Stable Beluga 2 TPS calculator

Open weights Stability AI 70B parameters July 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 Stable Beluga 2?

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: Stability AI
Organisation type: Industry
Country: United Kingdom of Great Britain and Northern Ireland
Published: 20 July 2023

What it does

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

Domain: Language
Task: Language generation
Base model: Llama 2-70B

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

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 (non-commercial)
Training code: Unreleased

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: Meet Stable Beluga 1 and Stable Beluga 2, Our Large and Mighty Instruction Fine-Tuned Language Models
Last updated: 28 November 2025

The extremes

The ten fastest GPUs that run Stable Beluga 2

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 Stable Beluga 2

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

34.9 GB

Fastest

48.4 tok/s

Stable Beluga 2 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.

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

What this model is

Stable Beluga 2 was published by Stability AI, in United Kingdom of Great Britain and Northern Ireland, in July 2023. The organisation is categorised as industry.

It works in Language, and is recorded as doing language generation.

It builds on Llama 2-70B, which is why it shares that model's general shape and size.

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

What decides the speed

Half the cards that hold it manage more than 17.1 tokens per second, and 50 exceed reading speed outright.

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 Stable Beluga 2

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

The table lists every card that can hold Stable Beluga 2 — around 34.9 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 Stable Beluga 2 stops fitting a card that seemed fine.
03

Set a quality floor

Compression is what makes Stable Beluga 2 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

Rank by throughput rather than spec sheet

The speed ordering for Stable Beluga 2 is effectively an ordering by memory bandwidth, which is why the B200 tops it at 48.4 tok/s.
05

Check the fit verdict before buying

Tight means Stable Beluga 2 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 Stable Beluga 2 is settled.

Answers

Stable Beluga 2 — common questions

When was Stable Beluga 2 released?

Stable Beluga 2 was published in July 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 Stable Beluga 2 used for?

Stable Beluga 2 works in Language, and is recorded as handling language generation. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.

Where can I download Stable Beluga 2?

The weights for Stable Beluga 2 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 Stable Beluga 2 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 14.2 GB. Our figures for Stable Beluga 2 assume it is fully resident.

Would two GPUs run Stable Beluga 2 faster?

A second card roughly doubles the memory available but not the generation rate. With 61 cards already able to run Stable Beluga 2 alone, the case for pairing is weak.

Why does the quantisation differ between cards for Stable Beluga 2?

A larger card holds a more accurate copy. Across the cards that run Stable Beluga 2, 5 compression levels are used; the floor control above pins it to one.

How accurate are these Stable Beluga 2 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.

What GPU do I need to run Stable Beluga 2?

The smallest card in our catalogue that holds Stable Beluga 2 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 Stable Beluga 2 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 Stable Beluga 2 clear that.

How much VRAM does Stable Beluga 2 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 Stable Beluga 2 open source?

Its weights are published, so Stable Beluga 2 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 Stable Beluga 2 have?

Stable Beluga 2 has 70B parameters. fine-tuned from Llama 2-70B. 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 Stable Beluga 2?

Stable Beluga 2 was published by Stability AI, based in United Kingdom of Great Britain and Northern Ireland, categorised as industry.

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