Tulu 3 8B TPS calculator

Open weights Allen Institute for AI,University of Washington 8B parameters November 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

582 cards that can run it

818 cards we hold specifications for

Smallest card that fits

Quadro 6000

6 GB · IQ4_XS · 15.9 tok/s

Fastest card

B200

424 tok/s · 180 GB

Which GPUs can run Tulu 3 8B?

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

582 cards match

Calculating

					Needs	Quantisation	Fit
424 tok/s 254–678 · low confidence	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	9.3 GB	Q8_0	Comfortable
424 tok/s 254–678 · low confidence	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	9.3 GB	Q8_0	Comfortable
338 tok/s 203–541 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	9.3 GB	Q8_0	Comfortable
338 tok/s 203–541 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	9.3 GB	Q8_0	Comfortable
270 tok/s 162–433 · low confidence	Radeon Instinct MI300 AMD	128 GB	6,550 GB/s	Jan 2023	9.3 GB	Q8_0	Comfortable
259 tok/s 155–414 · low confidence	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	9.3 GB	Q8_0	Comfortable
259 tok/s 155–414 · low confidence	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	9.3 GB	Q8_0	Comfortable
248 tok/s 149–396 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	9.3 GB	Q8_0	Comfortable
220 tok/s 132–352 · low confidence	Radeon Instinct MI300A AMD	128 GB	5,325 GB/s	Dec 2023	9.3 GB	Q8_0	Comfortable
220 tok/s 132–352 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	9.3 GB	Q8_0	Comfortable
220 tok/s 132–352 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	9.3 GB	Q8_0	Comfortable
209 tok/s 125–334 · low confidence	H100 NVL 94 GB NVIDIA	94 GB	3,940 GB/s	Mar 2023	9.3 GB	Q8_0	Comfortable
178 tok/s 107–285 · low confidence	H100 PCIe 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	9.3 GB	Q8_0	Comfortable
178 tok/s 107–285 · low confidence	H100 SXM5 80 GB NVIDIA	80 GB	3,360 GB/s	Oct 2022	9.3 GB	Q8_0	Comfortable
178 tok/s 107–285 · low confidence	H100 SXM5 94 GB NVIDIA	94 GB	3,360 GB/s	Mar 2023	9.3 GB	Q8_0	Comfortable
178 tok/s 107–285 · low confidence	H100 SXM5 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	9.3 GB	Q8_0	Comfortable
178 tok/s 107–285 · low confidence	H800 SXM5 NVIDIA	80 GB	3,360 GB/s	Mar 2023	9.3 GB	Q8_0	Comfortable
141 tok/s 85–225 · low confidence	CMP 170HX 8 GB NVIDIA	8 GB	1,490 GB/s	Sep 2021	6.5 GB	Q5_K_M	Tight
135 tok/s 81–217 · low confidence	Radeon Instinct MI250 AMD	128 GB	3,280 GB/s	Nov 2021	9.3 GB	Q8_0	Comfortable
135 tok/s 81–217 · low confidence	Radeon Instinct MI250X AMD	128 GB	3,280 GB/s	Nov 2021	9.3 GB	Q8_0	Comfortable
120 tok/s 72–192 · low confidence	CMP 170HX 10 GB NVIDIA	10 GB	1,560 GB/s	Sep 2021	7.4 GB	Q6_K	Comfortable
113 tok/s 68–181 · low confidence	Data Center GPU Max 1550 Intel	128 GB	3,280 GB/s	Jan 2023	9.3 GB	Q8_0	Comfortable
110 tok/s 66–177 · low confidence	Data Center GPU Max Subsystem Intel	128 GB	3,210 GB/s	Jan 2023	9.3 GB	Q8_0	Comfortable
108 tok/s 65–173 · low confidence	A100 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Nov 2020	9.3 GB	Q8_0	Comfortable
108 tok/s 65–173 · low confidence	A100X NVIDIA	80 GB	2,040 GB/s	Jun 2021	9.3 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: Allen Institute for AI,University of Washington
Organisation type: Research collective,Academia
Country: United States of America
Published: 21 November 2024
Authors: Nathan Lambert, Jacob Morrison, Valentina Pyatkin, Shengyi Huang, Hamish Ivison, Faeze Brahman, Lester James V. Miranda, Alisa Liu, Nouha Dziri, Shane Lyu, Yuling Gu, Saumya Malik, Victoria Graf, Jena D. Hwang, Jiangjiang Yang, Ronan Le Bras, Oyvind Tafjord, Chris Wilhelm, Luca Soldaini, Noah A. Smith, Yizhong Wang, Pradeep Dasigi, Hannaneh Hajishirzi

What it does

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

Domain: Language
Task: Language modeling/generation, Question answering
Base model: Llama 3.1-8B

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: 8B
Training data: 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.

