Deepseek OCR TPS calculator

Open weights DeepSeek 3B parameters October 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 · Q6_K · 17.9 tok/s

Fastest card

B200

1,129 tok/s · 180 GB

Which GPUs can run Deepseek OCR?

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
1,129 tok/s 678–1,807 · low confidence	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	3.9 GB	Q8_0	Comfortable
1,129 tok/s 678–1,807 · low confidence	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	3.9 GB	Q8_0	Comfortable
902 tok/s 541–1,443 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	3.9 GB	Q8_0	Comfortable
902 tok/s 541–1,443 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	3.9 GB	Q8_0	Comfortable
721 tok/s 433–1,154 · low confidence	Radeon Instinct MI300 AMD	128 GB	6,550 GB/s	Jan 2023	3.9 GB	Q8_0	Comfortable
690 tok/s 414–1,105 · low confidence	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	3.9 GB	Q8_0	Comfortable
690 tok/s 414–1,105 · low confidence	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	3.9 GB	Q8_0	Comfortable
661 tok/s 396–1,057 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	3.9 GB	Q8_0	Comfortable
586 tok/s 352–938 · low confidence	Radeon Instinct MI300A AMD	128 GB	5,325 GB/s	Dec 2023	3.9 GB	Q8_0	Comfortable
586 tok/s 352–938 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	3.9 GB	Q8_0	Comfortable
586 tok/s 352–938 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	3.9 GB	Q8_0	Comfortable
556 tok/s 334–890 · low confidence	H100 NVL 94 GB NVIDIA	94 GB	3,940 GB/s	Mar 2023	3.9 GB	Q8_0	Comfortable
474 tok/s 285–759 · low confidence	H100 PCIe 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	3.9 GB	Q8_0	Comfortable
474 tok/s 285–759 · low confidence	H100 SXM5 80 GB NVIDIA	80 GB	3,360 GB/s	Oct 2022	3.9 GB	Q8_0	Comfortable
474 tok/s 285–759 · low confidence	H100 SXM5 94 GB NVIDIA	94 GB	3,360 GB/s	Mar 2023	3.9 GB	Q8_0	Comfortable
474 tok/s 285–759 · low confidence	H100 SXM5 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	3.9 GB	Q8_0	Comfortable
474 tok/s 285–759 · low confidence	H800 SXM5 NVIDIA	80 GB	3,360 GB/s	Mar 2023	3.9 GB	Q8_0	Comfortable
361 tok/s 217–578 · low confidence	Radeon Instinct MI250 AMD	128 GB	3,280 GB/s	Nov 2021	3.9 GB	Q8_0	Comfortable
361 tok/s 217–578 · low confidence	Radeon Instinct MI250X AMD	128 GB	3,280 GB/s	Nov 2021	3.9 GB	Q8_0	Comfortable
301 tok/s 181–482 · low confidence	Data Center GPU Max 1550 Intel	128 GB	3,280 GB/s	Jan 2023	3.9 GB	Q8_0	Comfortable
295 tok/s 177–471 · low confidence	Data Center GPU Max Subsystem Intel	128 GB	3,210 GB/s	Jan 2023	3.9 GB	Q8_0	Comfortable
288 tok/s 173–461 · low confidence	A100 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Nov 2020	3.9 GB	Q8_0	Comfortable
288 tok/s 173–461 · low confidence	A100X NVIDIA	80 GB	2,040 GB/s	Jun 2021	3.9 GB	Q8_0	Comfortable
288 tok/s 173–461 · low confidence	A800 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Aug 2022	3.9 GB	Q8_0	Comfortable
288 tok/s 173–461 · low confidence	H100 CNX NVIDIA	80 GB	2,040 GB/s	Mar 2023	3.9 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: 21 October 2025
Authors: Haoran Wei, Yaofeng Sun, Yukun Li

What it does

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

Domain: Vision, Language
Task: Character recognition (OCR), Visual question answering
Base model: Segment Anything Model,CLIP (ViT L/14@336px)

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: 3B
Training data: tokens

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: 160
Power draw: 125.0 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 (unrestricted)
Training code: Unreleased
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: DeepSeek-OCR: Contexts Optical Compression
Last updated: 28 November 2025

The extremes

The ten fastest GPUs that run Deepseek OCR

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 Deepseek OCR

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 you need to run it

Minimum card

Tesla C1080

Memory needed

3.2 GB

Fastest

1,129 tok/s

Deepseek OCR is small enough at 3B parameters that hardware is rarely the obstacle — 818 of the cards we track can run it, including cards several years old.

