Janus-Pro-1B TPS calculator

Open weights DeepSeek 1B parameters January 2025

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 · 36.9 tok/s

Fastest card

B200

3,388 tok/s · 180 GB

Which GPUs can run Janus-Pro-1B?

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
3,388 tok/s 2,033–5,421 · low confidence	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	1.8 GB	Q8_0	Comfortable
3,388 tok/s 2,033–5,421 · low confidence	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	1.8 GB	Q8_0	Comfortable
2,706 tok/s 1,623–4,329 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	1.8 GB	Q8_0	Comfortable
2,706 tok/s 1,623–4,329 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	1.8 GB	Q8_0	Comfortable
2,164 tok/s 1,298–3,462 · low confidence	Radeon Instinct MI300 AMD	128 GB	6,550 GB/s	Jan 2023	1.8 GB	Q8_0	Comfortable
2,071 tok/s 1,243–3,314 · low confidence	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	1.8 GB	Q8_0	Comfortable
2,071 tok/s 1,243–3,314 · low confidence	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	1.8 GB	Q8_0	Comfortable
1,982 tok/s 1,189–3,171 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	1.8 GB	Q8_0	Comfortable
1,759 tok/s 1,055–2,815 · low confidence	Radeon Instinct MI300A AMD	128 GB	5,325 GB/s	Dec 2023	1.8 GB	Q8_0	Comfortable
1,759 tok/s 1,055–2,815 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	1.8 GB	Q8_0	Comfortable
1,759 tok/s 1,055–2,815 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	1.8 GB	Q8_0	Comfortable
1,669 tok/s 1,001–2,670 · low confidence	H100 NVL 94 GB NVIDIA	94 GB	3,940 GB/s	Mar 2023	1.8 GB	Q8_0	Comfortable
1,423 tok/s 854–2,277 · low confidence	H100 PCIe 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	1.8 GB	Q8_0	Comfortable
1,423 tok/s 854–2,277 · low confidence	H100 SXM5 80 GB NVIDIA	80 GB	3,360 GB/s	Oct 2022	1.8 GB	Q8_0	Comfortable
1,423 tok/s 854–2,277 · low confidence	H100 SXM5 94 GB NVIDIA	94 GB	3,360 GB/s	Mar 2023	1.8 GB	Q8_0	Comfortable
1,423 tok/s 854–2,277 · low confidence	H100 SXM5 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	1.8 GB	Q8_0	Comfortable
1,423 tok/s 854–2,277 · low confidence	H800 SXM5 NVIDIA	80 GB	3,360 GB/s	Mar 2023	1.8 GB	Q8_0	Comfortable
1,084 tok/s 650–1,734 · low confidence	Radeon Instinct MI250 AMD	128 GB	3,280 GB/s	Nov 2021	1.8 GB	Q8_0	Comfortable
1,084 tok/s 650–1,734 · low confidence	Radeon Instinct MI250X AMD	128 GB	3,280 GB/s	Nov 2021	1.8 GB	Q8_0	Comfortable
903 tok/s 542–1,445 · low confidence	Data Center GPU Max 1550 Intel	128 GB	3,280 GB/s	Jan 2023	1.8 GB	Q8_0	Comfortable
884 tok/s 530–1,414 · low confidence	Data Center GPU Max Subsystem Intel	128 GB	3,210 GB/s	Jan 2023	1.8 GB	Q8_0	Comfortable
864 tok/s 518–1,382 · low confidence	A100 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Nov 2020	1.8 GB	Q8_0	Comfortable
864 tok/s 518–1,382 · low confidence	A100X NVIDIA	80 GB	2,040 GB/s	Jun 2021	1.8 GB	Q8_0	Comfortable
864 tok/s 518–1,382 · low confidence	A800 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Aug 2022	1.8 GB	Q8_0	Comfortable
864 tok/s 518–1,382 · low confidence	H100 CNX NVIDIA	80 GB	2,040 GB/s	Mar 2023	1.8 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: DeepSeek
Organisation type: Industry
Country: China
Published: 27 January 2025
Authors: Xiaokang Chen, Zhiyu Wu, Xingchao Liu, Zizheng Pan, Wen Liu, Zhenda Xie, Xingkai Yu, Chong Ruan

What it does

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

Domain: Image generation, Vision, Language, Multimodal
Task: Image generation, Text-to-image, Visual question answering
Base model: SigLIP 400M,DeepSeek-LLM-1.3b-base

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: 1B
Training data: 817,889,280,000 tokens
Epochs: 1

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,Operation counting
Fine-tuning compute: 5.8 × 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 A100 SXM4 40 GB
Chips used: 8
Wall-clock time: 216 hours (9 days)
Power draw: 6.3 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)
Hugging Face: deepseek-ai

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: Janus-Pro: Unified Multimodal Understanding and Generation with Data and Model Scaling
Last updated: 28 November 2025

The extremes

The ten fastest GPUs that run Janus-Pro-1B

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 Janus-Pro-1B

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

1.8 GB

Fastest

3,388 tok/s

Janus-Pro-1B is small enough at 1B parameters that hardware is rarely the obstacle — 818 of the cards we track can run it, including cards several years old.