How it was established: Hardware
Fine-tuning compute: 9.2 × 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 H100 SXM5 80GB
Chip-hours: 864

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 (restricted use)
Training code: Open source
Hugging Face: allenai

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: Tulu 3: Pushing Frontiers in Open Language Model Post-Training
Last updated: 28 November 2025

The extremes

The ten fastest GPUs that run Tulu 3 8B

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 Tulu 3 8B

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

Quadro 6000

Memory needed

5.1 GB

Fastest

424 tok/s

Tulu 3 8B is small enough at 8B parameters that hardware is rarely the obstacle — 582 of the cards we track can run it, including cards several years old.

The entry point is the Quadro 6000: 6 GB of memory, IQ4_XS compression, roughly 15.9 tokens per second.

A B200 is the fastest we calculate for it: about 424 tokens per second, from 8,000 GB/s of memory bandwidth.

What this model is

Tulu 3 8B was published by Allen Institute for AI,University of Washington, in United States of America, in November 2024. The organisation is categorised as research collective,Academia.

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

Its starting point was Llama 3.1-8B — most models at this scale are adapted from an existing base rather than built from nothing.

Because its weights were released, nothing about running it depends on a provider staying available — it is yours once downloaded. It is published under the allenai organisation on Hugging Face.

What decides the speed

Across every card that can run it, the middle of the range is about 23.8 tokens per second, and 551 of them clear the ten tokens per second that roughly matches reading speed.

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.

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.

Step by step

How to choose a GPU for Tulu 3 8B

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

Every card here has been checked against Tulu 3 8B — around 5.1 GB at IQ4_XS. Capacity is the gate — a card either holds it or it does not.
02

Set the context length you will work at

Longer conversations cost memory on top of what the weights need. Move the slider to your real working length before trusting any row for Tulu 3 8B.
03

Choose how far you will compress it

The quantisation column varies by card, because a bigger card holds a more accurate copy of Tulu 3 8B — IQ4_XS 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 Tulu 3 8B follows memory bandwidth, not core counts, which is why the B200 tops it at 424 tok/s.
05

Look at the headroom, not just the fit

A tight fit runs Tulu 3 8B but leaves nothing spare for a longer conversation; comfortable has headroom. If you expect to grow the context, buy for comfortable.
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 Tulu 3 8B alone — a card is usually bought for more than one model.

Answers

Tulu 3 8B — common questions

Can I run Tulu 3 8B on a 24 GB GPU?

Yes. A GeForce RTX 5090 D V2 with 24 GB runs it at Q8_0, using about 9.3 GB and generating roughly 70.9 tokens per second — a comfortable fit.

Is Tulu 3 8B open source?

Its weights are published, so Tulu 3 8B 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 Tulu 3 8B have?

Tulu 3 8B has 8B parameters. 8B. 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 Tulu 3 8B?

Tulu 3 8B was published by Allen Institute for AI,University of Washington, based in United States of America, categorised as research collective,Academia.

When was Tulu 3 8B released?

Tulu 3 8B was published in November 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 Tulu 3 8B used for?

Tulu 3 8B works in Language, and is recorded as handling language modeling/generation, Question answering. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.

Where can I download Tulu 3 8B?

Its weights are published under the allenai organisation on Hugging Face. We do not host model files — this site calculates what hardware is needed to run them.

Can I run Tulu 3 8B 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 Tulu 3 8B is rarely worth using — the nearest miss we calculate is short by 1.0 GB. Every figure here assumes the whole model is on the card.

Would two GPUs run Tulu 3 8B faster?

Two cards buy memory rather than speed. That matters for Tulu 3 8B only if one card cannot hold it — 582 can, so a second adds little.

Why does the quantisation differ between cards for Tulu 3 8B?

A larger card holds a more accurate copy. Across the cards that run Tulu 3 8B, 4 compression levels are used; the floor control above pins it to one.

How accurate are these Tulu 3 8B speed estimates?

These are estimates with real error bars. The fastest result here, 254–678 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 Tulu 3 8B?

The smallest card in our catalogue that holds Tulu 3 8B is the Quadro 6000, with 6 GB of memory. It runs the model at IQ4_XS using about 5.1 GB, and produces roughly 15.9 tokens per second. 582 cards in total can run it.

How fast is Tulu 3 8B on a GPU?

It depends on the card. The quickest we calculate is a B200 at about 424 tokens per second; the slowest that still runs it manages considerably less. Reading speed is around ten tokens per second, and 551 of the cards that can run Tulu 3 8B clear that.

How much VRAM does Tulu 3 8B need?

About 5.1 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 Tulu 3 8B on a 8 GB GPU?

Yes. A CMP 170HX 8 GB with 8 GB runs it at Q5_K_M, using about 6.5 GB and generating roughly 141 tokens per second — a tight fit.

Can I run Tulu 3 8B on a 12 GB GPU?

Yes. A GeForce RTX 3080 Ti with 12 GB runs it at Q8_0, using about 9.3 GB and generating roughly 48.3 tokens per second — a tight fit.

Can I run Tulu 3 8B on a 16 GB GPU?

Yes. A Tesla V100 SXM2 16 GB with 16 GB runs it at Q8_0, using about 9.3 GB and generating roughly 59.8 tokens per second — a comfortable fit.

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