The least hardware that works is a Tesla C1080. Its 4 GB is enough at Q6_K compression, giving roughly 17.9 tokens per second.

Top of the range is the B200, at roughly 1,129 tokens per second thanks to 8,000 GB/s of bandwidth.

What this model is

Deepseek OCR was published by DeepSeek, in China, in October 2025. The organisation is categorised as industry.

It works in Vision, Language, and is recorded as doing character recognition (OCR), Visual question answering.

It is derived from Segment Anything Model,CLIP (ViT L/14@336px) rather than trained from scratch, which is the usual way a specialised model is produced.

Published weights mean the model runs on your machine rather than someone else's, which is what makes the hardware question below answerable at all. It is published under the deepseek-ai organisation on Hugging Face.

What decides the speed

Half the cards that hold it manage more than 35.8 tokens per second, and 780 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.

Step by step

How to choose a GPU for Deepseek OCR

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 Deepseek OCR — around 3.2 GB at Q6_K. 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 Deepseek OCR can slip off a card that handles short questions easily.
03

Set a quality floor

Each card runs the least-compressed copy it can hold — Q6_K on the smallest card that fits. Setting a floor drops the cards that only manage Deepseek OCR by squeezing it further than you would want.
04

Compare tokens per second, not specifications

Ranking by tokens per second for Deepseek OCR follows memory bandwidth, not core counts, which is why the B200 tops it at 1,129 tok/s.
05

Read the fit column last

A tight fit runs Deepseek OCR but leaves nothing spare for a longer conversation; comfortable has headroom. If you expect to grow the context, buy for comfortable.
06

Check the card from the other side

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

Answers

Deepseek OCR — common questions

Can I run Deepseek OCR on a 12 GB GPU?

Yes. A GeForce RTX 3080 Ti with 12 GB runs it at Q8_0, using about 3.9 GB and generating roughly 129 tokens per second — a comfortable fit.

Can I run Deepseek OCR on a 16 GB GPU?

Yes. A Tesla V100 SXM2 16 GB with 16 GB runs it at Q8_0, using about 3.9 GB and generating roughly 160 tokens per second — a comfortable fit.

Can I run Deepseek OCR on a 24 GB GPU?

Yes. A GeForce RTX 5090 D V2 with 24 GB runs it at Q8_0, using about 3.9 GB and generating roughly 189 tokens per second — a comfortable fit.

Is Deepseek OCR open source?

Its weights are published, so Deepseek OCR 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 Deepseek OCR have?

Deepseek OCR has 3B parameters. "DeepEncoder is approximately 380M in parameters, mainly composed of an 80M SAM-base [17] and a 300M CLIP-large [29] connected in series. The decoder adopts a 3B MoE [19, 20] architecture with 570M activated 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 Deepseek OCR?

Deepseek OCR was published by DeepSeek, based in China, categorised as industry.

When was Deepseek OCR released?

Deepseek OCR was published in October 2025.

What is Deepseek OCR used for?

Deepseek OCR works in Vision, Language, and is recorded as handling character recognition (OCR), 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 Deepseek OCR?

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 Deepseek OCR 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 Deepseek OCR assume it is fully resident.

Would two GPUs run Deepseek OCR faster?

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

Why does the quantisation differ between cards for Deepseek OCR?

Each card is shown running the least-compressed copy it can hold, and Deepseek OCR appears at 2 different compression levels across the cards that fit it. Bigger cards get the more accurate version.

How accurate are these Deepseek OCR speed estimates?

These are estimates with real error bars. The fastest result here, 678–1,807 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 Deepseek OCR?

The smallest card in our catalogue that holds Deepseek OCR is the Tesla C1080, with 4 GB of memory. It runs the model at Q6_K using about 3.2 GB, and produces roughly 17.9 tokens per second. 818 cards in total can run it.

How fast is Deepseek OCR on a GPU?

It depends on the card. The quickest we calculate is a B200 at about 1,129 tokens per second; the slowest that still runs it manages considerably less. Reading speed is around ten tokens per second, and 780 of the cards that can run Deepseek OCR clear that.

How much VRAM does Deepseek OCR need?

About 3.2 GB at Q6_K 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 Deepseek OCR on a 8 GB GPU?

Yes. A CMP 170HX 8 GB with 8 GB runs it at Q8_0, using about 3.9 GB and generating roughly 210 tokens per second — a comfortable fit.

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