Japanese-LM-3.6B TPS calculator

Open weights LINE Corporation 3.6B parameters August 2023

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

818 cards that can run it

818 cards we hold specifications for

Smallest card that fits

Tesla C1080

4 GB · Q5_K_M · 18.3 tok/s

Fastest card

B200

941 tok/s · 180 GB

Which GPUs can run Japanese-LM-3.6B?

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

818 cards match

Calculating

					Needs	Quantisation	Fit
941 tok/s 565–1,506 · low confidence	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	4.6 GB	Q8_0	Comfortable
941 tok/s 565–1,506 · low confidence	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	4.6 GB	Q8_0	Comfortable
752 tok/s 451–1,202 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	4.6 GB	Q8_0	Comfortable
752 tok/s 451–1,202 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	4.6 GB	Q8_0	Comfortable
601 tok/s 361–962 · low confidence	Radeon Instinct MI300 AMD	128 GB	6,550 GB/s	Jan 2023	4.6 GB	Q8_0	Comfortable
575 tok/s 345–920 · low confidence	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	4.6 GB	Q8_0	Comfortable
575 tok/s 345–920 · low confidence	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	4.6 GB	Q8_0	Comfortable
551 tok/s 330–881 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	4.6 GB	Q8_0	Comfortable
489 tok/s 293–782 · low confidence	Radeon Instinct MI300A AMD	128 GB	5,325 GB/s	Dec 2023	4.6 GB	Q8_0	Comfortable
489 tok/s 293–782 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	4.6 GB	Q8_0	Comfortable
489 tok/s 293–782 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	4.6 GB	Q8_0	Comfortable
464 tok/s 278–742 · low confidence	H100 NVL 94 GB NVIDIA	94 GB	3,940 GB/s	Mar 2023	4.6 GB	Q8_0	Comfortable
395 tok/s 237–632 · low confidence	H100 PCIe 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	4.6 GB	Q8_0	Comfortable
395 tok/s 237–632 · low confidence	H100 SXM5 80 GB NVIDIA	80 GB	3,360 GB/s	Oct 2022	4.6 GB	Q8_0	Comfortable
395 tok/s 237–632 · low confidence	H100 SXM5 94 GB NVIDIA	94 GB	3,360 GB/s	Mar 2023	4.6 GB	Q8_0	Comfortable
395 tok/s 237–632 · low confidence	H100 SXM5 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	4.6 GB	Q8_0	Comfortable
395 tok/s 237–632 · low confidence	H800 SXM5 NVIDIA	80 GB	3,360 GB/s	Mar 2023	4.6 GB	Q8_0	Comfortable
301 tok/s 181–482 · low confidence	Radeon Instinct MI250 AMD	128 GB	3,280 GB/s	Nov 2021	4.6 GB	Q8_0	Comfortable
301 tok/s 181–482 · low confidence	Radeon Instinct MI250X AMD	128 GB	3,280 GB/s	Nov 2021	4.6 GB	Q8_0	Comfortable
251 tok/s 150–401 · low confidence	Data Center GPU Max 1550 Intel	128 GB	3,280 GB/s	Jan 2023	4.6 GB	Q8_0	Comfortable
245 tok/s 147–393 · low confidence	Data Center GPU Max Subsystem Intel	128 GB	3,210 GB/s	Jan 2023	4.6 GB	Q8_0	Comfortable
240 tok/s 144–384 · low confidence	A100 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Nov 2020	4.6 GB	Q8_0	Comfortable
240 tok/s 144–384 · low confidence	A100X NVIDIA	80 GB	2,040 GB/s	Jun 2021	4.6 GB	Q8_0	Comfortable
240 tok/s 144–384 · low confidence	A800 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Aug 2022	4.6 GB	Q8_0	Comfortable
240 tok/s 144–384 · low confidence	H100 CNX NVIDIA	80 GB	2,040 GB/s	Mar 2023	4.6 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: LINE Corporation
Organisation type: Industry
Country: Japan
Published: 14 August 2023
Authors: Shun Kiyono, Sho Takase, Toshinori Sato

What it does

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

Domain: Language
Task: Language modeling

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: 3.6B
Training data: 72,150,000,000 tokens

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 A100

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: Likely

Sources

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

Reference: japanese-large-lm-3.6b
Last updated: 28 November 2025

The extremes

The ten fastest GPUs that run Japanese-LM-3.6B

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 Japanese-LM-3.6B

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

Hardware requirements in practice

Minimum card

Tesla C1080

Memory needed

3.3 GB

Fastest

941 tok/s

Japanese-LM-3.6B is small enough at 3.6B parameters that hardware is rarely the obstacle — 818 of the cards we track can run it, including cards several years old.

