DeepSeek Coder 33B TPS calculator

Open weights DeepSeek,Peking University 33B parameters January 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

132 cards that can run it

818 cards we hold specifications for

Smallest card that fits

RTX A4500

20 GB · Q3_K_M · 22.2 tok/s

Fastest card

B200

103 tok/s · 180 GB

Which GPUs can run DeepSeek Coder 33B?

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

132 cards match

Calculating

					Needs	Quantisation	Fit
103 tok/s 87–123	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	35.9 GB	Q8_0	Comfortable
103 tok/s 87–123	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	35.9 GB	Q8_0	Comfortable
82.0 tok/s 49–131 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	35.9 GB	Q8_0	Comfortable
82.0 tok/s 49–131 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	35.9 GB	Q8_0	Comfortable
65.6 tok/s 39–105 · low confidence	Radeon Instinct MI300 AMD	128 GB	6,550 GB/s	Jan 2023	35.9 GB	Q8_0	Comfortable
62.8 tok/s 53–75	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	35.9 GB	Q8_0	Comfortable
62.8 tok/s 53–75	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	35.9 GB	Q8_0	Comfortable
60.1 tok/s 36–96 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	35.9 GB	Q8_0	Comfortable
53.3 tok/s 32–85 · low confidence	Radeon Instinct MI300A AMD	128 GB	5,325 GB/s	Dec 2023	35.9 GB	Q8_0	Comfortable
53.3 tok/s 32–85 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	35.9 GB	Q8_0	Comfortable
53.3 tok/s 32–85 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	35.9 GB	Q8_0	Comfortable
50.6 tok/s 43–61	H100 NVL 94 GB NVIDIA	94 GB	3,940 GB/s	Mar 2023	35.9 GB	Q8_0	Comfortable
43.1 tok/s 37–52	H100 PCIe 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	35.9 GB	Q8_0	Comfortable
43.1 tok/s 37–52	H100 SXM5 80 GB NVIDIA	80 GB	3,360 GB/s	Oct 2022	35.9 GB	Q8_0	Comfortable
43.1 tok/s 37–52	H100 SXM5 94 GB NVIDIA	94 GB	3,360 GB/s	Mar 2023	35.9 GB	Q8_0	Comfortable
43.1 tok/s 37–52	H100 SXM5 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	35.9 GB	Q8_0	Comfortable
43.1 tok/s 37–52	H800 SXM5 NVIDIA	80 GB	3,360 GB/s	Mar 2023	35.9 GB	Q8_0	Comfortable
39.7 tok/s 34–48	GeForce RTX 5090 D V2 NVIDIA	24 GB	1,340 GB/s	Aug 2025	20.5 GB	Q4_K_M	Tight
36.2 tok/s 31–43	A30X NVIDIA	24 GB	1,220 GB/s	Apr 2021	20.5 GB	Q4_K_M	Tight
34.9 tok/s 30–42	DRIVE A100 PROD NVIDIA	32 GB	1,870 GB/s	May 2020	28.2 GB	Q6_K	Tight
34.9 tok/s 30–42	GRID A100A NVIDIA	32 GB	1,870 GB/s	May 2020	28.2 GB	Q6_K	Tight
33.4 tok/s 28–40	GeForce RTX 5090 NVIDIA	32 GB	1,790 GB/s	Jan 2025	28.2 GB	Q6_K	Tight
33.4 tok/s 28–40	GeForce RTX 5090 D NVIDIA	32 GB	1,790 GB/s	Jan 2025	28.2 GB	Q6_K	Tight
32.8 tok/s 20–53 · low confidence	Radeon Instinct MI250 AMD	128 GB	3,280 GB/s	Nov 2021	35.9 GB	Q8_0	Comfortable
32.8 tok/s 20–53 · low confidence	Radeon Instinct MI250X AMD	128 GB	3,280 GB/s	Nov 2021	35.9 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,Peking University
Organisation type: Industry,Academia
Country: China
Published: 25 January 2024
Authors: Daya Guo, Qihao Zhu, Dejian Yang, Zhenda Xie, Kai Dong, Wentao Zhang, Guanting Chen, Xiao Bi, Y. Wu, Y.K. Li, Fuli Luo, Yingfei Xiong, Wenfeng Liang

What it does

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

Domain: Language
Task: Code 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: 33B
Training data: 2,000,000,000,000 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.

Training compute: 4 × 10²³ FLOP
How it was established: Operation counting

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: 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.

Likely above 10²³ FLOP: Yes
Record confidence: Likely

Sources

Where this record came from and when it was last checked.

Reference: DeepSeek-Coder: When the Large Language Model Meets Programming -- The Rise of Code Intelligence
Last updated: 28 November 2025

The extremes

The ten fastest GPUs that run DeepSeek Coder 33B

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 Coder 33B

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

The hardware side

Minimum card

RTX A4500

Memory needed

16.7 GB

Fastest

103 tok/s

With 33B parameters, DeepSeek Coder 33B lands in the range a serious desktop card can handle once the weights are compressed. 132 of the cards we track can run it.

