Tk-Instruct TPS calculator

Open weights University of Washington,Arizona State University,Allen Institute for AI 11B parameters October 2022

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 cards that can run it

818 cards we hold specifications for

Smallest card that fits

Xeon Phi 5110P

8 GB · IQ4_XS · 19.7 tok/s

Fastest card

B200

308 tok/s · 180 GB

Which GPUs can run Tk-Instruct?

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
308 tok/s 185–493 · low confidence	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	12.5 GB	Q8_0	Comfortable
308 tok/s 185–493 · low confidence	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	12.5 GB	Q8_0	Comfortable
246 tok/s 148–394 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	12.5 GB	Q8_0	Comfortable
246 tok/s 148–394 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	12.5 GB	Q8_0	Comfortable
197 tok/s 118–315 · low confidence	Radeon Instinct MI300 AMD	128 GB	6,550 GB/s	Jan 2023	12.5 GB	Q8_0	Comfortable
188 tok/s 113–301 · low confidence	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	12.5 GB	Q8_0	Comfortable
188 tok/s 113–301 · low confidence	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	12.5 GB	Q8_0	Comfortable
180 tok/s 108–288 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	12.5 GB	Q8_0	Comfortable
160 tok/s 96–256 · low confidence	Radeon Instinct MI300A AMD	128 GB	5,325 GB/s	Dec 2023	12.5 GB	Q8_0	Comfortable
160 tok/s 96–256 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	12.5 GB	Q8_0	Comfortable
160 tok/s 96–256 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	12.5 GB	Q8_0	Comfortable
152 tok/s 91–243 · low confidence	H100 NVL 94 GB NVIDIA	94 GB	3,940 GB/s	Mar 2023	12.5 GB	Q8_0	Comfortable
141 tok/s 85–225 · low confidence	CMP 170HX 8 GB NVIDIA	8 GB	1,490 GB/s	Sep 2021	6.7 GB	IQ4_XS	Tight
129 tok/s 78–207 · low confidence	H100 PCIe 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	12.5 GB	Q8_0	Comfortable
129 tok/s 78–207 · low confidence	H100 SXM5 80 GB NVIDIA	80 GB	3,360 GB/s	Oct 2022	12.5 GB	Q8_0	Comfortable
129 tok/s 78–207 · low confidence	H100 SXM5 94 GB NVIDIA	94 GB	3,360 GB/s	Mar 2023	12.5 GB	Q8_0	Comfortable
129 tok/s 78–207 · low confidence	H100 SXM5 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	12.5 GB	Q8_0	Comfortable
129 tok/s 78–207 · low confidence	H800 SXM5 NVIDIA	80 GB	3,360 GB/s	Mar 2023	12.5 GB	Q8_0	Comfortable
107 tok/s 64–172 · low confidence	CMP 170HX 10 GB NVIDIA	10 GB	1,560 GB/s	Sep 2021	8.6 GB	Q5_K_M	Tight
98.5 tok/s 59–158 · low confidence	Radeon Instinct MI250 AMD	128 GB	3,280 GB/s	Nov 2021	12.5 GB	Q8_0	Comfortable
98.5 tok/s 59–158 · low confidence	Radeon Instinct MI250X AMD	128 GB	3,280 GB/s	Nov 2021	12.5 GB	Q8_0	Comfortable
82.1 tok/s 49–131 · low confidence	Data Center GPU Max 1550 Intel	128 GB	3,280 GB/s	Jan 2023	12.5 GB	Q8_0	Comfortable
80.3 tok/s 48–129 · low confidence	Data Center GPU Max Subsystem Intel	128 GB	3,210 GB/s	Jan 2023	12.5 GB	Q8_0	Comfortable
78.6 tok/s 47–126 · low confidence	A100 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Nov 2020	12.5 GB	Q8_0	Comfortable
78.6 tok/s 47–126 · low confidence	A100X NVIDIA	80 GB	2,040 GB/s	Jun 2021	12.5 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: University of Washington,Arizona State University,Allen Institute for AI
Organisation type: Academia,Academia,Research collective
Country: United States of America
Published: 24 October 2022
Authors: Yizhong Wang, Swaroop Mishra, Pegah Alipoormolabashi, Yeganeh Kordi, Amirreza Mirzaei, Anjana Arunkumar, Arjun Ashok, Arut Selvan Dhanasekaran, Atharva Naik, David Stap, Eshaan Pathak, Giannis Karamanolakis, Haizhi Gary Lai, Ishan Purohit, Ishani Mondal, Jacob Anderson, Kirby Kuznia, Krima Doshi, Maitreya Patel, Kuntal Kumar Pal, Mehrad Moradshahi, Mihir Parmar, Mirali Purohit, Neeraj Varshney, Ph…

What it does

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

Domain: Language
Task: Instruction interpretation
Base model: T5-11B

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: 11B
Training data: 1,048,576,000 tokens
Batch size: 1,048,576

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.

