Tongyi DeepResearch TPS calculator

Open weights Alibaba 30.5B 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

132 cards that can run it

818 cards we hold specifications for

Smallest card that fits

RTX A4500

20 GB · IQ4_XS · 21.8 tok/s

Fastest card

B200

111 tok/s · 180 GB

Which GPUs can run Tongyi DeepResearch?

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
111 tok/s 67–178 · low confidence	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	33.4 GB	Q8_0	Comfortable
111 tok/s 67–178 · low confidence	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	33.4 GB	Q8_0	Comfortable
88.7 tok/s 53–142 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	33.4 GB	Q8_0	Comfortable
88.7 tok/s 53–142 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	33.4 GB	Q8_0	Comfortable
70.9 tok/s 43–114 · low confidence	Radeon Instinct MI300 AMD	128 GB	6,550 GB/s	Jan 2023	33.4 GB	Q8_0	Comfortable
67.9 tok/s 41–109 · low confidence	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	33.4 GB	Q8_0	Comfortable
67.9 tok/s 41–109 · low confidence	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	33.4 GB	Q8_0	Comfortable
65.0 tok/s 39–104 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	33.4 GB	Q8_0	Comfortable
57.7 tok/s 35–92 · low confidence	Radeon Instinct MI300A AMD	128 GB	5,325 GB/s	Dec 2023	33.4 GB	Q8_0	Comfortable
57.7 tok/s 35–92 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	33.4 GB	Q8_0	Comfortable
57.7 tok/s 35–92 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	33.4 GB	Q8_0	Comfortable
54.7 tok/s 33–88 · low confidence	H100 NVL 94 GB NVIDIA	94 GB	3,940 GB/s	Mar 2023	33.4 GB	Q8_0	Comfortable
46.7 tok/s 28–75 · low confidence	H100 PCIe 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	33.4 GB	Q8_0	Comfortable
46.7 tok/s 28–75 · low confidence	H100 SXM5 80 GB NVIDIA	80 GB	3,360 GB/s	Oct 2022	33.4 GB	Q8_0	Comfortable
46.7 tok/s 28–75 · low confidence	H100 SXM5 94 GB NVIDIA	94 GB	3,360 GB/s	Mar 2023	33.4 GB	Q8_0	Comfortable
46.7 tok/s 28–75 · low confidence	H100 SXM5 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	33.4 GB	Q8_0	Comfortable
46.7 tok/s 28–75 · low confidence	H800 SXM5 NVIDIA	80 GB	3,360 GB/s	Mar 2023	33.4 GB	Q8_0	Comfortable
43.0 tok/s 26–69 · low confidence	GeForce RTX 5090 D V2 NVIDIA	24 GB	1,340 GB/s	Aug 2025	19.2 GB	Q4_K_M	Tight
39.1 tok/s 23–63 · low confidence	A30X NVIDIA	24 GB	1,220 GB/s	Apr 2021	19.2 GB	Q4_K_M	Tight
37.7 tok/s 23–60 · low confidence	DRIVE A100 PROD NVIDIA	32 GB	1,870 GB/s	May 2020	26.3 GB	Q6_K	Tight
37.7 tok/s 23–60 · low confidence	GRID A100A NVIDIA	32 GB	1,870 GB/s	May 2020	26.3 GB	Q6_K	Tight
36.1 tok/s 22–58 · low confidence	GeForce RTX 5090 NVIDIA	32 GB	1,790 GB/s	Jan 2025	26.3 GB	Q6_K	Tight
36.1 tok/s 22–58 · low confidence	GeForce RTX 5090 D NVIDIA	32 GB	1,790 GB/s	Jan 2025	26.3 GB	Q6_K	Tight
35.5 tok/s 21–57 · low confidence	Radeon Instinct MI250 AMD	128 GB	3,280 GB/s	Nov 2021	33.4 GB	Q8_0	Comfortable
35.5 tok/s 21–57 · low confidence	Radeon Instinct MI250X AMD	128 GB	3,280 GB/s	Nov 2021	33.4 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: Alibaba
Organisation type: Industry
Country: China
Published: 28 October 2025
Authors: Baixuan Li, Bo Zhang, Dingchu Zhang, Fei Huang, Guangyu Li, Guoxin Chen, Huifeng Yin, Jialong Wu, Jingren Zhou, Kuan Li, Liangcai Su, Litu Ou, Liwen Zhang, Pengjun Xie, Rui Ye, Wenbiao Yin, Xinmiao Yu, Xinyu Wang, Xixi Wu, Xuanzhong Chen, Yida Zhao, Zhen Zhang, Zhengwei Tao, Zhongwang Zhang, Zile Qiao, Chenxi Wang, Donglei Yu, Gang Fu, Haiyang Shen, Jiayin Yang, Jun Lin, Junkai Zhang, Kui Zeng, Li…

What it does

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

Domain: Language
Task: Language modeling/generation, Question answering, Quantitative reasoning, Search, System control
Base model: Qwen3-30B-A3B

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: 30.5B
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 (unrestricted)
Training code: Unreleased
Hugging Face: Alibaba-NLP

How it is classified

Labels the source dataset applies when tracking notable models, and how confident it is in the entry.