At the low end, a RTX A4500 handles it — 20 GB, at Q3_K_M, for about 22.2 tokens per second.

The quickest result comes from a B200 at around 103 tokens per second — its 8,000 GB/s of bandwidth is what buys that.

Background

DeepSeek Coder 33B was published by DeepSeek,Peking University, in China, in January 2024. industry,Academia is the category the publisher falls under.

It works in Language, and is recorded as doing code 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 deepseek-ai organisation on Hugging Face.

Reading the throughput figures

Half the cards that hold it manage more than 20.0 tokens per second, and 101 exceed reading speed outright.

Being dense, it reads all of itself per token, which is why the ordering by speed below follows the ordering by memory bandwidth so closely.

Because the architecture is recorded, the memory column is derived rather than estimated.

What went into building it

Producing it required around 4 × 10²³ FLOP of arithmetic, which is a statement about the training budget rather than about inference.

It was trained on about 2,000,000,000,000 tokens of text.

Step by step

How to choose a GPU for DeepSeek Coder 33B

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

Look at what DeepSeek Coder 33B actually needs — around 16.7 GB at Q3_K_M. No amount of processing power compensates for a card that cannot hold it.
02

Set the context length you will work at

The conversation occupies memory too, and grows as it goes. Set the slider to the length you expect: at long context DeepSeek Coder 33B can slip off a card that handles short questions easily.
03

Decide how much compression you will accept

The quantisation column varies by card, because a bigger card holds a more accurate copy of DeepSeek Coder 33B — Q3_K_M on the smallest card that fits. Set a floor to hold the comparison at one level.
04

Sort by speed

Sort by speed to see how cards rank for DeepSeek Coder 33B. It will not match a gaming ordering — generation is bound by memory bandwidth, which is why the B200 tops it at 103 tok/s.
05

Check the fit verdict before buying

The fit column separates cards that just manage DeepSeek Coder 33B from those with room to spare. Buy for the second if the context might grow.
06

Check the card from the other side

Every card name links to its own page, which runs the same calculation across the whole model catalogue. Worth a look before buying for DeepSeek Coder 33B alone — a card is usually bought for more than one model.

Answers

DeepSeek Coder 33B — common questions

How fast is DeepSeek Coder 33B on a GPU?

It depends on the card. The quickest we calculate is a B200 at about 103 tokens per second; the slowest that still runs it manages considerably less. Reading speed is around ten tokens per second, and 101 of the cards that can run DeepSeek Coder 33B clear that.

How much VRAM does DeepSeek Coder 33B need?

About 16.7 GB at Q3_K_M 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 Coder 33B on a 24 GB GPU?

Yes. A GeForce RTX 5090 D V2 with 24 GB runs it at Q4_K_M, using about 20.5 GB and generating roughly 39.7 tokens per second — a tight fit.

Is DeepSeek Coder 33B open source?

Its weights are published, so DeepSeek Coder 33B 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 Coder 33B have?

DeepSeek Coder 33B has 33B parameters. 33B. 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 Coder 33B?

DeepSeek Coder 33B was published by DeepSeek,Peking University, based in China, categorised as industry,Academia.

When was DeepSeek Coder 33B released?

DeepSeek Coder 33B was published in January 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 DeepSeek Coder 33B used for?

DeepSeek Coder 33B works in Language, and is recorded as handling code generation. These are the areas it was designed around; they describe intent rather than a hard boundary.

Where can I download DeepSeek Coder 33B?

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.

How much compute was used to train DeepSeek Coder 33B?

Around 4 × 10²³ FLOP. That measures what producing the model cost and says nothing about how quickly it answers once trained — inference speed comes from memory bandwidth, not from the training budget.

Can I run DeepSeek Coder 33B 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 — the nearest miss we calculate is short by 6.1 GB. Our figures for DeepSeek Coder 33B assume it is fully resident.

Would two GPUs run DeepSeek Coder 33B faster?

Capacity adds across cards; throughput does not. Since 132 of the cards we track already hold DeepSeek Coder 33B on their own, a second card is rarely the answer here.

Why does the quantisation differ between cards for DeepSeek Coder 33B?

Because capacity varies, so does how hard DeepSeek Coder 33B has to be squeezed — 5 distinct levels appear in the table above. Set a minimum quality to compare at one.

How accurate are these DeepSeek Coder 33B speed estimates?

They are calculated from specifications rather than measured, and each carries a range — 87–123 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 DeepSeek Coder 33B?

The smallest card in our catalogue that holds DeepSeek Coder 33B is the RTX A4500, with 20 GB of memory. It runs the model at Q3_K_M using about 16.7 GB, and produces roughly 22.2 tokens per second. 132 cards in total can run it.

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