Qarasu-14B TPS calculator

Open weights Lightblue 14B parameters December 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

306 cards that can run it

818 cards we hold specifications for

Smallest card that fits

P102-101

10 GB · IQ4_XS · 20.2 tok/s

Fastest card

B200

242 tok/s · 180 GB

Which GPUs can run Qarasu-14B?

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

306 cards match

Calculating

					Needs	Quantisation	Fit
242 tok/s 145–387 · low confidence	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	15.7 GB	Q8_0	Comfortable
242 tok/s 145–387 · low confidence	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	15.7 GB	Q8_0	Comfortable
193 tok/s 116–309 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	15.7 GB	Q8_0	Comfortable
193 tok/s 116–309 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	15.7 GB	Q8_0	Comfortable
155 tok/s 93–247 · low confidence	Radeon Instinct MI300 AMD	128 GB	6,550 GB/s	Jan 2023	15.7 GB	Q8_0	Comfortable
148 tok/s 89–237 · low confidence	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	15.7 GB	Q8_0	Comfortable
148 tok/s 89–237 · low confidence	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	15.7 GB	Q8_0	Comfortable
142 tok/s 85–227 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	15.7 GB	Q8_0	Comfortable
126 tok/s 75–201 · low confidence	Radeon Instinct MI300A AMD	128 GB	5,325 GB/s	Dec 2023	15.7 GB	Q8_0	Comfortable
126 tok/s 75–201 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	15.7 GB	Q8_0	Comfortable
126 tok/s 75–201 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	15.7 GB	Q8_0	Comfortable
119 tok/s 72–191 · low confidence	H100 NVL 94 GB NVIDIA	94 GB	3,940 GB/s	Mar 2023	15.7 GB	Q8_0	Comfortable
116 tok/s 70–185 · low confidence	CMP 170HX 10 GB NVIDIA	10 GB	1,560 GB/s	Sep 2021	8.4 GB	IQ4_XS	Tight
102 tok/s 61–163 · low confidence	H100 PCIe 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	15.7 GB	Q8_0	Comfortable
102 tok/s 61–163 · low confidence	H100 SXM5 80 GB NVIDIA	80 GB	3,360 GB/s	Oct 2022	15.7 GB	Q8_0	Comfortable
102 tok/s 61–163 · low confidence	H100 SXM5 94 GB NVIDIA	94 GB	3,360 GB/s	Mar 2023	15.7 GB	Q8_0	Comfortable
102 tok/s 61–163 · low confidence	H100 SXM5 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	15.7 GB	Q8_0	Comfortable
102 tok/s 61–163 · low confidence	H800 SXM5 NVIDIA	80 GB	3,360 GB/s	Mar 2023	15.7 GB	Q8_0	Comfortable
77.4 tok/s 46–124 · low confidence	Radeon Instinct MI250 AMD	128 GB	3,280 GB/s	Nov 2021	15.7 GB	Q8_0	Comfortable
77.4 tok/s 46–124 · low confidence	Radeon Instinct MI250X AMD	128 GB	3,280 GB/s	Nov 2021	15.7 GB	Q8_0	Comfortable
64.5 tok/s 39–103 · low confidence	Data Center GPU Max 1550 Intel	128 GB	3,280 GB/s	Jan 2023	15.7 GB	Q8_0	Comfortable
63.1 tok/s 38–101 · low confidence	Data Center GPU Max Subsystem Intel	128 GB	3,210 GB/s	Jan 2023	15.7 GB	Q8_0	Comfortable
61.7 tok/s 37–99 · low confidence	A100 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Nov 2020	15.7 GB	Q8_0	Comfortable
61.7 tok/s 37–99 · low confidence	A100X NVIDIA	80 GB	2,040 GB/s	Jun 2021	15.7 GB	Q8_0	Comfortable
61.7 tok/s 37–99 · low confidence	A800 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Aug 2022	15.7 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: Lightblue
Organisation type: Industry
Country: Japan
Published: 29 December 2023
Authors: Peter Devine

What it does

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

Domain: Language
Task: Chat
Base model: Qwen-14B

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: 14B
Training data: 7,000,000,000 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.

