SEA-LION V3 Llama3.1 70B TPS calculator

Open weights AI Singapore 70B parameters December 2024

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

61 cards that can run it

818 cards we hold specifications for

Smallest card that fits

A100 PCIe 40 GB

40 GB · Q3_K_M · 25.5 tok/s

Fastest card

B200

48.4 tok/s · 180 GB

Which GPUs can run SEA-LION V3 Llama3.1 70B?

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.

61 cards match

Calculating
Needs Quantisation Fit
48.4 tok/s

41–58

B200 NVIDIA 180 GB 8,000 GB/s Jan 2024 73.8 GB Q8_0 Comfortable
48.4 tok/s

41–58

B300 NVIDIA 288 GB 8,000 GB/s Sep 2025 73.8 GB Q8_0 Comfortable
38.7 tok/s

23–62 · low confidence

Radeon Instinct MI350X AMD 288 GB 8,190 GB/s Jan 2025 73.8 GB Q8_0 Comfortable
38.7 tok/s

23–62 · low confidence

Radeon Instinct MI355X AMD 288 GB 8,190 GB/s Jan 2025 73.8 GB Q8_0 Comfortable
30.9 tok/s

19–49 · low confidence

Radeon Instinct MI300 AMD 128 GB 6,550 GB/s Jan 2023 73.8 GB Q8_0 Comfortable
29.6 tok/s

25–36

H200 NVL NVIDIA 141 GB 4,890 GB/s Nov 2024 73.8 GB Q8_0 Comfortable
29.6 tok/s

25–36

H200 SXM 141 GB NVIDIA 141 GB 4,890 GB/s Nov 2024 73.8 GB Q8_0 Comfortable
29.5 tok/s

25–35

H100 SXM5 80 GB NVIDIA 80 GB 3,360 GB/s Oct 2022 57.5 GB Q6_K Comfortable
29.5 tok/s

25–35

H800 SXM5 NVIDIA 80 GB 3,360 GB/s Mar 2023 57.5 GB Q6_K Comfortable
28.3 tok/s

17–45 · low confidence

Radeon Instinct MI325X AMD 256 GB 6,000 GB/s Oct 2024 73.8 GB Q8_0 Comfortable
26.1 tok/s

22–31

GRID A100B NVIDIA 48 GB 1,870 GB/s May 2020 41.2 GB Q4_K_M Tight
25.5 tok/s

22–31

A100 PCIe 40 GB NVIDIA 40 GB 1,560 GB/s Jun 2020 33.0 GB Q3_K_M Tight
25.5 tok/s

22–31

A100 SXM4 40 GB NVIDIA 40 GB 1,560 GB/s May 2020 33.0 GB Q3_K_M Tight
25.5 tok/s

22–31

A800 PCIe 40 GB NVIDIA 40 GB 1,560 GB/s Nov 2022 33.0 GB Q3_K_M Tight
25.1 tok/s

15–40 · low confidence

Radeon Instinct MI300A AMD 128 GB 5,325 GB/s Dec 2023 73.8 GB Q8_0 Comfortable
25.1 tok/s

15–40 · low confidence

Radeon Instinct MI300X AMD 192 GB 5,325 GB/s Dec 2023 73.8 GB Q8_0 Comfortable
25.1 tok/s

15–40 · low confidence

Radeon Instinct MI308X AMD 192 GB 5,325 GB/s Dec 2023 73.8 GB Q8_0 Comfortable
23.8 tok/s

20–29

H100 NVL 94 GB NVIDIA 94 GB 3,940 GB/s Mar 2023 73.8 GB Q8_0 Tight
20.3 tok/s

17–24

H100 PCIe 96 GB NVIDIA 96 GB 3,360 GB/s Mar 2023 73.8 GB Q8_0 Tight
20.3 tok/s

17–24

H100 SXM5 94 GB NVIDIA 94 GB 3,360 GB/s Mar 2023 73.8 GB Q8_0 Tight
20.3 tok/s

17–24

H100 SXM5 96 GB NVIDIA 96 GB 3,360 GB/s Mar 2023 73.8 GB Q8_0 Tight
18.7 tok/s

16–22

RTX PRO 5000 Blackwell NVIDIA 48 GB 1,340 GB/s Mar 2025 41.2 GB Q4_K_M Tight
17.9 tok/s

15–22

A100 SXM4 80 GB NVIDIA 80 GB 2,040 GB/s Nov 2020 57.5 GB Q6_K Comfortable
17.9 tok/s

15–22

A100X NVIDIA 80 GB 2,040 GB/s Jun 2021 57.5 GB Q6_K Comfortable
17.9 tok/s

15–22

A800 SXM4 80 GB NVIDIA 80 GB 2,040 GB/s Aug 2022 57.5 GB Q6_K 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
19 December 2024
Authors
AI Singapore

What it does

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

Domain
Language
Task
Question answering, Chat, Language modeling/generation
Approach
Self-supervised learning
Base model
Llama 3.1-70B
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
70B
Training data
200,000,000,000 tokens

"pre-trained on 200B 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
8 × 10²⁴ FLOP