The smallest card that holds it is the Tesla C1080 with 4 GB, running it at Q8_0 and producing around 36.9 tokens per second.

At the other end, a B200 generates roughly 3,388 tokens per second on it, on the strength of 8,000 GB/s of memory bandwidth.

About this model

Janus-Pro-1B was published by DeepSeek, in China, in January 2025. industry is the category the publisher falls under.

It works in Image generation, Vision, Language, Multimodal, and is recorded as doing image generation, Text-to-image, Visual question answering.

It is derived from SigLIP 400M,DeepSeek-LLM-1.3b-base rather than trained from scratch, which is the usual way a specialised model is produced.

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 deepseek-ai organisation on Hugging Face.

How fast it runs, and why

Half the cards that hold it manage more than 95.1 tokens per second, and 806 exceed reading speed outright.

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.

How it was trained

It was trained on about 817,889,280,000 tokens of text.

Step by step

How to choose a GPU for Janus-Pro-1B

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

Every card here has been checked against Janus-Pro-1B — around 1.8 GB at Q8_0. Capacity is the gate — a card either holds it or it does not.
02

Match the context to your actual use

The conversation occupies memory too, and grows as it goes. Set the slider to the length you expect: at long context Janus-Pro-1B can slip off a card that handles short questions easily.
03

Decide how much compression you will accept

Each card runs the least-compressed copy it can hold — Q8_0 on the smallest card that fits. Setting a floor drops the cards that only manage Janus-Pro-1B by squeezing it further than you would want.
04

Rank by throughput rather than spec sheet

Sort by speed to see how cards rank for Janus-Pro-1B. It will not match a gaming ordering — generation is bound by memory bandwidth, which is why the B200 tops it at 3,388 tok/s.
05

Read the fit column last

The fit column separates cards that just manage Janus-Pro-1B from those with room to spare. Buy for the second if the context might grow.
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 Janus-Pro-1B is settled.

Answers

Janus-Pro-1B — common questions

How accurate are these Janus-Pro-1B speed estimates?

They are calculated from specifications rather than measured, and each carries a range — 2,033–5,421 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 Janus-Pro-1B?

The smallest card in our catalogue that holds Janus-Pro-1B is the Tesla C1080, with 4 GB of memory. It runs the model at Q8_0 using about 1.8 GB, and produces roughly 36.9 tokens per second. 818 cards in total can run it.

How fast is Janus-Pro-1B on a GPU?

It depends on the card. The quickest we calculate is a B200 at about 3,388 tokens per second; the slowest that still runs it manages considerably less. Reading speed is around ten tokens per second, and 806 of the cards that can run Janus-Pro-1B clear that.

How much VRAM does Janus-Pro-1B need?

About 1.8 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 Janus-Pro-1B on a 8 GB GPU?

Yes. A CMP 170HX 8 GB with 8 GB runs it at Q8_0, using about 1.8 GB and generating roughly 631 tokens per second — a comfortable fit.

Can I run Janus-Pro-1B on a 12 GB GPU?

Yes. A GeForce RTX 3080 Ti with 12 GB runs it at Q8_0, using about 1.8 GB and generating roughly 386 tokens per second — a comfortable fit.

Can I run Janus-Pro-1B on a 16 GB GPU?

Yes. A Tesla V100 SXM2 16 GB with 16 GB runs it at Q8_0, using about 1.8 GB and generating roughly 479 tokens per second — a comfortable fit.

Can I run Janus-Pro-1B on a 24 GB GPU?

Yes. A GeForce RTX 5090 D V2 with 24 GB runs it at Q8_0, using about 1.8 GB and generating roughly 568 tokens per second — a comfortable fit.

Is Janus-Pro-1B open source?

Its weights are published, so Janus-Pro-1B 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 Janus-Pro-1B have?

Janus-Pro-1B has 1B parameters. 1B In our experiments, we utilize DeepSeek-LLM (1.5B and 7B) [3] with a maximum supported sequence length of 4096 as the base language model. For the vision encoder used in understanding tasks, we select SigLIP-Large-Patch16-384 [53]. ** I am not sure which DeepSeek-LLM 1.5B they are referring to, there is no such model in the linked paper. 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 Janus-Pro-1B?

Janus-Pro-1B was published by DeepSeek, based in China, categorised as industry.

When was Janus-Pro-1B released?

Janus-Pro-1B was published in January 2025.

What is Janus-Pro-1B used for?

Janus-Pro-1B works in Image generation, Vision, Language, Multimodal, and is recorded as handling image generation, Text-to-image, Visual question answering. A model can carry several of each, so these are the areas it was built for rather than a limit on what it will attempt.

Where can I download Janus-Pro-1B?

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

Can I run Janus-Pro-1B 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 Janus-Pro-1B is rarely worth using. Every figure here assumes the whole model is on the card.

Would two GPUs run Janus-Pro-1B faster?

Capacity adds across cards; throughput does not. Since 818 of the cards we track already hold Janus-Pro-1B on their own, a second card is rarely the answer here.

Why does the quantisation differ between cards for Janus-Pro-1B?

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

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