Olmo 3 32B Instruct TPS calculator

Open weights Allen Institute for AI,University of Washington,Carnegie Mellon University (CMU),Stanford University,Mila - Quebec AI (originally Montreal Institute for Learning Algorithms),University of Montreal / Université de Montréal,Princeton University,Massachusetts Institute of Technology (MIT),University of Maryland 32B parameters November 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

132 cards that can run it

818 cards we hold specifications for

Smallest card that fits

RTX A4500

20 GB · Q3_K_M · 22.9 tok/s

Fastest card

B200

106 tok/s · 180 GB

Which GPUs can run Olmo 3 32B 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

132 cards match

Calculating

					Needs	Quantisation	Fit
106 tok/s 64–169 · low confidence	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	35.0 GB	Q8_0	Comfortable
106 tok/s 64–169 · low confidence	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	35.0 GB	Q8_0	Comfortable
84.6 tok/s 51–135 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	35.0 GB	Q8_0	Comfortable
84.6 tok/s 51–135 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	35.0 GB	Q8_0	Comfortable
67.6 tok/s 41–108 · low confidence	Radeon Instinct MI300 AMD	128 GB	6,550 GB/s	Jan 2023	35.0 GB	Q8_0	Comfortable
64.7 tok/s 39–104 · low confidence	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	35.0 GB	Q8_0	Comfortable
64.7 tok/s 39–104 · low confidence	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	35.0 GB	Q8_0	Comfortable
61.9 tok/s 37–99 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	35.0 GB	Q8_0	Comfortable
55.0 tok/s 33–88 · low confidence	Radeon Instinct MI300A AMD	128 GB	5,325 GB/s	Dec 2023	35.0 GB	Q8_0	Comfortable
55.0 tok/s 33–88 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	35.0 GB	Q8_0	Comfortable
55.0 tok/s 33–88 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	35.0 GB	Q8_0	Comfortable
52.2 tok/s 31–83 · low confidence	H100 NVL 94 GB NVIDIA	94 GB	3,940 GB/s	Mar 2023	35.0 GB	Q8_0	Comfortable
44.5 tok/s 27–71 · low confidence	H100 PCIe 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	35.0 GB	Q8_0	Comfortable
44.5 tok/s 27–71 · low confidence	H100 SXM5 80 GB NVIDIA	80 GB	3,360 GB/s	Oct 2022	35.0 GB	Q8_0	Comfortable
44.5 tok/s 27–71 · low confidence	H100 SXM5 94 GB NVIDIA	94 GB	3,360 GB/s	Mar 2023	35.0 GB	Q8_0	Comfortable
44.5 tok/s 27–71 · low confidence	H100 SXM5 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	35.0 GB	Q8_0	Comfortable
44.5 tok/s 27–71 · low confidence	H800 SXM5 NVIDIA	80 GB	3,360 GB/s	Mar 2023	35.0 GB	Q8_0	Comfortable
40.9 tok/s 25–66 · low confidence	GeForce RTX 5090 D V2 NVIDIA	24 GB	1,340 GB/s	Aug 2025	20.1 GB	Q4_K_M	Tight
37.3 tok/s 22–60 · low confidence	A30X NVIDIA	24 GB	1,220 GB/s	Apr 2021	20.1 GB	Q4_K_M	Tight
36.0 tok/s 22–58 · low confidence	DRIVE A100 PROD NVIDIA	32 GB	1,870 GB/s	May 2020	27.5 GB	Q6_K	Tight
36.0 tok/s 22–58 · low confidence	GRID A100A NVIDIA	32 GB	1,870 GB/s	May 2020	27.5 GB	Q6_K	Tight
34.4 tok/s 21–55 · low confidence	GeForce RTX 5090 NVIDIA	32 GB	1,790 GB/s	Jan 2025	27.5 GB	Q6_K	Tight
34.4 tok/s 21–55 · low confidence	GeForce RTX 5090 D NVIDIA	32 GB	1,790 GB/s	Jan 2025	27.5 GB	Q6_K	Tight
33.9 tok/s 20–54 · low confidence	Radeon Instinct MI250 AMD	128 GB	3,280 GB/s	Nov 2021	35.0 GB	Q8_0	Comfortable
33.9 tok/s 20–54 · low confidence	Radeon Instinct MI250X AMD	128 GB	3,280 GB/s	Nov 2021	35.0 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,Carnegie Mellon University (CMU),Stanford University,Mila - Quebec AI (originally Montreal Institute for Learning Algorithms),University of Montreal / Université de Montréal,Princeton University,Massachusetts Institute of Technology (MIT),University of Maryland
Organisation type: Research collective,Academia,Academia,Academia,Academia,Academia,Academia,Academia,Academia
Country: United States of America, Canada
Published: 20 November 2025
Authors: Allyson Ettinger, Amanda Bertsch, Bailey Kuehl, David Graham, David Heineman, Dirk Groeneveld, Faeze Brahman, Finbarr Timbers, Hamish Ivison, Jacob Morrison, Jake Poznanski, Kyle Lo, Luca Soldaini, Matt Jordan, Mayee Chen, Michael Noukhovitch, Nathan Lambert, Pete Walsh, Pradeep Dasigi, Robert Berry, Saumya Malik, Saurabh Shah, Scott Geng, Shane Arora, Shashank Gupta, Taira Anderson, Teng Xiao, Ty…

What it does

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

Domain: Language
Task: Language modeling/generation, Chat, Code generation, Mathematical reasoning, Tool use

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: 32B
Training data: tokens

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
Chips used: 1,024
Power draw: 1.4 MW

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.