Why it is tracked: SOTA improvement
Record confidence: Confident

Sources

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

Reference: Tongyi DeepResearch Technical Report
Last updated: 28 November 2025

The extremes

The ten fastest GPUs that run Tongyi DeepResearch

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 Tongyi DeepResearch

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

RTX A4500

Memory needed

17.4 GB

Fastest

111 tok/s

Tongyi DeepResearch reaches a parameter count of 30.5B. That lands in the range a serious desktop card can handle once the weights are compressed. The number of cards we track that can run it: 132.

The smallest card that holds it is RTX A4500, with a memory capacity of 20 GB, running it at a compression of IQ4_XS and producing around 21.8 tokens per second.

At the other end sits B200, generating roughly 111 tokens per second on the strength of a memory bandwidth of 8,000 GB/s.

What this model is

Tongyi DeepResearch was published by Alibaba, in the country recorded as China, during October 2025. It comes out of an organisation categorised as industry.

It works in the domain of Language, and is recorded as performing the task of language modeling/generation, Question answering, Quantitative reasoning, Search, System control.

Its starting point was an existing base model, Qwen3-30B-A3B. Most models at this scale are adapted from an existing base rather than built from nothing.

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. On Hugging Face it is published under the organisation Alibaba-NLP.

What decides the speed

Across every card that can run it, the middle of the range sits at 21.6 tokens per second. Clearing the ten tokens per second that roughly matches reading speed: 104 of them.

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.

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

Its inclusion criterion: sOTA improvement.

Step by step

How to choose a GPU for Tongyi DeepResearch

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

The table lists every card able to hold Tongyi DeepResearch, needing around 17.4 GB at a compression of IQ4_XS. Capacity is the gate — a card either holds it or it does not.
02

Set the context length you will work at

Set the context to what you will actually use. The cache grows with the conversation, and it is the usual reason a card that seemed fine stops fitting Tongyi DeepResearch.
03

Decide how much compression you will accept

Compression is what makes a model fit smaller cards, at some cost in accuracy, reaching a compression of IQ4_XS on the smallest card that fits. Setting a minimum quality drops the cards that only manage it by squeezing further than you would want, and holds the comparison at one level.
04

Compare tokens per second, not specifications

Ranking by tokens per second follows memory bandwidth rather than core counts, for Tongyi DeepResearch. It will not match a gaming ordering, because generation is bound by memory bandwidth. The card topping the list is B200, at 111 tok/s.
05

Check the fit verdict before buying

The fit column separates cards that just manage it from those with room to spare, in the case of Tongyi DeepResearch. Comfortable means you can grow the context later. That difference matters more than a few tokens per second, so buy for comfortable if you expect to.
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 you have settled on Tongyi DeepResearch.

Answers

Tongyi DeepResearch — common questions

Tongyi DeepResearch— what GPU do I need to run it?

The smallest card in our catalogue that holds it is RTX A4500, with a memory capacity of 20 GB. It runs the model at a compression of IQ4_XS using about 17.4 GB, and produces roughly 21.8 tokens per second. The number of cards able to run it in total: 132.

Tongyi DeepResearch— how fast is it on a GPU?

It depends on the card. The quickest we calculate is B200, at about 111 tokens per second; the slowest that still runs it manages considerably less. Reading speed is around ten tokens per second, and the number of cards clearing that: 104.

Tongyi DeepResearch— how much VRAM does it need?

It needs about 17.4 GB at a compression of IQ4_XS, 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.

Tongyi DeepResearch— can I run it on a GPU holding 24 GB?

Yes. The card GeForce RTX 5090 D V2, holding 24 GB, runs it at a compression of Q4_K_M, using about 19.2 GB and generating roughly 43.0 tokens per second. The fit is tight.

Tongyi DeepResearch— is it open source?

Its weights are published, so it 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.

Tongyi DeepResearch— how many parameters does it have?

It has a parameter count of 30.5B. 30.5 billion total parameters, with only 3.3 billion activated per token. 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.

Tongyi DeepResearch— who created it?

It was published by Alibaba, based in China, an organisation categorised as industry.

Tongyi DeepResearch— when was it released?

It was published in October 2025.

Tongyi DeepResearch— what is it used for?

It works in the domain of Language, and is recorded as handling the task of language modeling/generation, Question answering, Quantitative reasoning, Search, System control. 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.

Tongyi DeepResearch— where can I download it?

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

Tongyi DeepResearch— can I run it 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 model is rarely worth using. The nearest miss we calculate falls short by 4.8 GB. Every figure here assumes the whole model is resident on the card.

Tongyi DeepResearch— would two GPUs run it faster?

Two cards buy memory rather than speed, which matters only if one card cannot hold it. The number that can: 132. So a second card is rarely the answer here.

Tongyi DeepResearch— why does the quantisation differ between cards?

Because capacity varies, so does how hard it has to be squeezed. The number of distinct levels in the table above: 5. Bigger cards get the more accurate version, and the quality floor above pins the comparison to one level.

Tongyi DeepResearch— how accurate are these speed estimates?

They are calculated from specifications rather than measured, and each carries a range. One example: 67–178 tok/s on B200. The same model and card vary by thirty to fifty per cent depending on the inference software and its version.

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