The entry point is the Tesla C1080: 4 GB of memory, Q5_K_M compression, roughly 18.3 tokens per second.

At the other end, a B200 generates roughly 941 tokens per second on it, on the strength of 8,000 GB/s of memory bandwidth.

What this model is

Japanese-LM-3.6B was published by LINE Corporation, in Japan, in August 2023. It comes out of industry.

It works in Language, and is recorded as doing language modeling.

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

What decides the speed

Across every card that can run it, the middle of the range is about 31.6 tokens per second, and 778 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.

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.

What went into building it

The training set ran to roughly 72,150,000,000 tokens.

Step by step

How to choose a GPU for Japanese-LM-3.6B

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

Every card here has been checked against Japanese-LM-3.6B — around 3.3 GB at Q5_K_M. Capacity is the gate — a card either holds it or it does not.
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 Japanese-LM-3.6B can slip off a card that handles short questions easily.
03

Set a quality floor

The quantisation column varies by card, because a bigger card holds a more accurate copy of Japanese-LM-3.6B — Q5_K_M on the smallest card that fits. Set a floor to hold the comparison at one level.
04

Rank by throughput rather than spec sheet

Ranking by tokens per second for Japanese-LM-3.6B follows memory bandwidth, not core counts, which is why the B200 tops it at 941 tok/s.
05

Read the fit column last

Tight means Japanese-LM-3.6B 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

Every card name links to its own page, which runs the same calculation across the whole model catalogue. Worth a look before buying for Japanese-LM-3.6B alone — a card is usually bought for more than one model.

Answers

Japanese-LM-3.6B — common questions

How much VRAM does Japanese-LM-3.6B need?

About 3.3 GB at Q5_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 Japanese-LM-3.6B on a 8 GB GPU?

Yes. A CMP 170HX 8 GB with 8 GB runs it at Q8_0, using about 4.6 GB and generating roughly 175 tokens per second — a comfortable fit.

Can I run Japanese-LM-3.6B on a 12 GB GPU?

Yes. A GeForce RTX 3080 Ti with 12 GB runs it at Q8_0, using about 4.6 GB and generating roughly 107 tokens per second — a comfortable fit.

Can I run Japanese-LM-3.6B on a 16 GB GPU?

Yes. A Tesla V100 SXM2 16 GB with 16 GB runs it at Q8_0, using about 4.6 GB and generating roughly 133 tokens per second — a comfortable fit.

Can I run Japanese-LM-3.6B on a 24 GB GPU?

Yes. A GeForce RTX 5090 D V2 with 24 GB runs it at Q8_0, using about 4.6 GB and generating roughly 158 tokens per second — a comfortable fit.

Is Japanese-LM-3.6B open source?

Its weights are published, so Japanese-LM-3.6B 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.

How many parameters does Japanese-LM-3.6B have?

Japanese-LM-3.6B has 3.6B parameters. 3.6B. 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 Japanese-LM-3.6B?

Japanese-LM-3.6B was published by LINE Corporation, based in Japan, categorised as industry.

When was Japanese-LM-3.6B released?

Japanese-LM-3.6B was published in August 2023. 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 Japanese-LM-3.6B used for?

Japanese-LM-3.6B works in Language, and is recorded as handling language modeling. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.

Where can I download Japanese-LM-3.6B?

The weights for Japanese-LM-3.6B are published, though we do not hold a repository link for it. This site calculates hardware requirements rather than hosting model files.

Can I run Japanese-LM-3.6B 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. Our figures for Japanese-LM-3.6B assume it is fully resident.

Would two GPUs run Japanese-LM-3.6B faster?

Two cards buy memory rather than speed. That matters for Japanese-LM-3.6B only if one card cannot hold it — 818 can, so a second adds little.

Why does the quantisation differ between cards for Japanese-LM-3.6B?

Because capacity varies, so does how hard Japanese-LM-3.6B has to be squeezed — 3 distinct levels appear in the table above. Set a minimum quality to compare at one.

How accurate are these Japanese-LM-3.6B 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 565–1,506 tok/s on the B200 rather than a single number.

What GPU do I need to run Japanese-LM-3.6B?

The smallest card in our catalogue that holds Japanese-LM-3.6B is the Tesla C1080, with 4 GB of memory. It runs the model at Q5_K_M using about 3.3 GB, and produces roughly 18.3 tokens per second. 818 cards in total can run it.

How fast is Japanese-LM-3.6B on a GPU?

It depends on the card. The quickest we calculate is a B200 at about 941 tokens per second; the slowest that still runs it manages considerably less. Reading speed is around ten tokens per second, and 778 of the cards that can run Japanese-LM-3.6B clear that.

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