SANA 1.6B TPS calculator

Open weights NVIDIA,Massachusetts Institute of Technology (MIT),Tsinghua University 1.6B parameters October 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 · Q8_0 · 22.4 tok/s

Fastest card

B200

2,056 tok/s · 180 GB

Which GPUs can run SANA 1.6B?

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
2,056 tok/s 1,234–3,290 · low confidence	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	2.5 GB	Q8_0	Comfortable
2,056 tok/s 1,234–3,290 · low confidence	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	2.5 GB	Q8_0	Comfortable
1,642 tok/s 985–2,627 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	2.5 GB	Q8_0	Comfortable
1,642 tok/s 985–2,627 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	2.5 GB	Q8_0	Comfortable
1,313 tok/s 788–2,101 · low confidence	Radeon Instinct MI300 AMD	128 GB	6,550 GB/s	Jan 2023	2.5 GB	Q8_0	Comfortable
1,257 tok/s 754–2,011 · low confidence	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	2.5 GB	Q8_0	Comfortable
1,257 tok/s 754–2,011 · low confidence	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	2.5 GB	Q8_0	Comfortable
1,203 tok/s 722–1,924 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	2.5 GB	Q8_0	Comfortable
1,067 tok/s 640–1,708 · low confidence	Radeon Instinct MI300A AMD	128 GB	5,325 GB/s	Dec 2023	2.5 GB	Q8_0	Comfortable
1,067 tok/s 640–1,708 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	2.5 GB	Q8_0	Comfortable
1,067 tok/s 640–1,708 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	2.5 GB	Q8_0	Comfortable
1,013 tok/s 608–1,620 · low confidence	H100 NVL 94 GB NVIDIA	94 GB	3,940 GB/s	Mar 2023	2.5 GB	Q8_0	Comfortable
864 tok/s 518–1,382 · low confidence	H100 PCIe 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	2.5 GB	Q8_0	Comfortable
864 tok/s 518–1,382 · low confidence	H100 SXM5 80 GB NVIDIA	80 GB	3,360 GB/s	Oct 2022	2.5 GB	Q8_0	Comfortable
864 tok/s 518–1,382 · low confidence	H100 SXM5 94 GB NVIDIA	94 GB	3,360 GB/s	Mar 2023	2.5 GB	Q8_0	Comfortable
864 tok/s 518–1,382 · low confidence	H100 SXM5 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	2.5 GB	Q8_0	Comfortable
864 tok/s 518–1,382 · low confidence	H800 SXM5 NVIDIA	80 GB	3,360 GB/s	Mar 2023	2.5 GB	Q8_0	Comfortable
658 tok/s 395–1,052 · low confidence	Radeon Instinct MI250 AMD	128 GB	3,280 GB/s	Nov 2021	2.5 GB	Q8_0	Comfortable
658 tok/s 395–1,052 · low confidence	Radeon Instinct MI250X AMD	128 GB	3,280 GB/s	Nov 2021	2.5 GB	Q8_0	Comfortable
548 tok/s 329–877 · low confidence	Data Center GPU Max 1550 Intel	128 GB	3,280 GB/s	Jan 2023	2.5 GB	Q8_0	Comfortable
536 tok/s 322–858 · low confidence	Data Center GPU Max Subsystem Intel	128 GB	3,210 GB/s	Jan 2023	2.5 GB	Q8_0	Comfortable
524 tok/s 315–839 · low confidence	A100 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Nov 2020	2.5 GB	Q8_0	Comfortable
524 tok/s 315–839 · low confidence	A100X NVIDIA	80 GB	2,040 GB/s	Jun 2021	2.5 GB	Q8_0	Comfortable
524 tok/s 315–839 · low confidence	A800 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Aug 2022	2.5 GB	Q8_0	Comfortable
524 tok/s 315–839 · low confidence	H100 CNX NVIDIA	80 GB	2,040 GB/s	Mar 2023	2.5 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: NVIDIA,Massachusetts Institute of Technology (MIT),Tsinghua University
Organisation type: Industry,Academia,Academia
Country: United States of America, China
Published: 14 October 2024
Authors: Enze Xie, Junsong Chen, Junyu Chen, Han Cai, Haotian Tang, Yujun Lin, Zhekai Zhang, Muyang Li, Ligeng Zhu, Yao Lu, Song Han

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: 1.6B
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
Hugging Face: Efficient-Large-Model

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: SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformers
Last updated: 28 November 2025

The extremes

The ten fastest GPUs that run SANA 1.6B

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 SANA 1.6B

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

Tesla C1080

Memory needed

2.5 GB

Fastest

2,056 tok/s

SANA 1.6B is small enough at 1.6B parameters that hardware is rarely the obstacle — 818 of the cards we track can run it, including cards several years old.

