Stable Cascade TPS calculator

Open weights Stability AI 5.1B parameters February 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

818 cards that can run it

818 cards we hold specifications for

Smallest card that fits

Tesla C1080

4 GB · IQ4_XS · 17.7 tok/s

Fastest card

B200

662 tok/s · 180 GB

Which GPUs can run Stable Cascade?

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

818 cards match

Calculating

					Needs	Quantisation	Fit
662 tok/s 397–1,059 · low confidence	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	6.2 GB	Q8_0	Comfortable
662 tok/s 397–1,059 · low confidence	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	6.2 GB	Q8_0	Comfortable
528 tok/s 317–846 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	6.2 GB	Q8_0	Comfortable
528 tok/s 317–846 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	6.2 GB	Q8_0	Comfortable
423 tok/s 254–676 · low confidence	Radeon Instinct MI300 AMD	128 GB	6,550 GB/s	Jan 2023	6.2 GB	Q8_0	Comfortable
405 tok/s 243–647 · low confidence	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	6.2 GB	Q8_0	Comfortable
405 tok/s 243–647 · low confidence	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	6.2 GB	Q8_0	Comfortable
387 tok/s 232–619 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	6.2 GB	Q8_0	Comfortable
344 tok/s 206–550 · low confidence	Radeon Instinct MI300A AMD	128 GB	5,325 GB/s	Dec 2023	6.2 GB	Q8_0	Comfortable
344 tok/s 206–550 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	6.2 GB	Q8_0	Comfortable
344 tok/s 206–550 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	6.2 GB	Q8_0	Comfortable
326 tok/s 196–521 · low confidence	H100 NVL 94 GB NVIDIA	94 GB	3,940 GB/s	Mar 2023	6.2 GB	Q8_0	Comfortable
278 tok/s 167–445 · low confidence	H100 PCIe 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	6.2 GB	Q8_0	Comfortable
278 tok/s 167–445 · low confidence	H100 SXM5 80 GB NVIDIA	80 GB	3,360 GB/s	Oct 2022	6.2 GB	Q8_0	Comfortable
278 tok/s 167–445 · low confidence	H100 SXM5 94 GB NVIDIA	94 GB	3,360 GB/s	Mar 2023	6.2 GB	Q8_0	Comfortable
278 tok/s 167–445 · low confidence	H100 SXM5 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	6.2 GB	Q8_0	Comfortable
278 tok/s 167–445 · low confidence	H800 SXM5 NVIDIA	80 GB	3,360 GB/s	Mar 2023	6.2 GB	Q8_0	Comfortable
212 tok/s 127–339 · low confidence	Radeon Instinct MI250 AMD	128 GB	3,280 GB/s	Nov 2021	6.2 GB	Q8_0	Comfortable
212 tok/s 127–339 · low confidence	Radeon Instinct MI250X AMD	128 GB	3,280 GB/s	Nov 2021	6.2 GB	Q8_0	Comfortable
176 tok/s 106–282 · low confidence	Data Center GPU Max 1550 Intel	128 GB	3,280 GB/s	Jan 2023	6.2 GB	Q8_0	Comfortable
173 tok/s 104–276 · low confidence	Data Center GPU Max Subsystem Intel	128 GB	3,210 GB/s	Jan 2023	6.2 GB	Q8_0	Comfortable
169 tok/s 101–270 · low confidence	A100 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Nov 2020	6.2 GB	Q8_0	Comfortable
169 tok/s 101–270 · low confidence	A100X NVIDIA	80 GB	2,040 GB/s	Jun 2021	6.2 GB	Q8_0	Comfortable
169 tok/s 101–270 · low confidence	A800 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Aug 2022	6.2 GB	Q8_0	Comfortable
169 tok/s 101–270 · low confidence	H100 CNX NVIDIA	80 GB	2,040 GB/s	Mar 2023	6.2 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: Stability AI
Organisation type: Industry
Country: United Kingdom of Great Britain and Northern Ireland
Published: 12 February 2024

What it does

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

Domain: Image generation
Task: Text-to-image, Image generation

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: 5.1B
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: Open source

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: Introducing Stable Cascade
Last updated: 28 November 2025

The extremes

The ten fastest GPUs that run Stable Cascade

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 Cascade

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

Tesla C1080

Memory needed

3.5 GB

Fastest

662 tok/s

Stable Cascade reaches a parameter count of 5.1B. That is small enough that hardware is rarely the obstacle, including on cards several years old. The number of cards we track that can run it: 818.

The smallest card that holds it is Tesla C1080, with a memory capacity of 4 GB, running it at a compression of IQ4_XS and producing around 17.7 tokens per second.

At the other end sits B200, generating roughly 662 tokens per second on the strength of a memory bandwidth of 8,000 GB/s.

What this model is

Stable Cascade was published by Stability AI, in the country recorded as United Kingdom of Great Britain and Northern Ireland, during February 2024. The category the publisher falls under is industry.

It works in the domain of Image generation, and is recorded as performing the task of text-to-image, Image generation.

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.

What decides the speed

Half the cards that hold it manage more than 26.4 tokens per second. Exceeding reading speed outright: 770 of them.

