Tulu 3 405B TPS calculator

Open weights Allen Institute for AI,University of Washington 405B parameters January 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

4 of 818 cards that can run it

Smallest card that fits

Radeon Instinct MI325X

256 GB · IQ4_XS · 12.0 tok/s

Fastest card

B300

19.3 tok/s · 288 GB

Which GPUs can run Tulu 3 405B?

Set the inputs, read the answer

A longer conversation needs more memory, which can push this model off smaller cards.

Hides cards that would only fit the model by compressing it below this point.

4 cards match

Calculating
Needs Quantisation Fit
19.3 tok/s

12–31 · low confidence

B300 NVIDIA 288 GB 8,000 GB/s Sep 2025 245.7 GB Q4_K_M Tight
15.4 tok/s

9–25 · low confidence

Radeon Instinct MI350X AMD 288 GB 8,190 GB/s Jan 2025 245.7 GB Q4_K_M Tight
15.4 tok/s

9–25 · low confidence

Radeon Instinct MI355X AMD 288 GB 8,190 GB/s Jan 2025 245.7 GB Q4_K_M Tight
12.0 tok/s

7–19 · low confidence

Radeon Instinct MI325X AMD 256 GB 6,000 GB/s Oct 2024 222.1 GB IQ4_XS 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
Allen Institute for AI,University of Washington
Organisation type
Research collective,Academia
Country
United States of America
Published
30 January 2025
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, Quantitative reasoning
Base model
Llama 3.1-405B

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
405B

405B

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
3.8 × 10²² FLOP

SFT and DPO infrastructure usage is unknown RLVR: "the final 405B RL run takes 46 hours on 256 GPUs" 989400000000000 FLOP / GPU / sec [H100 reported, bf16 assumed] * 256 GPUs * 46 hours * 3600 sec / hour * 0.3 [assumed utilization] = 1.2583268e+22 FLOP Assuming that SFT and DPO training compute was same OOM as RLVR stage (similar to 70B model), 1.2583268e+22 FLOP * 3 = 3.7749804e+22 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

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

Llama 3.1 license https://huggingface.co/allenai/Llama-3.1-Tulu-3-405B Apache 2.0 https://github.com/allenai/open-instruct

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
Likely

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 for Tulu 3 405B

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.

  1. 01 B300 288 GB · 8,000 GB/s · Q4_K_M 19.3 tok/s
  2. 02 Radeon Instinct MI350X 288 GB · 8,190 GB/s · Q4_K_M 15.4 tok/s
  3. 03 Radeon Instinct MI355X 288 GB · 8,190 GB/s · Q4_K_M 15.4 tok/s
  4. 04 Radeon Instinct MI325X 256 GB · 6,000 GB/s · IQ4_XS 12.0 tok/s

What the numbers mean

The hardware side

Minimum card

Radeon Instinct MI325X

Memory needed

222.1 GB

Fastest

19.3 tok/s

At 405B parameters, Tulu 3 405B is beyond what any single graphics card holds. Running it means either splitting it across several cards or renting hardware built for the job — 4 of the cards we track can hold it on their own, and all of them are datacentre parts.

At the low end, a Radeon Instinct MI325X handles it — 256 GB, at IQ4_XS, for about 12.0 tokens per second.

At the other end, a B300 generates roughly 19.3 tokens per second on it, on the strength of 8,000 GB/s of memory bandwidth.

What this model is

Tulu 3 405B was published by Allen Institute for AI,University of Washington, in United States of America, in January 2025. It comes out of research collective,Academia.

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

It is derived from Llama 3.1-405B 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. It is published under the allenai organisation on Hugging Face.

What decides the speed

Half the cards that hold it manage more than 15.4 tokens per second, and 4 exceed reading speed outright.

Every weight participates in every token here, so bandwidth is the whole story: the ranking below is effectively a ranking of memory throughput.

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 405B

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

  1. 01

    Start from the memory column

    Look at what Tulu 3 405B actually needs — around 222.1 GB at IQ4_XS. No amount of processing power compensates for a card that cannot hold it.

  2. 02

    Set the context length you will work at

    The conversation occupies memory too, and grows as it goes. Set the slider to the length you expect: at long context Tulu 3 405B can slip off a card that handles short questions easily.

  3. 03

    Choose how far you will compress it

    Compression is what makes Tulu 3 405B fit smaller cards, at some cost in accuracy — IQ4_XS on the smallest card that fits. A minimum quality removes the ones that go too far.

  4. 04

    Rank by throughput rather than spec sheet

    The speed ordering for Tulu 3 405B is effectively an ordering by memory bandwidth, which is why the B300 tops it at 19.3 tok/s.

  5. 05

    Look at the headroom, not just the fit

    A tight fit runs Tulu 3 405B but leaves nothing spare for a longer conversation; comfortable has headroom. If you expect to grow the context, buy for comfortable.

  6. 06

    See what else that card runs

    Following a card through to its own page shows every other model it can hold, which is the question that follows once Tulu 3 405B is settled.

Answers

Tulu 3 405B — common questions

01

What is Tulu 3 405B used for?

Tulu 3 405B works in Language, and is recorded as handling language modeling/generation, Question answering, Quantitative reasoning. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.

02

Where can I download Tulu 3 405B?

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.

03

Can I run Tulu 3 405B 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 72.9 GB. Our figures for Tulu 3 405B assume it is fully resident.

04

Would two GPUs run Tulu 3 405B faster?

Two cards buy memory rather than speed. That matters for Tulu 3 405B only if one card cannot hold it — 4 can, so a second adds little.

05

Why does the quantisation differ between cards for Tulu 3 405B?

Because capacity varies, so does how hard Tulu 3 405B has to be squeezed — 2 distinct levels appear in the table above. Set a minimum quality to compare at one.

06

How accurate are these Tulu 3 405B speed estimates?

These are estimates with real error bars. The fastest result here, 12–31 tok/s on the B300, could reasonably land anywhere in its published range depending on which runtime you use.

07

What GPU do I need to run Tulu 3 405B?

The smallest card in our catalogue that holds Tulu 3 405B is the Radeon Instinct MI325X, with 256 GB of memory. It runs the model at IQ4_XS using about 222.1 GB, and produces roughly 12.0 tokens per second. 4 cards in total can run it.

08

How fast is Tulu 3 405B on a GPU?

It depends on the card. The quickest we calculate is a B300 at about 19.3 tokens per second; the slowest that still runs it manages considerably less. Reading speed is around ten tokens per second, and 4 of the cards that can run Tulu 3 405B clear that.

09

How much VRAM does Tulu 3 405B need?

About 222.1 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.

10

Is Tulu 3 405B open source?

Its weights are published, so Tulu 3 405B 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.

11

How many parameters does Tulu 3 405B have?

Tulu 3 405B has 405B parameters. 405B. 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.

12

Who created Tulu 3 405B?

Tulu 3 405B was published by Allen Institute for AI,University of Washington, based in United States of America, categorised as research collective,Academia.

13

When was Tulu 3 405B released?

Tulu 3 405B was published in January 2025.

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.