Llama3.1 70B base model: 7.929e+24 Additional pretraining compute: Stage 1: 200*60*60*989500000000000*64*0.3=1.36788×10^22 Stage 2: 495*60*60*989500000000000*128*0.3=6.77103×10^22 Total: 7.929×10^24 + 1.36788×10^22 + 6.77103×10^22 = 8.0103891 × 10^24

How it was established
Hardware,Operation counting
Fine-tuning compute
8.3 × 10²² FLOP

Additional pretraining compute: Stage 1: 200 hour * 3600 sec / hour * 989500000000000 FLOP / GPU / sec * 64 GPUs * 0.3 [assumed utilization] = 1.36788×10^22 FLOP Stage 2: 495 hours * 3600 sec / hour * 989500000000000 FLOP / GPU /sec * 128 GPUs * 0.3 [assumed utilization] = 6.77103×10^22 FLOP 1.36788×10^22 FLOP + 6.77103×10^22 FLOP = 8.13891e+22 FLOP 6 FLOP / parameter / token * 70*10^9 parameters * 200*10^9 tokens = 8.4e+22 FLOP sqrt(8.13891e+22*8.4e+22) = 8.2684245e+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,NVIDIA H100 SXM5 80GB
Chips used
192
Wall-clock time
136 hours

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

Llama 3.1 license (branding requirements, size cap 700M MAU) https://huggingface.co/aisingapore/Llama-SEA-LION-v3-70B https://github.com/aisingapore/sealion

Hugging Face
aisingapore

How it is classified

Labels the source dataset applies when tracking notable models, and how confident it is in the entry.

Likely above 10²³ FLOP
Yes
Record confidence
Confident

Sources

Where this record came from and when it was last checked.

Reference
SEA-LION V3
Last updated
28 November 2025

The extremes

The ten fastest GPUs that run SEA-LION V3 Llama3.1 70B

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 48.4 tok/s
  2. 02 B200 180 GB · 8,000 GB/s · Q8_0 48.4 tok/s
  3. 03 Radeon Instinct MI350X 288 GB · 8,190 GB/s · Q8_0 38.7 tok/s
  4. 04 Radeon Instinct MI355X 288 GB · 8,190 GB/s · Q8_0 38.7 tok/s
  5. 05 Radeon Instinct MI300 128 GB · 6,550 GB/s · Q8_0 30.9 tok/s
  6. 06 H200 NVL 141 GB · 4,890 GB/s · Q8_0 29.6 tok/s
  7. 07 H200 SXM 141 GB 141 GB · 4,890 GB/s · Q8_0 29.6 tok/s
  8. 08 H800 SXM5 80 GB · 3,360 GB/s · Q6_K 29.5 tok/s
  9. 09 H100 SXM5 80 GB 80 GB · 3,360 GB/s · Q6_K 29.5 tok/s
  10. 10 Radeon Instinct MI325X 256 GB · 6,000 GB/s · Q8_0 28.3 tok/s

The smallest GPUs that still run SEA-LION V3 Llama3.1 70B

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

  1. 01 A800 PCIe 40 GB 40 GB · needs 33.0 GB · Q3_K_M · tight 25.5 tok/s
  2. 02 A100 PCIe 40 GB 40 GB · needs 33.0 GB · Q3_K_M · tight 25.5 tok/s
  3. 03 A100 SXM4 40 GB 40 GB · needs 33.0 GB · Q3_K_M · tight 25.5 tok/s
  4. 04 Radeon PRO W7900D 48 GB · needs 41.2 GB · Q4_K_M · tight 9.4 tok/s
  5. 05 RTX PRO 5000 Blackwell 48 GB · needs 41.2 GB · Q4_K_M · tight 18.7 tok/s
  6. 06 RTX 5880 Ada Generation 48 GB · needs 41.2 GB · Q4_K_M · tight 12.1 tok/s
  7. 07 L20 48 GB · needs 41.2 GB · Q4_K_M · tight 12.1 tok/s
  8. 08 Radeon PRO W7800 48 GB 48 GB · needs 41.2 GB · Q4_K_M · tight 9.4 tok/s
  9. 09 Radeon PRO W7900 48 GB · needs 41.2 GB · Q4_K_M · tight 9.4 tok/s
  10. 10 Data Center GPU Max 1100 48 GB · needs 41.2 GB · Q4_K_M · tight 11.2 tok/s

What the numbers mean

What you need to run it

Minimum card

A100 PCIe 40 GB

Memory needed

33.0 GB

Fastest

48.4 tok/s

SEA-LION V3 Llama3.1 70B sits at 70B parameters, which puts it above consumer hardware and into the range where a card is bought for this purpose rather than repurposed for it. 61 of the cards we track can hold it.

The least hardware that works is a A100 PCIe 40 GB. Its 40 GB is enough at Q3_K_M compression, giving roughly 25.5 tokens per second.

The quickest result comes from a B200 at around 48.4 tokens per second — its 8,000 GB/s of bandwidth is what buys that.

What this model is

SEA-LION V3 Llama3.1 70B was published by AI Singapore, in Singapore, in December 2024. government is the category the publisher falls under.

