Smaug-72B TPS calculator

Open weights Abacus AI 72B parameters July 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

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 · 24.8 tok/s

Fastest card

B200

47.1 tok/s · 180 GB

Which GPUs can run Smaug-72B?

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
47.1 tok/s 28–75 · low confidence	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	77.8 GB	Q8_0	Comfortable
47.1 tok/s 28–75 · low confidence	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	77.8 GB	Q8_0	Comfortable
37.6 tok/s 23–60 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	77.8 GB	Q8_0	Comfortable
37.6 tok/s 23–60 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	77.8 GB	Q8_0	Comfortable
30.1 tok/s 18–48 · low confidence	Radeon Instinct MI300 AMD	128 GB	6,550 GB/s	Jan 2023	77.8 GB	Q8_0	Comfortable
28.8 tok/s 17–46 · low confidence	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	77.8 GB	Q8_0	Comfortable
28.8 tok/s 17–46 · low confidence	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	77.8 GB	Q8_0	Comfortable
28.7 tok/s 17–46 · low confidence	H100 SXM5 80 GB NVIDIA	80 GB	3,360 GB/s	Oct 2022	61.0 GB	Q6_K	Tight
28.7 tok/s 17–46 · low confidence	H800 SXM5 NVIDIA	80 GB	3,360 GB/s	Mar 2023	61.0 GB	Q6_K	Tight
27.5 tok/s 17–44 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	77.8 GB	Q8_0	Comfortable
27.0 tok/s 16–43 · low confidence	GRID A100B NVIDIA	48 GB	1,870 GB/s	May 2020	40.1 GB	IQ4_XS	Tight
24.8 tok/s 15–40 · low confidence	A100 PCIe 40 GB NVIDIA	40 GB	1,560 GB/s	Jun 2020	35.9 GB	Q3_K_M	Tight
24.8 tok/s 15–40 · low confidence	A100 SXM4 40 GB NVIDIA	40 GB	1,560 GB/s	May 2020	35.9 GB	Q3_K_M	Tight
24.8 tok/s 15–40 · low confidence	A800 PCIe 40 GB NVIDIA	40 GB	1,560 GB/s	Nov 2022	35.9 GB	Q3_K_M	Tight
24.4 tok/s 15–39 · low confidence	Radeon Instinct MI300A AMD	128 GB	5,325 GB/s	Dec 2023	77.8 GB	Q8_0	Comfortable
24.4 tok/s 15–39 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	77.8 GB	Q8_0	Comfortable
24.4 tok/s 15–39 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	77.8 GB	Q8_0	Comfortable
23.2 tok/s 14–37 · low confidence	H100 NVL 94 GB NVIDIA	94 GB	3,940 GB/s	Mar 2023	77.8 GB	Q8_0	Tight
21.2 tok/s 13–34 · low confidence	H100 SXM5 64 GB NVIDIA	64 GB	2,020 GB/s	Mar 2023	52.6 GB	Q5_K_M	Tight
19.8 tok/s 12–32 · low confidence	H100 PCIe 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	77.8 GB	Q8_0	Tight
19.8 tok/s 12–32 · low confidence	H100 SXM5 94 GB NVIDIA	94 GB	3,360 GB/s	Mar 2023	77.8 GB	Q8_0	Tight
19.8 tok/s 12–32 · low confidence	H100 SXM5 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	77.8 GB	Q8_0	Tight
19.4 tok/s 12–31 · low confidence	RTX PRO 5000 Blackwell NVIDIA	48 GB	1,340 GB/s	Mar 2025	40.1 GB	IQ4_XS	Tight
17.4 tok/s 10–28 · low confidence	A100 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Nov 2020	61.0 GB	Q6_K	Tight
17.4 tok/s 10–28 · low confidence	A100X NVIDIA	80 GB	2,040 GB/s	Jun 2021	61.0 GB	Q6_K	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: Abacus AI
Organisation type: Industry
Country: United States of America
Published: 3 July 2024
Authors: Arka Pal, Deep Karkhanis, Samuel Dooley, Manley Roberts, Siddartha Naidu, Colin White

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: Qwen-72B

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: 72B
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: 8.2 × 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
Chips used: 8
Wall-clock time: 96 hours
Power draw: 11.1 kW

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: Unreleased
Hugging Face: abacusai

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: Smaug: Fixing Failure Modes of Preference Optimisation with DPO-Positive
Last updated: 28 November 2025

The extremes

The ten fastest GPUs that run Smaug-72B

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 Smaug-72B

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

The hardware side

Minimum card

A100 PCIe 40 GB

Memory needed

35.9 GB

Fastest

47.1 tok/s

Smaug-72B sits at 72B 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.