The entry point is the Tesla C1080: 4 GB of memory, Q8_0 compression, roughly 22.4 tokens per second.

A B200 is the fastest we calculate for it: about 2,056 tokens per second, from 8,000 GB/s of memory bandwidth.

What this model is

SANA 1.6B was published by NVIDIA,Massachusetts Institute of Technology (MIT),Tsinghua University, in United States of America, in October 2024. industry,Academia,Academia is the category the publisher falls under.

It works in Image generation, and is recorded as doing 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. It is published under the Efficient-Large-Model organisation on Hugging Face.

What decides the speed

Across every card that can run it, the middle of the range is about 57.7 tokens per second, and 794 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.

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 SANA 1.6B

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

Every card here has been checked against SANA 1.6B — around 2.5 GB at Q8_0. Capacity is the gate — a card either holds it or it does not.
02

Decide how long your conversations run

Longer conversations cost memory on top of what the weights need. Move the slider to your real working length before trusting any row for SANA 1.6B.
03

Decide how much compression you will accept

The quantisation column varies by card, because a bigger card holds a more accurate copy of SANA 1.6B — Q8_0 on the smallest card that fits. Set a floor to hold the comparison at one level.
04

Rank by throughput rather than spec sheet

The speed ordering for SANA 1.6B is effectively an ordering by memory bandwidth, which is why the B200 tops it at 2,056 tok/s.
05

Check the fit verdict before buying

Tight means SANA 1.6B 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

Following a card through to its own page shows every other model it can hold, which is the question that follows once SANA 1.6B is settled.

Answers

SANA 1.6B — common questions

How much VRAM does SANA 1.6B need?

About 2.5 GB at Q8_0 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 SANA 1.6B on a 8 GB GPU?

Yes. A CMP 170HX 8 GB with 8 GB runs it at Q8_0, using about 2.5 GB and generating roughly 383 tokens per second — a comfortable fit.

Can I run SANA 1.6B on a 12 GB GPU?

Yes. A GeForce RTX 3080 Ti with 12 GB runs it at Q8_0, using about 2.5 GB and generating roughly 234 tokens per second — a comfortable fit.

Can I run SANA 1.6B on a 16 GB GPU?

Yes. A Tesla V100 SXM2 16 GB with 16 GB runs it at Q8_0, using about 2.5 GB and generating roughly 290 tokens per second — a comfortable fit.

Can I run SANA 1.6B on a 24 GB GPU?

Yes. A GeForce RTX 5090 D V2 with 24 GB runs it at Q8_0, using about 2.5 GB and generating roughly 344 tokens per second — a comfortable fit.

Is SANA 1.6B open source?

Its weights are published, so SANA 1.6B 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 SANA 1.6B have?

SANA 1.6B has 1.6B parameters. 1648M parameters. 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 SANA 1.6B?

SANA 1.6B was published by NVIDIA,Massachusetts Institute of Technology (MIT),Tsinghua University, based in United States of America, categorised as industry,Academia,Academia.

When was SANA 1.6B released?

SANA 1.6B was published in October 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 SANA 1.6B used for?

SANA 1.6B works in Image generation, and is recorded as handling text-to-image, Image generation. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.

Where can I download SANA 1.6B?

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

Can I run SANA 1.6B 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. Our figures for SANA 1.6B assume it is fully resident.

Would two GPUs run SANA 1.6B faster?

A second card roughly doubles the memory available but not the generation rate. With 818 cards already able to run SANA 1.6B alone, the case for pairing is weak.

Why does the quantisation differ between cards for SANA 1.6B?

Because capacity varies, so does how hard SANA 1.6B has to be squeezed — 1 distinct levels appear in the table above. Set a minimum quality to compare at one.

How accurate are these SANA 1.6B 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 1,234–3,290 tok/s on the B200 rather than a single number.

What GPU do I need to run SANA 1.6B?

The smallest card in our catalogue that holds SANA 1.6B is the Tesla C1080, with 4 GB of memory. It runs the model at Q8_0 using about 2.5 GB, and produces roughly 22.4 tokens per second. 818 cards in total can run it.

How fast is SANA 1.6B on a GPU?

It depends on the card. The quickest we calculate is a B200 at about 2,056 tokens per second; the slowest that still runs it manages considerably less. Reading speed is around ten tokens per second, and 794 of the cards that can run SANA 1.6B clear that.

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