Janus 1.3B TPS calculator

Open weights DeepSeek,The University of Hong Kong,Peking University 1.3B 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 of 818 cards that can run it

Smallest card that fits

Tesla C1080

4 GB · Q8_0 · 28.4 tok/s

Fastest card

B200

2,606 tok/s · 180 GB

Which GPUs can run Janus 1.3B?

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
2,606 tok/s 1,564–4,170 · low confidence	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	2.1 GB	Q8_0	Comfortable
2,606 tok/s 1,564–4,170 · low confidence	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	2.1 GB	Q8_0	Comfortable
2,081 tok/s 1,249–3,330 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	2.1 GB	Q8_0	Comfortable
2,081 tok/s 1,249–3,330 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	2.1 GB	Q8_0	Comfortable
1,664 tok/s 999–2,663 · low confidence	Radeon Instinct MI300 AMD	128 GB	6,550 GB/s	Jan 2023	2.1 GB	Q8_0	Comfortable
1,593 tok/s 956–2,549 · low confidence	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	2.1 GB	Q8_0	Comfortable
1,593 tok/s 956–2,549 · low confidence	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	2.1 GB	Q8_0	Comfortable
1,525 tok/s 915–2,440 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	2.1 GB	Q8_0	Comfortable
1,353 tok/s 812–2,165 · low confidence	Radeon Instinct MI300A AMD	128 GB	5,325 GB/s	Dec 2023	2.1 GB	Q8_0	Comfortable
1,353 tok/s 812–2,165 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	2.1 GB	Q8_0	Comfortable
1,353 tok/s 812–2,165 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	2.1 GB	Q8_0	Comfortable
1,284 tok/s 770–2,054 · low confidence	H100 NVL 94 GB NVIDIA	94 GB	3,940 GB/s	Mar 2023	2.1 GB	Q8_0	Comfortable
1,095 tok/s 657–1,751 · low confidence	H100 PCIe 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	2.1 GB	Q8_0	Comfortable
1,095 tok/s 657–1,751 · low confidence	H100 SXM5 80 GB NVIDIA	80 GB	3,360 GB/s	Oct 2022	2.1 GB	Q8_0	Comfortable
1,095 tok/s 657–1,751 · low confidence	H100 SXM5 94 GB NVIDIA	94 GB	3,360 GB/s	Mar 2023	2.1 GB	Q8_0	Comfortable
1,095 tok/s 657–1,751 · low confidence	H100 SXM5 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	2.1 GB	Q8_0	Comfortable
1,095 tok/s 657–1,751 · low confidence	H800 SXM5 NVIDIA	80 GB	3,360 GB/s	Mar 2023	2.1 GB	Q8_0	Comfortable
834 tok/s 500–1,334 · low confidence	Radeon Instinct MI250 AMD	128 GB	3,280 GB/s	Nov 2021	2.1 GB	Q8_0	Comfortable
834 tok/s 500–1,334 · low confidence	Radeon Instinct MI250X AMD	128 GB	3,280 GB/s	Nov 2021	2.1 GB	Q8_0	Comfortable
695 tok/s 417–1,111 · low confidence	Data Center GPU Max 1550 Intel	128 GB	3,280 GB/s	Jan 2023	2.1 GB	Q8_0	Comfortable
680 tok/s 408–1,088 · low confidence	Data Center GPU Max Subsystem Intel	128 GB	3,210 GB/s	Jan 2023	2.1 GB	Q8_0	Comfortable
665 tok/s 399–1,063 · low confidence	A100 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Nov 2020	2.1 GB	Q8_0	Comfortable
665 tok/s 399–1,063 · low confidence	A100X NVIDIA	80 GB	2,040 GB/s	Jun 2021	2.1 GB	Q8_0	Comfortable
665 tok/s 399–1,063 · low confidence	A800 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Aug 2022	2.1 GB	Q8_0	Comfortable
665 tok/s 399–1,063 · low confidence	H100 CNX NVIDIA	80 GB	2,040 GB/s	Mar 2023	2.1 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,The University of Hong Kong,Peking University
Organisation type: Industry,Academia,Academia
Country: China, Hong Kong
Published: 17 October 2024
Authors: Chengyue Wu, Xiaokang Chen, Zhiyu Wu, Yiyang Ma, Xingchao Liu, Zizheng Pan, Wen Liu, Zhenda Xie, Xingkai Yu, Chong Ruan, Ping Luo

What it does

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

Domain: Language, Vision, Multimodal
Task: Language modeling/generation, Question answering, Visual question answering
Base model: 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: 1.3B
Training data: tokens

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
Fine-tuning compute: 9.1 × 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: 16
Wall-clock time: 168 hours (7 days)
Power draw: 12.6 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: 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: Decoupling Visual Encoding for Unified Multimodal Understanding and Generation
Last updated: 28 November 2025

The extremes

The ten fastest GPUs for Janus 1.3B

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 1.3B

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

2.1 GB

Fastest

2,606 tok/s

Janus 1.3B is small enough at 1.3B 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 28.4 tokens per second.