How it was established: Operation counting
Fine-tuning compute: 3.4 × 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: Google TPU v3
Wall-clock time: 20 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 (unrestricted)
Training code: Open source

How it is classified

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

Record confidence: Speculative

Sources

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

Reference: Super-NaturalInstructions: Generalization via Declarative Instructions on 1600+ NLP Tasks
Last updated: 28 November 2025

The extremes

The ten fastest GPUs that run Tk-Instruct

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 Tk-Instruct

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 it takes to run this model

Minimum card

Xeon Phi 5110P

Memory needed

6.7 GB

Fastest

308 tok/s

Tk-Instruct is small enough at 11B parameters that hardware is rarely the obstacle — 509 of the cards we track can run it, including cards several years old.

The smallest card that holds it is the Xeon Phi 5110P with 8 GB, running it at IQ4_XS and producing around 19.7 tokens per second.

At the other end, a B200 generates roughly 308 tokens per second on it, on the strength of 8,000 GB/s of memory bandwidth.

What this model is

Tk-Instruct was published by University of Washington,Arizona State University,Allen Institute for AI, in United States of America, in October 2022. It comes out of academia,Academia,Research collective.

It works in Language, and is recorded as doing instruction interpretation.

It is derived from T5-11B rather than trained from scratch, which is the usual way a specialised model is produced.

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

Half the cards that hold it manage more than 21.2 tokens per second, and 460 exceed reading speed outright.

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.

How it was trained

The training set ran to roughly 1,048,576,000 tokens.

Step by step

How to choose a GPU for Tk-Instruct

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

01

Check what it needs before anything else

The table lists every card that can hold Tk-Instruct — around 6.7 GB at IQ4_XS. That figure, not the card's headline performance, is what decides whether it runs.
02

Set the context length you will work at

Set the context to what you will actually use. The cache grows with the conversation, and it is the usual reason Tk-Instruct stops fitting a card that seemed fine.
03

Choose how far you will compress it

The quantisation column varies by card, because a bigger card holds a more accurate copy of Tk-Instruct — IQ4_XS on the smallest card that fits. Set a floor to hold the comparison at one level.
04

Sort by speed

The speed ordering for Tk-Instruct is effectively an ordering by memory bandwidth, which is why the B200 tops it at 308 tok/s.
05

Read the fit column last

A tight fit runs Tk-Instruct but leaves nothing spare for a longer conversation; comfortable has headroom. If you expect to grow the context, buy for comfortable.
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 Tk-Instruct alone — a card is usually bought for more than one model.

Answers

Tk-Instruct — common questions

Can I run Tk-Instruct on a 8 GB GPU?

Yes. A CMP 170HX 8 GB with 8 GB runs it at IQ4_XS, using about 6.7 GB and generating roughly 141 tokens per second — a tight fit.

Can I run Tk-Instruct on a 12 GB GPU?

Yes. A GeForce RTX 3080 Ti with 12 GB runs it at Q6_K, using about 9.9 GB and generating roughly 51.0 tokens per second — a tight fit.

Can I run Tk-Instruct on a 16 GB GPU?

Yes. A Tesla V100 SXM2 16 GB with 16 GB runs it at Q8_0, using about 12.5 GB and generating roughly 43.5 tokens per second — a tight fit.

Can I run Tk-Instruct on a 24 GB GPU?

Yes. A GeForce RTX 5090 D V2 with 24 GB runs it at Q8_0, using about 12.5 GB and generating roughly 51.6 tokens per second — a comfortable fit.

Is Tk-Instruct open source?

Its weights are published, so Tk-Instruct 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 Tk-Instruct have?

Tk-Instruct has 11B parameters. 11B. 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 Tk-Instruct?

Tk-Instruct was published by University of Washington,Arizona State University,Allen Institute for AI, based in United States of America, categorised as academia,Academia,Research collective.

When was Tk-Instruct released?

Tk-Instruct was published in October 2022. 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 Tk-Instruct used for?

Tk-Instruct works in Language, and is recorded as handling instruction interpretation. These are the areas it was designed around; they describe intent rather than a hard boundary.

Where can I download Tk-Instruct?

The weights for Tk-Instruct 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 Tk-Instruct 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 Tk-Instruct is rarely worth using — the nearest miss we calculate is short by 2.0 GB. Every figure here assumes the whole model is on the card.

Would two GPUs run Tk-Instruct faster?

Capacity adds across cards; throughput does not. Since 509 of the cards we track already hold Tk-Instruct on their own, a second card is rarely the answer here.

Why does the quantisation differ between cards for Tk-Instruct?

A larger card holds a more accurate copy. Across the cards that run Tk-Instruct, 4 compression levels are used; the floor control above pins it to one.

How accurate are these Tk-Instruct 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 185–493 tok/s on the B200 rather than a single number.

What GPU do I need to run Tk-Instruct?

The smallest card in our catalogue that holds Tk-Instruct is the Xeon Phi 5110P, with 8 GB of memory. It runs the model at IQ4_XS using about 6.7 GB, and produces roughly 19.7 tokens per second. 509 cards in total can run it.

How fast is Tk-Instruct on a GPU?

It depends on the card. The quickest we calculate is a B200 at about 308 tokens per second; the slowest that still runs it manages considerably less. Reading speed is around ten tokens per second, and 460 of the cards that can run Tk-Instruct clear that.

How much VRAM does Tk-Instruct need?

About 6.7 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.

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