Tulu V2 DPO 70B TPS calculator

Open weights Allen Institute for AI,University of Washington 70B parameters November 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

61 cards that can run it

818 cards we hold specifications for

Smallest card that fits

A100 PCIe 40 GB

40 GB · Q3_K_M · 25.5 tok/s

Fastest card

B200

48.4 tok/s · 180 GB

Which GPUs can run Tulu V2 DPO 70B?

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

61 cards match

Calculating

					Needs	Quantisation	Fit
48.4 tok/s 29–77 · low confidence	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	75.6 GB	Q8_0	Comfortable
48.4 tok/s 29–77 · low confidence	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	75.6 GB	Q8_0	Comfortable
38.7 tok/s 23–62 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	75.6 GB	Q8_0	Comfortable
38.7 tok/s 23–62 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	75.6 GB	Q8_0	Comfortable
30.9 tok/s 19–49 · low confidence	Radeon Instinct MI300 AMD	128 GB	6,550 GB/s	Jan 2023	75.6 GB	Q8_0	Comfortable
29.6 tok/s 18–47 · low confidence	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	75.6 GB	Q8_0	Comfortable
29.6 tok/s 18–47 · low confidence	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	75.6 GB	Q8_0	Comfortable
29.5 tok/s 18–47 · low confidence	H100 SXM5 80 GB NVIDIA	80 GB	3,360 GB/s	Oct 2022	59.3 GB	Q6_K	Comfortable
29.5 tok/s 18–47 · low confidence	H800 SXM5 NVIDIA	80 GB	3,360 GB/s	Mar 2023	59.3 GB	Q6_K	Comfortable
28.3 tok/s 17–45 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	75.6 GB	Q8_0	Comfortable
26.1 tok/s 16–42 · low confidence	GRID A100B NVIDIA	48 GB	1,870 GB/s	May 2020	43.0 GB	Q4_K_M	Tight
25.5 tok/s 15–41 · low confidence	A100 PCIe 40 GB NVIDIA	40 GB	1,560 GB/s	Jun 2020	34.9 GB	Q3_K_M	Tight
25.5 tok/s 15–41 · low confidence	A100 SXM4 40 GB NVIDIA	40 GB	1,560 GB/s	May 2020	34.9 GB	Q3_K_M	Tight
25.5 tok/s 15–41 · low confidence	A800 PCIe 40 GB NVIDIA	40 GB	1,560 GB/s	Nov 2022	34.9 GB	Q3_K_M	Tight
25.1 tok/s 15–40 · low confidence	Radeon Instinct MI300A AMD	128 GB	5,325 GB/s	Dec 2023	75.6 GB	Q8_0	Comfortable
25.1 tok/s 15–40 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	75.6 GB	Q8_0	Comfortable
25.1 tok/s 15–40 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	75.6 GB	Q8_0	Comfortable
23.8 tok/s 14–38 · low confidence	H100 NVL 94 GB NVIDIA	94 GB	3,940 GB/s	Mar 2023	75.6 GB	Q8_0	Tight
21.8 tok/s 13–35 · low confidence	H100 SXM5 64 GB NVIDIA	64 GB	2,020 GB/s	Mar 2023	51.2 GB	Q5_K_M	Tight
20.3 tok/s 12–33 · low confidence	H100 PCIe 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	75.6 GB	Q8_0	Tight
20.3 tok/s 12–33 · low confidence	H100 SXM5 94 GB NVIDIA	94 GB	3,360 GB/s	Mar 2023	75.6 GB	Q8_0	Tight
20.3 tok/s 12–33 · low confidence	H100 SXM5 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	75.6 GB	Q8_0	Tight
18.7 tok/s 11–30 · low confidence	RTX PRO 5000 Blackwell NVIDIA	48 GB	1,340 GB/s	Mar 2025	43.0 GB	Q4_K_M	Tight
17.9 tok/s 11–29 · low confidence	A100 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Nov 2020	59.3 GB	Q6_K	Comfortable
17.9 tok/s 11–29 · low confidence	A100X NVIDIA	80 GB	2,040 GB/s	Jun 2021	59.3 GB	Q6_K	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: 20 November 2023
Authors: Hamish Ivison, Yizhong Wang, Valentina Pyatkin, Nathan Lambert, Matthew Peters, Pradeep Dasigi, Joel Jang, David Wadden, Noah A. Smith, Iz Beltagy, 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 2-70B
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: 70B
Training data: tokens
Epochs: 3

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,Operation counting
Fine-tuning compute: 5.7 × 10²¹ 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
Chips used: 512
Wall-clock time: 168 hours (7 days)
Power draw: 457.0 kW
Cloud vendor: Google Cloud

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

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: Camels in a Changing Climate: Enhancing LM Adaptation with Tulu 2
Last updated: 28 November 2025

The extremes

The ten fastest GPUs that run Tulu V2 DPO 70B

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 V2 DPO 70B

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

A100 PCIe 40 GB

Memory needed

34.9 GB

Fastest

48.4 tok/s

Tulu V2 DPO 70B sits at 70B parameters, which puts it above consumer hardware and into the range where a card is bought for this purpose rather than repurposed for it. 61 of the cards we track can hold it.

