llama-3-airoboros-70b-3.3 TPS calculator

Open weights 70B parameters May 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 · 25.5 tok/s

Fastest card

B200

48.4 tok/s · 180 GB

Which GPUs can run llama-3-airoboros-70b-3.3?

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 41–58	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	73.8 GB	Q8_0	Comfortable
48.4 tok/s 41–58	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	73.8 GB	Q8_0	Comfortable
38.7 tok/s 23–62 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	73.8 GB	Q8_0	Comfortable
38.7 tok/s 23–62 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	73.8 GB	Q8_0	Comfortable
30.9 tok/s 19–49 · low confidence	Radeon Instinct MI300 AMD	128 GB	6,550 GB/s	Jan 2023	73.8 GB	Q8_0	Comfortable
29.6 tok/s 25–36	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	73.8 GB	Q8_0	Comfortable
29.6 tok/s 25–36	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	73.8 GB	Q8_0	Comfortable
29.5 tok/s 25–35	H100 SXM5 80 GB NVIDIA	80 GB	3,360 GB/s	Oct 2022	57.5 GB	Q6_K	Comfortable
29.5 tok/s 25–35	H800 SXM5 NVIDIA	80 GB	3,360 GB/s	Mar 2023	57.5 GB	Q6_K	Comfortable
28.3 tok/s 17–45 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	73.8 GB	Q8_0	Comfortable
26.1 tok/s 22–31	GRID A100B NVIDIA	48 GB	1,870 GB/s	May 2020	41.2 GB	Q4_K_M	Tight
25.5 tok/s 22–31	A100 PCIe 40 GB NVIDIA	40 GB	1,560 GB/s	Jun 2020	33.0 GB	Q3_K_M	Tight
25.5 tok/s 22–31	A100 SXM4 40 GB NVIDIA	40 GB	1,560 GB/s	May 2020	33.0 GB	Q3_K_M	Tight
25.5 tok/s 22–31	A800 PCIe 40 GB NVIDIA	40 GB	1,560 GB/s	Nov 2022	33.0 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	73.8 GB	Q8_0	Comfortable
25.1 tok/s 15–40 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	73.8 GB	Q8_0	Comfortable
25.1 tok/s 15–40 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	73.8 GB	Q8_0	Comfortable
23.8 tok/s 20–29	H100 NVL 94 GB NVIDIA	94 GB	3,940 GB/s	Mar 2023	73.8 GB	Q8_0	Tight
20.3 tok/s 17–24	H100 PCIe 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	73.8 GB	Q8_0	Tight
20.3 tok/s 17–24	H100 SXM5 94 GB NVIDIA	94 GB	3,360 GB/s	Mar 2023	73.8 GB	Q8_0	Tight
20.3 tok/s 17–24	H100 SXM5 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	73.8 GB	Q8_0	Tight
18.7 tok/s 16–22	RTX PRO 5000 Blackwell NVIDIA	48 GB	1,340 GB/s	Mar 2025	41.2 GB	Q4_K_M	Tight
17.9 tok/s 15–22	A100 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Nov 2020	57.5 GB	Q6_K	Comfortable
17.9 tok/s 15–22	A100X NVIDIA	80 GB	2,040 GB/s	Jun 2021	57.5 GB	Q6_K	Comfortable
17.9 tok/s 15–22	A800 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Aug 2022	57.5 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.

Published: 12 May 2024
Authors: Jon Durbin

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 3-70B

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

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 RTX A6000
Chips used: 2
Power draw: 1.2 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 (restricted use)
Training code: Open source
Hugging Face: jondurbin

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: airoboros: using large language models to fine-tune large language models
Last updated: 28 November 2025

The extremes

The ten fastest GPUs that run llama-3-airoboros-70b-3.3

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 llama-3-airoboros-70b-3.3

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 it takes to run this model

Minimum card

A100 PCIe 40 GB

Memory needed

33.0 GB

Fastest

48.4 tok/s

llama-3-airoboros-70b-3.3 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 smallest card that holds it is the A100 PCIe 40 GB with 40 GB, running it at Q3_K_M and producing around 25.5 tokens per second.

A B200 is the fastest we calculate for it: about 48.4 tokens per second, from 8,000 GB/s of memory bandwidth.

What this model is

llama-3-airoboros-70b-3.3 was published by its authors, in May 2024.

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

It builds on Llama 3-70B, which is why it shares that model's general shape and size.

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 jondurbin organisation on Hugging Face.

What decides the speed

Across every card that can run it, the middle of the range is about 17.1 tokens per second, and 49 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.

Because the architecture is recorded, the memory column is derived rather than estimated.

Step by step

How to choose a GPU for llama-3-airoboros-70b-3.3

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 llama-3-airoboros-70b-3.3 actually needs — around 33.0 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 llama-3-airoboros-70b-3.3 can slip off a card that handles short questions easily.
03

Choose how far you will compress it

Compression is what makes llama-3-airoboros-70b-3.3 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

Compare tokens per second, not specifications

Sort by speed to see how cards rank for llama-3-airoboros-70b-3.3. It will not match a gaming ordering — generation is bound by memory bandwidth, which is why the B200 tops it at 48.4 tok/s.
05

Look at the headroom, not just the fit

Tight means llama-3-airoboros-70b-3.3 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

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 llama-3-airoboros-70b-3.3 is settled.

Answers

llama-3-airoboros-70b-3.3 — common questions

Can I run llama-3-airoboros-70b-3.3 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 12.4 GB. Our figures for llama-3-airoboros-70b-3.3 assume it is fully resident.

Would two GPUs run llama-3-airoboros-70b-3.3 faster?

A second card roughly doubles the memory available but not the generation rate. With 61 cards already able to run llama-3-airoboros-70b-3.3 alone, the case for pairing is weak.

Why does the quantisation differ between cards for llama-3-airoboros-70b-3.3?

Each card is shown running the least-compressed copy it can hold, and llama-3-airoboros-70b-3.3 appears at 4 different compression levels across the cards that fit it. Bigger cards get the more accurate version.

How accurate are these llama-3-airoboros-70b-3.3 speed estimates?

They are calculated from specifications rather than measured, and each carries a range — 41–58 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 llama-3-airoboros-70b-3.3?

The smallest card in our catalogue that holds llama-3-airoboros-70b-3.3 is the A100 PCIe 40 GB, with 40 GB of memory. It runs the model at Q3_K_M using about 33.0 GB, and produces roughly 25.5 tokens per second. 61 cards in total can run it.

How fast is llama-3-airoboros-70b-3.3 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 49 of the cards that can run llama-3-airoboros-70b-3.3 clear that.

How much VRAM does llama-3-airoboros-70b-3.3 need?

About 33.0 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 llama-3-airoboros-70b-3.3 open source?

Its weights are published, so llama-3-airoboros-70b-3.3 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 llama-3-airoboros-70b-3.3 have?

llama-3-airoboros-70b-3.3 has 70B parameters. same as llama 3 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.

When was llama-3-airoboros-70b-3.3 released?

llama-3-airoboros-70b-3.3 was published in May 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 llama-3-airoboros-70b-3.3 used for?

llama-3-airoboros-70b-3.3 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 llama-3-airoboros-70b-3.3?

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

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