VAETKI TPS calculator

Open weights NC AI 100B parameters December 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

43 cards that can run it

818 cards we hold specifications for

Smallest card that fits

Radeon Instinct MI200

64 GB · Q4_K_M · 69.5 tok/s

Fastest card

B200

188 tok/s · 180 GB

Which GPUs can run VAETKI?

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

43 cards match

Calculating

					Needs	Quantisation	Fit
188 tok/s 113–301 · low confidence	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	102.3 GB	Q8_0	Comfortable
188 tok/s 113–301 · low confidence	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	102.3 GB	Q8_0	Comfortable
150 tok/s 90–241 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	102.3 GB	Q8_0	Comfortable
150 tok/s 90–241 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	102.3 GB	Q8_0	Comfortable
141 tok/s 85–226 · low confidence	H100 SXM5 80 GB NVIDIA	80 GB	3,360 GB/s	Oct 2022	67.4 GB	Q5_K_M	Tight
141 tok/s 85–226 · low confidence	H800 SXM5 NVIDIA	80 GB	3,360 GB/s	Mar 2023	67.4 GB	Q5_K_M	Tight
135 tok/s 81–216 · low confidence	H100 NVL 94 GB NVIDIA	94 GB	3,940 GB/s	Mar 2023	79.1 GB	Q6_K	Tight
120 tok/s 72–192 · low confidence	Radeon Instinct MI300 AMD	128 GB	6,550 GB/s	Jan 2023	102.3 GB	Q8_0	Tight
115 tok/s 69–184 · low confidence	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	102.3 GB	Q8_0	Comfortable
115 tok/s 69–184 · low confidence	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	102.3 GB	Q8_0	Comfortable
115 tok/s 69–184 · low confidence	H100 PCIe 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	79.1 GB	Q6_K	Tight
115 tok/s 69–184 · low confidence	H100 SXM5 94 GB NVIDIA	94 GB	3,360 GB/s	Mar 2023	79.1 GB	Q6_K	Tight
115 tok/s 69–184 · low confidence	H100 SXM5 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	79.1 GB	Q6_K	Tight
110 tok/s 66–176 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	102.3 GB	Q8_0	Comfortable
110 tok/s 66–176 · low confidence	H100 SXM5 64 GB NVIDIA	64 GB	2,020 GB/s	Mar 2023	55.8 GB	Q4_K_M	Tight
97.7 tok/s 59–156 · low confidence	Radeon Instinct MI300A AMD	128 GB	5,325 GB/s	Dec 2023	102.3 GB	Q8_0	Tight
97.7 tok/s 59–156 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	102.3 GB	Q8_0	Comfortable
97.7 tok/s 59–156 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	102.3 GB	Q8_0	Comfortable
85.7 tok/s 51–137 · low confidence	A100 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Nov 2020	67.4 GB	Q5_K_M	Tight
85.7 tok/s 51–137 · low confidence	A100X NVIDIA	80 GB	2,040 GB/s	Jun 2021	67.4 GB	Q5_K_M	Tight
85.7 tok/s 51–137 · low confidence	A800 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Aug 2022	67.4 GB	Q5_K_M	Tight
85.7 tok/s 51–137 · low confidence	H100 CNX NVIDIA	80 GB	2,040 GB/s	Mar 2023	67.4 GB	Q5_K_M	Tight
85.7 tok/s 51–137 · low confidence	H100 PCIe 80 GB NVIDIA	80 GB	2,040 GB/s	Oct 2022	67.4 GB	Q5_K_M	Tight
85.7 tok/s 51–137 · low confidence	H800 PCIe 80 GB NVIDIA	80 GB	2,040 GB/s	Mar 2023	67.4 GB	Q5_K_M	Tight
81.5 tok/s 49–130 · low confidence	A100 PCIe 80 GB NVIDIA	80 GB	1,940 GB/s	Jun 2021	67.4 GB	Q5_K_M	Tight

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: NC AI
Organisation type: Industry
Country: Korea (Republic of)
Published: 30 December 2025

What it does

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

Domain: Language
Task: Language modeling/generation
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: 100B
Training data: tokens
Epochs: 1
Batch size: 8,000

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 H100 80G
Chips used: 1,016
Wall-clock time: 3,238 hours (134.9 days)

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.