The least hardware that works is a A100 PCIe 40 GB. Its 40 GB is enough at Q3_K_M compression, giving roughly 25.5 tokens per second.

At the other end, a B200 generates roughly 48.4 tokens per second on it, on the strength of 8,000 GB/s of memory bandwidth.

Background

Tulu V2 DPO 70B was published by Allen Institute for AI,University of Washington, in United States of America, in November 2023. It comes out of research collective,Academia.

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

It is derived from Llama 2-70B rather than trained from scratch, which is the usual way a specialised model is produced.

The weights being open is what puts this page in the calculator rather than only in the catalogue: it is a model you can actually hold.

Reading the throughput figures

The median result is around 17.1 tokens per second; 50 cards produce text faster than most people read it.

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.

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 V2 DPO 70B

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

Look at what Tulu V2 DPO 70B actually needs — around 34.9 GB at Q3_K_M. No amount of processing power compensates for a card that cannot hold it.
02

Decide how long your conversations run

The conversation occupies memory too, and grows as it goes. Set the slider to the length you expect: at long context Tulu V2 DPO 70B can slip off a card that handles short questions easily.
03

Choose how far you will compress it

Each card runs the least-compressed copy it can hold — Q3_K_M on the smallest card that fits. Setting a floor drops the cards that only manage Tulu V2 DPO 70B by squeezing it further than you would want.
04

Rank by throughput rather than spec sheet

Ranking by tokens per second for Tulu V2 DPO 70B follows memory bandwidth, not core counts, which is why the B200 tops it at 48.4 tok/s.
05

Read the fit column last

A tight fit runs Tulu V2 DPO 70B 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

Following a card through to its own page shows every other model it can hold, which is the question that follows once Tulu V2 DPO 70B is settled.

Answers

Tulu V2 DPO 70B — common questions

What GPU do I need to run Tulu V2 DPO 70B?

The smallest card in our catalogue that holds Tulu V2 DPO 70B is the A100 PCIe 40 GB, with 40 GB of memory. It runs the model at Q3_K_M using about 34.9 GB, and produces roughly 25.5 tokens per second. 61 cards in total can run it.

How fast is Tulu V2 DPO 70B on a GPU?

It depends on the card. The quickest we calculate is a B200 at about 48.4 tokens per second; the slowest that still runs it manages considerably less. Reading speed is around ten tokens per second, and 50 of the cards that can run Tulu V2 DPO 70B clear that.

How much VRAM does Tulu V2 DPO 70B need?

About 34.9 GB at Q3_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.

Is Tulu V2 DPO 70B open source?

Its weights are published, so Tulu V2 DPO 70B 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 V2 DPO 70B have?

Tulu V2 DPO 70B has 70B parameters. 70B. 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 V2 DPO 70B?

Tulu V2 DPO 70B was published by Allen Institute for AI,University of Washington, based in United States of America, categorised as research collective,Academia.

When was Tulu V2 DPO 70B released?

Tulu V2 DPO 70B was published in November 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 Tulu V2 DPO 70B used for?

Tulu V2 DPO 70B works in Language, and is recorded as handling language modeling/generation, Question answering. These are the areas it was designed around; they describe intent rather than a hard boundary.

Where can I download Tulu V2 DPO 70B?

The weights for Tulu V2 DPO 70B 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 Tulu V2 DPO 70B if it does not fit in my GPU?

It can be split between the card and system memory, but Tulu V2 DPO 70B generates painfully slowly that way — the nearest miss we calculate is short by 14.2 GB. Nothing on this page assumes offloading.

Would two GPUs run Tulu V2 DPO 70B faster?

A second card roughly doubles the memory available but not the generation rate. With 61 cards already able to run Tulu V2 DPO 70B alone, the case for pairing is weak.

Why does the quantisation differ between cards for Tulu V2 DPO 70B?

A larger card holds a more accurate copy. Across the cards that run Tulu V2 DPO 70B, 5 compression levels are used; the floor control above pins it to one.

How accurate are these Tulu V2 DPO 70B speed estimates?

These are estimates with real error bars. The fastest result here, 29–77 tok/s on the B200, could reasonably land anywhere in its published range depending on which runtime you use.

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