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.

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 Cascade

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

01

Start from the memory column

Start from what it actually needs, which is the requirement of Stable Cascade, needing around 3.5 GB at a compression of IQ4_XS. Capacity is the gate — a card either holds it or it does not.
02

Decide how long your conversations run

Set the context to what you will actually use. The cache grows with the conversation, and it is the usual reason a card that seemed fine stops fitting Stable Cascade.
03

Choose how far you will compress it

Compression is what makes a model fit smaller cards, at some cost in accuracy, reaching a compression of IQ4_XS on the smallest card that fits. Setting a minimum quality drops the cards that only manage it by squeezing further than you would want, and holds the comparison at one level.
04

Rank by throughput rather than spec sheet

Ranking by tokens per second follows memory bandwidth rather than core counts, for Stable Cascade. It will not match a gaming ordering, because generation is bound by memory bandwidth. The card topping the list is B200, at 662 tok/s.
05

Check the fit verdict before buying

A tight fit runs, but leaves nothing spare for a longer conversation, in the case of Stable Cascade. Comfortable means you can grow the context later. That difference matters more than a few tokens per second, so buy for comfortable if you expect to.
06

See what else that card runs

Each card page repeats this sweep for every model we hold, answering what else the hardware is good for beyond Stable Cascade.

Answers

Stable Cascade — common questions

Stable Cascade— what GPU do I need to run it?

The smallest card in our catalogue that holds it is Tesla C1080, with a memory capacity of 4 GB. It runs the model at a compression of IQ4_XS using about 3.5 GB, and produces roughly 17.7 tokens per second. The number of cards able to run it in total: 818.

Stable Cascade— how fast is it on a GPU?

It depends on the card. The quickest we calculate is B200, at about 662 tokens per second; the slowest that still runs it manages considerably less. Reading speed is around ten tokens per second, and the number of cards clearing that: 770.

Stable Cascade— how much VRAM does it need?

It needs about 3.5 GB at a compression of IQ4_XS, 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.

Stable Cascade— can I run it on a GPU holding 8 GB?

Yes. The card CMP 170HX 8 GB, holding 8 GB, runs it at a compression of Q8_0, using about 6.2 GB and generating roughly 123 tokens per second. The fit is tight.

Stable Cascade— can I run it on a GPU holding 12 GB?

Yes. The card GeForce RTX 3080 Ti, holding 12 GB, runs it at a compression of Q8_0, using about 6.2 GB and generating roughly 75.5 tokens per second. The fit is comfortable.

Stable Cascade— can I run it on a GPU holding 16 GB?

Yes. The card Tesla V100 SXM2 16 GB, holding 16 GB, runs it at a compression of Q8_0, using about 6.2 GB and generating roughly 93.5 tokens per second. The fit is comfortable.

Stable Cascade— can I run it on a GPU holding 24 GB?

Yes. The card GeForce RTX 5090 D V2, holding 24 GB, runs it at a compression of Q8_0, using about 6.2 GB and generating roughly 111 tokens per second. The fit is comfortable.

Stable Cascade— is it open source?

Its weights are published, so it 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.

Stable Cascade— how many parameters does it have?

It has a parameter count of 5.1B. "we are providing two checkpoints for Stage C, two for Stage B and one for Stage A. Stage C comes with a 1 billion and 3.6 billion parameter version, but we highly recommend using the 3.6 billion version, as most work was put into its finetuning. The two versions for Stage B amount to 700 million and 1.5 billion parameters. Both achieve great results, however the 1.5 billion excels at reconstructing small and fine details. Therefore, you will achieve the best results if you use the larger variant of each. Lastly, Stage A contains 20 million parameters and is fixed due to its small size." 3.6B + 1.5B + 20M = 5.12B. 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.

Stable Cascade— who created it?

It was published by Stability AI, based in United Kingdom of Great Britain and Northern Ireland, an organisation categorised as industry.

Stable Cascade— when was it released?

It was published in February 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.

Stable Cascade— what is it used for?

It works in the domain of Image generation, and is recorded as handling the task of text-to-image, Image generation. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.

Stable Cascade— where can I download it?

The weights are published, though we do not hold a repository link for it. This site calculates hardware requirements rather than hosting model files.

Stable Cascade— can I run it if it does not fit in my GPU?

Only by offloading, which is usually a false economy: the part held in system memory drags the whole thing down. Every figure here assumes the whole model is resident on the card.

Stable Cascade— would two GPUs run it faster?

Two cards buy memory rather than speed, which matters only if one card cannot hold it. The number that can: 818. So a second card is rarely the answer here.

Stable Cascade— why does the quantisation differ between cards?

Each card is shown running the least-compressed copy it can hold. The number of distinct compression levels across the cards that fit it: 4. Bigger cards get the more accurate version, and the quality floor above pins the comparison to one level.

Stable Cascade— how accurate are these speed estimates?

Every figure is derived from memory bandwidth and model size, not benchmarked, which is why each is published as a range rather than a single number. One example: 397–1,059 tok/s on B200. The same model and card vary by thirty to fifty per cent depending on the inference software and its version.

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