It works in Language, and is recorded as doing question answering, Chat, Language modeling/generation.

Its starting point was Llama 3.1-70B — most models at this scale are adapted from an existing base rather than built from nothing.

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

What decides the speed

Across every card that can run it, the middle of the range is about 17.1 tokens per second, and 49 of them clear the ten tokens per second that roughly matches reading speed.

Being dense, it reads all of itself per token, which is why the ordering by speed below follows the ordering by memory bandwidth so closely.

Its attention layout is on file, so the memory figures are computed exactly rather than approximated.

Training and provenance

Training it took roughly 8 × 10²⁴ FLOP of computation, on NVIDIA H200 SXM,NVIDIA H100 SXM5 80GB — a measure of what producing the model cost, not of how fast it answers.

It was trained on about 200,000,000,000 tokens of text.

Step by step

How to choose a GPU for SEA-LION V3 Llama3.1 70B

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

  1. 01

    Check what it needs before anything else

    The table lists every card that can hold SEA-LION V3 Llama3.1 70B — around 33.0 GB at Q3_K_M. That figure, not the card's headline performance, is what decides whether it runs.

  2. 02

    Set the context length you will work at

    The conversation occupies memory too, and grows as it goes. Set the slider to the length you expect: at long context SEA-LION V3 Llama3.1 70B can slip off a card that handles short questions easily.

  3. 03

    Decide how much compression you will accept

    Each card runs the least-compressed copy it can hold — Q3_K_M on the smallest card that fits. Setting a floor drops the cards that only manage SEA-LION V3 Llama3.1 70B by squeezing it further than you would want.

  4. 04

    Rank by throughput rather than spec sheet

    Ranking by tokens per second for SEA-LION V3 Llama3.1 70B follows memory bandwidth, not core counts, which is why the B200 tops it at 48.4 tok/s.

  5. 05

    Read the fit column last

    Tight means SEA-LION V3 Llama3.1 70B 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

    Open the card you have settled on

    Every card name links to its own page, which runs the same calculation across the whole model catalogue. Worth a look before buying for SEA-LION V3 Llama3.1 70B alone — a card is usually bought for more than one model.

Answers

SEA-LION V3 Llama3.1 70B — common questions

01

Why does the quantisation differ between cards for SEA-LION V3 Llama3.1 70B?

Each card is shown running the least-compressed copy it can hold, and SEA-LION V3 Llama3.1 70B appears at 4 different compression levels across the cards that fit it. Bigger cards get the more accurate version.

02

How accurate are these SEA-LION V3 Llama3.1 70B 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 41–58 tok/s on the B200 rather than a single number.

03

What GPU do I need to run SEA-LION V3 Llama3.1 70B?

The smallest card in our catalogue that holds SEA-LION V3 Llama3.1 70B is the A100 PCIe 40 GB, with 40 GB of memory. It runs the model at Q3_K_M using about 33.0 GB, and produces roughly 25.5 tokens per second. 61 cards in total can run it.

04

How fast is SEA-LION V3 Llama3.1 70B on a GPU?

It depends on the card. The quickest we calculate is a B200 at about 48.4 tokens per second; the slowest that still runs it manages considerably less. Reading speed is around ten tokens per second, and 49 of the cards that can run SEA-LION V3 Llama3.1 70B clear that.

05

How much VRAM does SEA-LION V3 Llama3.1 70B need?

About 33.0 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.

06

Is SEA-LION V3 Llama3.1 70B open source?

Its weights are published, so SEA-LION V3 Llama3.1 70B 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.

07

How many parameters does SEA-LION V3 Llama3.1 70B have?

SEA-LION V3 Llama3.1 70B has 70B 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.

08

Who created SEA-LION V3 Llama3.1 70B?

SEA-LION V3 Llama3.1 70B was published by AI Singapore, based in Singapore, categorised as government.

09

When was SEA-LION V3 Llama3.1 70B released?

SEA-LION V3 Llama3.1 70B was published in December 2024. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.

10

What is SEA-LION V3 Llama3.1 70B used for?

SEA-LION V3 Llama3.1 70B works in Language, and is recorded as handling question answering, Chat, Language modeling/generation. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.

11

Where can I download SEA-LION V3 Llama3.1 70B?

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.

12

How much compute was used to train SEA-LION V3 Llama3.1 70B?

Around 8 × 10²⁴ FLOP, on NVIDIA H200 SXM,NVIDIA H100 SXM5 80GB. 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.

13

Can I run SEA-LION V3 Llama3.1 70B if it does not fit in my GPU?

Partly. Layers that do not fit sit in system memory and run at a fraction of the speed, so a mostly-offloaded SEA-LION V3 Llama3.1 70B is rarely worth using — the nearest miss we calculate is short by 12.4 GB. Every figure here assumes the whole model is on the card.

14

Would two GPUs run SEA-LION V3 Llama3.1 70B faster?

Two cards buy memory rather than speed. That matters for SEA-LION V3 Llama3.1 70B only if one card cannot hold it — 61 can, so a second adds little.

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