Record confidence: Likely

Sources

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

Reference: Olmo 3
Last updated: 8 April 2026

The extremes

The ten fastest GPUs that run Olmo 3 32B 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 Olmo 3 32B 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

Hardware requirements in practice

Minimum card

RTX A4500

Memory needed

16.3 GB

Fastest

106 tok/s

With 32B parameters, Olmo 3 32B Instruct lands in the range a serious desktop card can handle once the weights are compressed. 132 of the cards we track can run it.

The entry point is the RTX A4500: 20 GB of memory, Q3_K_M compression, roughly 22.9 tokens per second.

The quickest result comes from a B200 at around 106 tokens per second — its 8,000 GB/s of bandwidth is what buys that.

About this model

Olmo 3 32B Instruct was published by Allen Institute for AI,University of Washington,Carnegie Mellon University (CMU),Stanford University,Mila - Quebec AI (originally Montreal Institute for Learning Algorithms),University of Montreal / Université de Montréal,Princeton University,Massachusetts Institute of Technology (MIT),University of Maryland, in United States of America, in November 2025. research collective,Academia,Academia,Academia,Academia,Academia,Academia,Academia,Academia is the category the publisher falls under.

It works in Language, and is recorded as doing language modeling/generation, Chat, Code generation, Mathematical reasoning, Tool use.

The weights are published, so it can be downloaded and run on your own hardware indefinitely, offline, with no account attached.

How fast it runs, and why

Across every card that can run it, the middle of the range is about 20.7 tokens per second, and 103 of them clear the ten tokens per second that roughly matches reading speed.

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.

Step by step

How to choose a GPU for Olmo 3 32B Instruct

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

The table lists every card that can hold Olmo 3 32B Instruct — around 16.3 GB at Q3_K_M. 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 Olmo 3 32B Instruct stops fitting a card that seemed fine.
03

Set a quality floor

Compression is what makes Olmo 3 32B Instruct fit smaller cards, at some cost in accuracy — Q3_K_M on the smallest card that fits. A minimum quality removes the ones that go too far.
04

Sort by speed

The speed ordering for Olmo 3 32B Instruct is effectively an ordering by memory bandwidth, which is why the B200 tops it at 106 tok/s.
05

Read the fit column last

Tight means Olmo 3 32B Instruct loads and works, with no room to raise the context later. Comfortable means you can. The difference matters more than a few tokens per second.
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 Olmo 3 32B Instruct alone — a card is usually bought for more than one model.

Answers

Olmo 3 32B Instruct — common questions

Would two GPUs run Olmo 3 32B Instruct faster?

Capacity adds across cards; throughput does not. Since 132 of the cards we track already hold Olmo 3 32B Instruct on their own, a second card is rarely the answer here.

Why does the quantisation differ between cards for Olmo 3 32B Instruct?

A larger card holds a more accurate copy. Across the cards that run Olmo 3 32B Instruct, 5 compression levels are used; the floor control above pins it to one.

How accurate are these Olmo 3 32B 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 64–169 tok/s on the B200 rather than a single number.

What GPU do I need to run Olmo 3 32B Instruct?

The smallest card in our catalogue that holds Olmo 3 32B Instruct is the RTX A4500, with 20 GB of memory. It runs the model at Q3_K_M using about 16.3 GB, and produces roughly 22.9 tokens per second. 132 cards in total can run it.

How fast is Olmo 3 32B Instruct on a GPU?

It depends on the card. The quickest we calculate is a B200 at about 106 tokens per second; the slowest that still runs it manages considerably less. Reading speed is around ten tokens per second, and 103 of the cards that can run Olmo 3 32B Instruct clear that.

How much VRAM does Olmo 3 32B Instruct need?

About 16.3 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.

Can I run Olmo 3 32B Instruct on a 24 GB GPU?

Yes. A GeForce RTX 5090 D V2 with 24 GB runs it at Q4_K_M, using about 20.1 GB and generating roughly 40.9 tokens per second — a tight fit.

Is Olmo 3 32B Instruct open source?

Its weights are published, so Olmo 3 32B 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 Olmo 3 32B Instruct have?

Olmo 3 32B Instruct has 32B parameters. 7B and 32B variants. Dense transformer architecture. (https://arxiv.org/abs/2512.13961). 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 Olmo 3 32B Instruct?

Olmo 3 32B Instruct was published by Allen Institute for AI,University of Washington,Carnegie Mellon University (CMU),Stanford University,Mila - Quebec AI (originally Montreal Institute for Learning Algorithms),University of Montreal / Université de Montréal,Princeton University,Massachusetts Institute of Technology (MIT),University of Maryland, based in United States of America, categorised as research collective,Academia,Academia,Academia,Academia,Academia,Academia,Academia,Academia.

When was Olmo 3 32B Instruct released?

Olmo 3 32B Instruct was published in November 2025.

What is Olmo 3 32B Instruct used for?

Olmo 3 32B Instruct works in Language, and is recorded as handling language modeling/generation, Chat, Code generation, Mathematical reasoning, Tool use. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.

Where can I download Olmo 3 32B Instruct?

The weights for Olmo 3 32B 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 Olmo 3 32B 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 Olmo 3 32B Instruct is rarely worth using — the nearest miss we calculate is short by 5.7 GB. Every figure here assumes the whole model is on the card.

Source

Original publication

Record last updated 8 April 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