A B200 is the fastest we calculate for it: about 2,606 tokens per second, from 8,000 GB/s of memory bandwidth.

Where it came from

Janus 1.3B was published by DeepSeek,The University of Hong Kong,Peking University, in China, in October 2024. The organisation is categorised as industry,Academia,Academia.

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

Its starting point was DeepSeek-LLM-1.3b-base — most models at this scale are adapted from an existing base rather than built from nothing.

Because its weights were released, nothing about running it depends on a provider staying available — it is yours once downloaded. It is published under the deepseek-ai organisation on Hugging Face.

Understanding the speeds

The median result is around 73.2 tokens per second; 797 cards produce text faster than most people read it.

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 Janus 1.3B

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

Every card here has been checked against Janus 1.3B — around 2.1 GB at Q8_0. Capacity is the gate — a card either holds it or it does not.
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 Janus 1.3B can slip off a card that handles short questions easily.
03

Decide how much compression you will accept

Compression is what makes Janus 1.3B fit smaller cards, at some cost in accuracy — Q8_0 on the smallest card that fits. A minimum quality removes the ones that go too far.
04

Sort by speed

The speed ordering for Janus 1.3B is effectively an ordering by memory bandwidth, which is why the B200 tops it at 2,606 tok/s.
05

Read the fit column last

The fit column separates cards that just manage Janus 1.3B from those with room to spare. Buy for the second if the context might grow.
06

Check the card from the other side

Each card page repeats this sweep for every model we hold. It answers what else the hardware is good for, beyond Janus 1.3B.

Answers

Janus 1.3B — common questions

Would two GPUs run Janus 1.3B faster?

Two cards buy memory rather than speed. That matters for Janus 1.3B only if one card cannot hold it — 818 can, so a second adds little.

Why does the quantisation differ between cards for Janus 1.3B?

A larger card holds a more accurate copy. Across the cards that run Janus 1.3B, 1 compression levels are used; the floor control above pins it to one.

How accurate are these Janus 1.3B speed estimates?

These are estimates with real error bars. The fastest result here, 1,564–4,170 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 Janus 1.3B?

The smallest card in our catalogue that holds Janus 1.3B is the Tesla C1080, with 4 GB of memory. It runs the model at Q8_0 using about 2.1 GB, and produces roughly 28.4 tokens per second. 818 cards in total can run it.

How fast is Janus 1.3B on a GPU?

It depends on the card. The quickest we calculate is a B200 at about 2,606 tokens per second; the slowest that still runs it manages considerably less. Reading speed is around ten tokens per second, and 797 of the cards that can run Janus 1.3B clear that.

How much VRAM does Janus 1.3B need?

About 2.1 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 1.3B on a 8 GB GPU?

Yes. A CMP 170HX 8 GB with 8 GB runs it at Q8_0, using about 2.1 GB and generating roughly 485 tokens per second — a comfortable fit.

Can I run Janus 1.3B on a 12 GB GPU?

Yes. A GeForce RTX 3080 Ti with 12 GB runs it at Q8_0, using about 2.1 GB and generating roughly 297 tokens per second — a comfortable fit.

Can I run Janus 1.3B on a 16 GB GPU?

Yes. A Tesla V100 SXM2 16 GB with 16 GB runs it at Q8_0, using about 2.1 GB and generating roughly 368 tokens per second — a comfortable fit.

Can I run Janus 1.3B on a 24 GB GPU?

Yes. A GeForce RTX 5090 D V2 with 24 GB runs it at Q8_0, using about 2.1 GB and generating roughly 437 tokens per second — a comfortable fit.

Is Janus 1.3B open source?

Its weights are published, so Janus 1.3B 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 1.3B have?

Janus 1.3B has 1.3B parameters. 1.3B ! In the paper they say that they "utilize DeepSeek-LLM (1.3B) [5] with a maximum supported sequence length of 4096 as the base language model." but I haven't found any mentioning of 1.3B model in that Deepseek paper (only 7B and 67B). 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 1.3B?

Janus 1.3B was published by DeepSeek,The University of Hong Kong,Peking University, based in China, categorised as industry,Academia,Academia.

When was Janus 1.3B released?

Janus 1.3B 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 Janus 1.3B used for?

Janus 1.3B works in Language, Vision, Multimodal, and is recorded as handling language modeling/generation, Question answering, Visual question answering. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.

Where can I download Janus 1.3B?

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 1.3B 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 1.3B is rarely worth using. Every figure here assumes the whole model is on the card.

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