Fine-tuning compute: 5.9 × 10²⁰ 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 A100 SXM4 40 GB

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)

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: Karasu and Qarasu: The new top Japanese Chatbots
Last updated: 28 November 2025

The extremes

The ten fastest GPUs that run Qarasu-14B

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 Qarasu-14B

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

What you need to run it

Minimum card

P102-101

Memory needed

8.4 GB

Fastest

242 tok/s

Qarasu-14B is small enough at 14B parameters that hardware is rarely the obstacle — 306 of the cards we track can run it, including cards several years old.

The least hardware that works is a P102-101. Its 10 GB is enough at IQ4_XS compression, giving roughly 20.2 tokens per second.

The quickest result comes from a B200 at around 242 tokens per second — its 8,000 GB/s of bandwidth is what buys that.

About this model

Qarasu-14B was published by Lightblue, in Japan, in December 2023. The organisation is categorised as industry.

It works in Language, and is recorded as doing chat.

It builds on Qwen-14B, which is why it shares that model's general shape and size.

Because its weights were released, nothing about running it depends on a provider staying available — it is yours once downloaded.

How fast it runs, and why

Across every card that can run it, the middle of the range is about 20.4 tokens per second, and 268 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.

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.

Training and provenance

It was trained on about 7,000,000,000 tokens of text.

Step by step

How to choose a GPU for Qarasu-14B

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 Qarasu-14B — around 8.4 GB at IQ4_XS. Capacity is the gate — a card either holds it or it does not.
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 Qarasu-14B.
03

Set a quality floor

Each card runs the least-compressed copy it can hold — IQ4_XS on the smallest card that fits. Setting a floor drops the cards that only manage Qarasu-14B by squeezing it further than you would want.
04

Compare tokens per second, not specifications

Ranking by tokens per second for Qarasu-14B follows memory bandwidth, not core counts, which is why the B200 tops it at 242 tok/s.
05

Read the fit column last

Tight means Qarasu-14B 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

Open the card you have settled on

Each card page repeats this sweep for every model we hold. It answers what else the hardware is good for, beyond Qarasu-14B.

Answers

Qarasu-14B — common questions

How fast is Qarasu-14B on a GPU?

It depends on the card. The quickest we calculate is a B200 at about 242 tokens per second; the slowest that still runs it manages considerably less. Reading speed is around ten tokens per second, and 268 of the cards that can run Qarasu-14B clear that.

How much VRAM does Qarasu-14B need?

About 8.4 GB at IQ4_XS 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 Qarasu-14B on a 12 GB GPU?

Yes. A GeForce RTX 3080 Ti with 12 GB runs it at Q5_K_M, using about 10.8 GB and generating roughly 49.3 tokens per second — a tight fit.

Can I run Qarasu-14B on a 16 GB GPU?

Yes. A Tesla V100 SXM2 16 GB with 16 GB runs it at Q6_K, using about 12.4 GB and generating roughly 49.7 tokens per second — a tight fit.

Can I run Qarasu-14B on a 24 GB GPU?

Yes. A GeForce RTX 5090 D V2 with 24 GB runs it at Q8_0, using about 15.7 GB and generating roughly 40.5 tokens per second — a comfortable fit.

Is Qarasu-14B open source?

Its weights are published, so Qarasu-14B 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 Qarasu-14B have?

Qarasu-14B has 14B parameters. 14B. 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 Qarasu-14B?

Qarasu-14B was published by Lightblue, based in Japan, categorised as industry.

When was Qarasu-14B released?

Qarasu-14B was published in December 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 Qarasu-14B used for?

Qarasu-14B works in Language, and is recorded as handling chat. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.

Where can I download Qarasu-14B?

The weights for Qarasu-14B 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 Qarasu-14B 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 2.0 GB. Our figures for Qarasu-14B assume it is fully resident.

Would two GPUs run Qarasu-14B faster?

Two cards buy memory rather than speed. That matters for Qarasu-14B only if one card cannot hold it — 306 can, so a second adds little.

Why does the quantisation differ between cards for Qarasu-14B?

Because capacity varies, so does how hard Qarasu-14B has to be squeezed — 5 distinct levels appear in the table above. Set a minimum quality to compare at one.

How accurate are these Qarasu-14B speed estimates?

These are estimates with real error bars. The fastest result here, 145–387 tok/s on the B200, could reasonably land anywhere in its published range depending on which runtime you use.

What GPU do I need to run Qarasu-14B?

The smallest card in our catalogue that holds Qarasu-14B is the P102-101, with 10 GB of memory. It runs the model at IQ4_XS using about 8.4 GB, and produces roughly 20.2 tokens per second. 306 cards in total can run it.

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