Why it is tracked: Training cost
Record confidence: Confident

Sources

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

Last updated: 3 January 2026

The extremes

The ten fastest GPUs that run VAETKI

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 VAETKI

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

Radeon Instinct MI200

Memory needed

55.8 GB

Fastest

188 tok/s

VAETKI reaches a parameter count of 100B. That puts it above consumer hardware, into the range where a card is bought for this purpose rather than repurposed for it. The number of cards we track that can hold it: 43.

The entry point is Radeon Instinct MI200, with a memory capacity of 64 GB, running it at a compression of Q4_K_M and producing around 69.5 tokens per second.

The quickest result comes from B200, generating roughly 188 tokens per second on the strength of a memory bandwidth of 8,000 GB/s.

Background

VAETKI was published by NC AI, in the country recorded as Korea (Republic of), during December 2025. The publishing organisation is categorised as industry.

It works in the domain of Language, and is recorded as performing the task of language modeling/generation.

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.

Reading the throughput figures

Across every card that can run it, the middle of the range sits at 85.7 tokens per second. Clearing the ten tokens per second that roughly matches reading speed: 41 of them.

Mixture-of-experts routing is why the speeds here look high for the parameter count. Only a fraction is read per token, but the whole thing has to be loaded.

Its internal architecture is not on file, so memory is approximated from the parameter count and marked accordingly. Expect the real figure to differ, more so at long context.

Training and provenance

It is tracked in the underlying dataset for one reason in particular: training cost.

Step by step

How to choose a GPU for VAETKI

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

01

Read the memory figure first

Start from what it actually needs, which is the requirement of VAETKI, needing around 55.8 GB at a compression of Q4_K_M. That figure, not the headline performance of a card, 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 VAETKI.
03

Decide how much compression you will accept

Each card runs the least-compressed copy it can hold, reaching a compression of Q4_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.
04

Compare tokens per second, not specifications

The speed ordering is effectively an ordering by memory bandwidth, for VAETKI. It will not match a gaming ordering, because generation is bound by memory bandwidth. The card topping the list is B200, at 188 tok/s.
05

Check the fit verdict before buying

A tight fit runs, but leaves nothing spare for a longer conversation, in the case of VAETKI. 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.
06

Check the card from the other side

Every card name links to its own page, which runs the same calculation across the whole model catalogue. A card is usually bought for more than one model, so it is worth a look before buying for VAETKI.

Answers

VAETKI — common questions

VAETKI— 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.

VAETKI— how many parameters does it have?

It has a parameter count of 100B. Total parameters: 100B (Sparse), Active parameters: 10B per token. It uses a Mixture-of-Experts architecture with 1 shared expert and 128 total experts(top-8 routing). 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.

VAETKI— who created it?

It was published by NC AI, based in Korea (Republic of), an organisation categorised as industry.

VAETKI— when was it released?

It was published in December 2025.

VAETKI— what is it used for?

It works in the domain of Language, and is recorded as handling the task of language modeling/generation. These are the areas it was designed around; they describe intent rather than a hard boundary.

VAETKI— where can I download it?

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

VAETKI— can I run it 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 model is rarely worth using. The nearest miss we calculate falls short by 12.6 GB. Every figure here assumes the whole model is resident on the card.

VAETKI— would two GPUs run it faster?

Capacity adds across cards; throughput does not. The number of cards already holding it on their own: 43. So a second card is rarely the answer here.

VAETKI— why does the quantisation differ between cards?

Because capacity varies, so does how hard it has to be squeezed. The number of distinct levels in the table above: 4. Bigger cards get the more accurate version, and the quality floor above pins the comparison to one level.

VAETKI— how accurate are these speed estimates?

Every figure is derived from memory bandwidth and model size, not benchmarked, which is why each is published as a range rather than a single number. One example: 113–301 tok/s on B200. The same model and card vary by thirty to fifty per cent depending on the inference software and its version.

VAETKI— what GPU do I need to run it?

The smallest card in our catalogue that holds it is Radeon Instinct MI200, with a memory capacity of 64 GB. It runs the model at a compression of Q4_K_M using about 55.8 GB, and produces roughly 69.5 tokens per second. The number of cards able to run it in total: 43.

VAETKI— how fast is it on a GPU?

It depends on the card. The quickest we calculate is B200, at about 188 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: 41.

VAETKI— how much VRAM does it need?

It needs about 55.8 GB at a compression of Q4_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.

Source

Original publication

Record last updated 3 January 2026

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