At the low end, a A100 PCIe 40 GB handles it — 40 GB, at Q3_K_M, for about 24.8 tokens per second.

The quickest result comes from a B200 at around 47.1 tokens per second — its 8,000 GB/s of bandwidth is what buys that.

About this model

Smaug-72B was published by Abacus AI, in United States of America, in July 2024. It comes out of industry.

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

Its starting point was Qwen-72B — most models at this scale are adapted from an existing base rather than built from nothing.

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. It is published under the abacusai organisation on Hugging Face.

How fast it runs, and why

Across every card that can run it, the middle of the range is about 16.6 tokens per second, and 51 of them clear the ten tokens per second that roughly matches reading speed.

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

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 Smaug-72B

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

Look at what Smaug-72B actually needs — around 35.9 GB at Q3_K_M. No amount of processing power compensates for a card that cannot hold it.
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 Smaug-72B can slip off a card that handles short questions easily.
03

Set a quality floor

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 Smaug-72B by squeezing it further than you would want.
04

Sort by speed

The speed ordering for Smaug-72B is effectively an ordering by memory bandwidth, which is why the B200 tops it at 47.1 tok/s.
05

Read the fit column last

The fit column separates cards that just manage Smaug-72B from those with room to spare. Buy for the second if the context might grow.
06

Check the card from the other side

Each card page repeats this sweep for every model we hold. It answers what else the hardware is good for, beyond Smaug-72B.

Answers

Smaug-72B — common questions

How fast is Smaug-72B on a GPU?

It depends on the card. The quickest we calculate is a B200 at about 47.1 tokens per second; the slowest that still runs it manages considerably less. Reading speed is around ten tokens per second, and 51 of the cards that can run Smaug-72B clear that.

How much VRAM does Smaug-72B need?

About 35.9 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 Smaug-72B open source?

Its weights are published, so Smaug-72B 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 Smaug-72B have?

Smaug-72B has 72B parameters. For 72B, we start from MoMo-72b-lora-1.8.7-DPO [Moreh, 2024], which itself is a fine-tune of Qwen72B [Bai et al., 2023]. MoMo-72b-lora-1.8.7-DPO has already undergone SFT, so we simply run the DPOP routines as in Smaug-34B. 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 Smaug-72B?

Smaug-72B was published by Abacus AI, based in United States of America, categorised as industry.

When was Smaug-72B released?

Smaug-72B was published in July 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 Smaug-72B used for?

Smaug-72B 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 Smaug-72B?

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

Can I run Smaug-72B 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 Smaug-72B is rarely worth using — the nearest miss we calculate is short by 15.5 GB. Every figure here assumes the whole model is on the card.

Would two GPUs run Smaug-72B faster?

A second card roughly doubles the memory available but not the generation rate. With 61 cards already able to run Smaug-72B alone, the case for pairing is weak.

Why does the quantisation differ between cards for Smaug-72B?

A larger card holds a more accurate copy. Across the cards that run Smaug-72B, 5 compression levels are used; the floor control above pins it to one.

How accurate are these Smaug-72B speed estimates?

They are calculated from specifications rather than measured, and each carries a range — 28–75 tok/s on the B200, for instance. The same model and card vary by thirty to fifty per cent depending on the inference software and its version.

What GPU do I need to run Smaug-72B?

The smallest card in our catalogue that holds Smaug-72B is the A100 PCIe 40 GB, with 40 GB of memory. It runs the model at Q3_K_M using about 35.9 GB, and produces roughly 24.8 tokens per second. 61 cards in total can run it.

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