA-LION-v4-27B-IT reaches a parameter count of 27B. That lands in the range a serious desktop card can handle once the weights are compressed. The number of cards we track that can run it: 241.

At the low end it is handled by Xeon Phi 7120P, with a memory capacity of 16 GB, running it at a compression of Q3_K_M and producing around 9.7 tokens per second.

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

Background

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

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

Rather than being trained from scratch, it is derived from Gemma 3 27B. That 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. On Hugging Face it is published under the organisation aisingapore.

Reading the throughput figures

Across every card that can run it, the middle of the range sits at 19.0 tokens per second. Exceeding reading speed outright: 196 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.

What went into building it

Training it took a computation budget of roughly 2.3 × 10²⁴ FLOP, on hardware recorded as NVIDIA H200 SXM. That figure measures what producing the model cost, and has no bearing on how fast it answers.

It was trained on a corpus of 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

    Start from what it actually needs, which is the requirement of Gemma-SEA-LION-v4-27B-IT, needing around 13.3 GB at a compression of Q3_K_M. Capacity is the gate — a card either holds it or it does not.

  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 a model fit smaller cards, at some cost in accuracy, 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.

  4. 04

    Rank by throughput rather than spec sheet

    Ranking by tokens per second follows memory bandwidth rather than core counts, for Gemma-SEA-LION-v4-27B-IT. It will not match a gaming ordering, because generation is bound by memory bandwidth. The card topping the list is B200, at 125 tok/s.

  5. 05

    Read the fit column last

    Tight means it loads and works with no room to raise the context later, in the case of Gemma-SEA-LION-v4-27B-IT. 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.

  6. 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-SEA-LION-v4-27B-IT.

Answers

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

01

Gemma-SEA-LION-v4-27B-IT— what is it used for?

It works in the domain of Multimodal, Language, Vision, and is recorded as handling the task of 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

Gemma-SEA-LION-v4-27B-IT— where can I download it?

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

03

Gemma-SEA-LION-v4-27B-IT— how much compute was used to train it?

Training consumed around 2.3 × 10²⁴ FLOP, on hardware recorded as 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

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

It can be split between the card and system memory, but it generates painfully slowly that way. The nearest miss we calculate falls short by 5.6 GB. Every figure here assumes the whole model is resident on the card.

05

Gemma-SEA-LION-v4-27B-IT— would two GPUs run it faster?

Two cards buy memory rather than speed, which matters only if one card cannot hold it. The number that can: 241. So a second card is rarely the answer here.

06

Gemma-SEA-LION-v4-27B-IT— why does the quantisation differ between cards?

A larger card holds a more accurate copy. The number of compression levels used across the cards that run it: 5. Bigger cards get the more accurate version, and the quality floor above pins the comparison to one level.

07

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

These are estimates with real error bars, and any of them could reasonably land anywhere in its published range depending on which runtime you use. The fastest result here: 107–151 tok/s on B200. The same model and card vary by thirty to fifty per cent depending on the inference software and its version.

08

Gemma-SEA-LION-v4-27B-IT— what GPU do I need to run it?

The smallest card in our catalogue that holds it is Xeon Phi 7120P, with a memory capacity of 16 GB. It runs the model at a compression of Q3_K_M using about 13.3 GB, and produces roughly 9.7 tokens per second. The number of cards able to run it in total: 241.

09

Gemma-SEA-LION-v4-27B-IT— how fast is it on a GPU?

It depends on the card. The quickest we calculate is 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 the number of cards clearing that: 196.

10

Gemma-SEA-LION-v4-27B-IT— how much VRAM does it need?

It needs about 13.3 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.

11

Gemma-SEA-LION-v4-27B-IT— 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 Q3_K_M, using about 13.3 GB and generating roughly 47.8 tokens per second. The fit is tight.

12

Gemma-SEA-LION-v4-27B-IT— 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 Q5_K_M, using about 19.5 GB and generating roughly 37.5 tokens per second. The fit is tight.

13

Gemma-SEA-LION-v4-27B-IT— 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.

14

Gemma-SEA-LION-v4-27B-IT— how many parameters does it have?

It has a parameter count of 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.

15

Gemma-SEA-LION-v4-27B-IT— who created it?

It was published by AI Singapore, based in Singapore, an organisation categorised as government.

16

Gemma-SEA-LION-v4-27B-IT— when was it released?

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