Fugaku-LLM TPS calculator

Open weights Tohoku University,CyberAgent,Tokyo Institute of Technology,Fujitsu,RIKEN,Nagoya University,Kotoba Technologies 13B parameters May 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

509 of 818 cards that can run it

Smallest card that fits

Xeon Phi 5110P

8 GB · Q3_K_M · 18.3 tok/s

Fastest card

B200

261 tok/s · 180 GB

Which GPUs can run Fugaku-LLM?

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
261 tok/s 156–417 · low confidence	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	14.6 GB	Q8_0	Comfortable
261 tok/s 156–417 · low confidence	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	14.6 GB	Q8_0	Comfortable
208 tok/s 125–333 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	14.6 GB	Q8_0	Comfortable
208 tok/s 125–333 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	14.6 GB	Q8_0	Comfortable
166 tok/s 100–266 · low confidence	Radeon Instinct MI300 AMD	128 GB	6,550 GB/s	Jan 2023	14.6 GB	Q8_0	Comfortable
159 tok/s 96–255 · low confidence	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	14.6 GB	Q8_0	Comfortable
159 tok/s 96–255 · low confidence	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	14.6 GB	Q8_0	Comfortable
152 tok/s 91–244 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	14.6 GB	Q8_0	Comfortable
135 tok/s 81–217 · low confidence	Radeon Instinct MI300A AMD	128 GB	5,325 GB/s	Dec 2023	14.6 GB	Q8_0	Comfortable
135 tok/s 81–217 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	14.6 GB	Q8_0	Comfortable
135 tok/s 81–217 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	14.6 GB	Q8_0	Comfortable
131 tok/s 79–210 · low confidence	CMP 170HX 8 GB NVIDIA	8 GB	1,490 GB/s	Sep 2021	7.1 GB	Q3_K_M	Tight
128 tok/s 77–205 · low confidence	H100 NVL 94 GB NVIDIA	94 GB	3,940 GB/s	Mar 2023	14.6 GB	Q8_0	Comfortable
117 tok/s 70–188 · low confidence	CMP 170HX 10 GB NVIDIA	10 GB	1,560 GB/s	Sep 2021	8.6 GB	Q4_K_M	Tight
109 tok/s 66–175 · low confidence	H100 PCIe 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	14.6 GB	Q8_0	Comfortable
109 tok/s 66–175 · low confidence	H100 SXM5 80 GB NVIDIA	80 GB	3,360 GB/s	Oct 2022	14.6 GB	Q8_0	Comfortable
109 tok/s 66–175 · low confidence	H100 SXM5 94 GB NVIDIA	94 GB	3,360 GB/s	Mar 2023	14.6 GB	Q8_0	Comfortable
109 tok/s 66–175 · low confidence	H100 SXM5 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	14.6 GB	Q8_0	Comfortable
109 tok/s 66–175 · low confidence	H800 SXM5 NVIDIA	80 GB	3,360 GB/s	Mar 2023	14.6 GB	Q8_0	Comfortable
83.4 tok/s 50–133 · low confidence	Radeon Instinct MI250 AMD	128 GB	3,280 GB/s	Nov 2021	14.6 GB	Q8_0	Comfortable
83.4 tok/s 50–133 · low confidence	Radeon Instinct MI250X AMD	128 GB	3,280 GB/s	Nov 2021	14.6 GB	Q8_0	Comfortable
69.5 tok/s 42–111 · low confidence	Data Center GPU Max 1550 Intel	128 GB	3,280 GB/s	Jan 2023	14.6 GB	Q8_0	Comfortable
68.0 tok/s 41–109 · low confidence	Data Center GPU Max Subsystem Intel	128 GB	3,210 GB/s	Jan 2023	14.6 GB	Q8_0	Comfortable
67.5 tok/s 41–108 · low confidence	RTX A5000-8Q NVIDIA	8 GB	768 GB/s	Apr 2021	7.1 GB	Q3_K_M	Tight
66.5 tok/s 40–106 · low confidence	A100 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Nov 2020	14.6 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: Tohoku University,CyberAgent,Tokyo Institute of Technology,Fujitsu,RIKEN,Nagoya University,Kotoba Technologies
Organisation type: Academia,Industry,Academia,Industry,Academia,Industry
Country: Japan
Published: 10 May 2024
Authors: Fugaku Team

What it does

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

Domain: Language
Task: Language modeling, Translation, Japanese language modeling, Language modeling/generation, Question answering

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: 13B
Training data: 380,000,000,000 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: 3 × 10²² FLOP
How it was established: Operation counting

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 (unrestricted)
Training code: Unreleased

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: Release of “Fugaku-LLM” – a large language model trained on the supercomputer “Fugaku”
Last updated: 28 November 2025

The extremes

The ten fastest GPUs for Fugaku-LLM

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 Fugaku-LLM

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

7.1 GB

Fastest

261 tok/s

Fugaku-LLM is small enough at 13B parameters that hardware is rarely the obstacle — 509 of the cards we track can run it, including cards several years old.

At the low end, a Xeon Phi 5110P handles it — 8 GB, at Q3_K_M, for about 18.3 tokens per second.

At the other end, a B200 generates roughly 261 tokens per second on it, on the strength of 8,000 GB/s of memory bandwidth.

About this model

Fugaku-LLM was published by Tohoku University,CyberAgent,Tokyo Institute of Technology,Fujitsu,RIKEN,Nagoya University,Kotoba Technologies, in Japan, in May 2024. The organisation is categorised as academia,Industry,Academia,Industry,Academia,Industry.

It works in Language, and is recorded as doing language modeling, Translation, Japanese language modeling, Language modeling/generation, Question answering.

The weights are published, so it can be downloaded and run on your own hardware indefinitely, offline, with no account attached.

How fast it runs, and why

The median result is around 21.2 tokens per second; 459 cards produce text faster than most people read it.

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.

Without the attention layout on record, the memory column is an approximation. It is close enough to choose hardware by, and least reliable at long context.

How it was trained

Producing it required around 3 × 10²² FLOP of arithmetic, which is a statement about the training budget rather than about inference.

Around 380,000,000,000 tokens went into training it.

Step by step

How to choose a GPU for Fugaku-LLM

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

01

Start from the memory column

The table lists every card that can hold Fugaku-LLM — around 7.1 GB at Q3_K_M. That figure, not the card's headline performance, is what decides whether it runs.
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 Fugaku-LLM.
03

Decide how much compression you will accept

The quantisation column varies by card, because a bigger card holds a more accurate copy of Fugaku-LLM — Q3_K_M on the smallest card that fits. Set a floor to hold the comparison at one level.
04

Sort by speed

Ranking by tokens per second for Fugaku-LLM follows memory bandwidth, not core counts, which is why the B200 tops it at 261 tok/s.
05

Look at the headroom, not just the fit

Tight means Fugaku-LLM 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.
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 Fugaku-LLM.

Answers

Fugaku-LLM — common questions

How many parameters does Fugaku-LLM have?

Fugaku-LLM has 13B parameters. "Fugaku-LLM has 13 billion parameters (2)". 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.

Who created Fugaku-LLM?

Fugaku-LLM was published by Tohoku University,CyberAgent,Tokyo Institute of Technology,Fujitsu,RIKEN,Nagoya University,Kotoba Technologies, based in Japan, categorised as academia,Industry,Academia,Industry,Academia,Industry.

When was Fugaku-LLM released?

Fugaku-LLM was published in May 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.

What is Fugaku-LLM used for?

Fugaku-LLM works in Language, and is recorded as handling language modeling, Translation, Japanese language modeling, Language modeling/generation, Question answering. These are the areas it was designed around; they describe intent rather than a hard boundary.

Where can I download Fugaku-LLM?

The weights for Fugaku-LLM are published, though we do not hold a repository link for it. This site calculates hardware requirements rather than hosting model files.

How much compute was used to train Fugaku-LLM?

Around 3 × 10²² FLOP. 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.

Can I run Fugaku-LLM 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 3.2 GB. Our figures for Fugaku-LLM assume it is fully resident.

Would two GPUs run Fugaku-LLM faster?

A second card roughly doubles the memory available but not the generation rate. With 509 cards already able to run Fugaku-LLM alone, the case for pairing is weak.

Why does the quantisation differ between cards for Fugaku-LLM?

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

How accurate are these Fugaku-LLM 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 156–417 tok/s on the B200 rather than a single number.

What GPU do I need to run Fugaku-LLM?

The smallest card in our catalogue that holds Fugaku-LLM is the Xeon Phi 5110P, with 8 GB of memory. It runs the model at Q3_K_M using about 7.1 GB, and produces roughly 18.3 tokens per second. 509 cards in total can run it.

How fast is Fugaku-LLM on a GPU?

It depends on the card. The quickest we calculate is a B200 at about 261 tokens per second; the slowest that still runs it manages considerably less. Reading speed is around ten tokens per second, and 459 of the cards that can run Fugaku-LLM clear that.

How much VRAM does Fugaku-LLM need?

About 7.1 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.

Can I run Fugaku-LLM on a 8 GB GPU?

Yes. A CMP 170HX 8 GB with 8 GB runs it at Q3_K_M, using about 7.1 GB and generating roughly 131 tokens per second — a tight fit.

Can I run Fugaku-LLM on a 12 GB GPU?

Yes. A GeForce RTX 3080 Ti with 12 GB runs it at Q5_K_M, using about 10.1 GB and generating roughly 53.1 tokens per second — a tight fit.

Can I run Fugaku-LLM on a 16 GB GPU?

Yes. A Tesla V100 SXM2 16 GB with 16 GB runs it at Q6_K, using about 11.6 GB and generating roughly 53.5 tokens per second — a comfortable fit.

Can I run Fugaku-LLM on a 24 GB GPU?

Yes. A GeForce RTX 5090 D V2 with 24 GB runs it at Q8_0, using about 14.6 GB and generating roughly 43.7 tokens per second — a comfortable fit.

Is Fugaku-LLM open source?

Its weights are published, so Fugaku-LLM 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.

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