Tongyi DeepResearch TPS calculator
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 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
A longer conversation needs more memory, which can push this model off smaller cards.
Hides cards that would only fit the model by compressing it below this point.
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
30.5 billion total parameters, with only 3.3 billion activated per token
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
Apache 2.0 https://huggingface.co/Alibaba-NLP/Tongyi-DeepResearch-30B-A3B https://github.com/Alibaba-NLP/DeepResearch
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
" achieves state-of-the-art performance across a range of agentic deep research benchmarks, including Humanity’s Last Exam, BrowseComp, BrowseComp-ZH, WebWalkerQA, xbench-DeepSearch, FRAMES and xbench-DeepSearch-2510"
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.
- 01 B300 288 GB · 8,000 GB/s · Q8_0 111 tok/s
- 02 B200 180 GB · 8,000 GB/s · Q8_0 111 tok/s
- 03 Radeon Instinct MI350X 288 GB · 8,190 GB/s · Q8_0 88.7 tok/s
- 04 Radeon Instinct MI355X 288 GB · 8,190 GB/s · Q8_0 88.7 tok/s
- 05 Radeon Instinct MI300 128 GB · 6,550 GB/s · Q8_0 70.9 tok/s
- 06 H200 NVL 141 GB · 4,890 GB/s · Q8_0 67.9 tok/s
- 07 H200 SXM 141 GB 141 GB · 4,890 GB/s · Q8_0 67.9 tok/s
- 08 Radeon Instinct MI325X 256 GB · 6,000 GB/s · Q8_0 65.0 tok/s
- 09 Radeon Instinct MI300A 128 GB · 5,325 GB/s · Q8_0 57.7 tok/s
- 10 Radeon Instinct MI300X 192 GB · 5,325 GB/s · Q8_0 57.7 tok/s
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.
- 01 RTX 4000 Ada Generation 20 GB · needs 17.4 GB · IQ4_XS · tight 12.3 tok/s
- 02 RTX 4000 SFF Ada Generation 20 GB · needs 17.4 GB · IQ4_XS · tight 9.6 tok/s
- 03 Radeon RX 7900 XT 20 GB · needs 17.4 GB · IQ4_XS · tight 21.3 tok/s
- 04 A10M 20 GB · needs 17.4 GB · IQ4_XS · tight 17.1 tok/s
- 05 GeForce RTX 3080 Ti 20 GB 20 GB · needs 17.4 GB · IQ4_XS · tight 25.9 tok/s
- 06 RTX A4500 20 GB · needs 17.4 GB · IQ4_XS · tight 21.8 tok/s
- 07 Arc Pro B60 24 GB · needs 19.2 GB · Q4_K_M · tight 9.5 tok/s
- 08 GeForce RTX 5090 D V2 24 GB · needs 19.2 GB · Q4_K_M · tight 43.0 tok/s
- 09 RTX PRO 4000 Blackwell SFF 24 GB · needs 19.2 GB · Q4_K_M · tight 13.9 tok/s
- 10 GeForce RTX 5090 Mobile 24 GB · needs 19.2 GB · Q4_K_M · tight 28.7 tok/s
What the numbers mean
What it takes to run this model
Minimum card
RTX A4500
Memory needed
17.4 GB
Fastest
111 tok/s
With 30.5B parameters, Tongyi DeepResearch lands in the range a serious desktop card can handle once the weights are compressed. 132 of the cards we track can run it.
The smallest card that holds it is the RTX A4500 with 20 GB, running it at IQ4_XS and producing around 21.8 tokens per second.
At the other end, a B200 generates roughly 111 tokens per second on it, on the strength of 8,000 GB/s of memory bandwidth.
What this model is
Tongyi DeepResearch was published by Alibaba, in China, in October 2025. It comes out of industry.
It works in Language, and is recorded as doing language modeling/generation, Question answering, Quantitative reasoning, Search, System control.
Its starting point was 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. It is published under the Alibaba-NLP organisation on Hugging Face.
What decides the speed
Across every card that can run it, the middle of the range is about 21.6 tokens per second, and 104 of them clear the ten tokens per second that roughly matches reading speed.
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 is 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 that can hold Tongyi DeepResearch — around 17.4 GB at IQ4_XS. That figure, not the card's headline performance, is what decides whether it runs.
-
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 Tongyi DeepResearch stops fitting a card that seemed fine.
-
03
Decide how much compression you will accept
Compression is what makes Tongyi DeepResearch fit smaller cards, at some cost in accuracy — IQ4_XS on the smallest card that fits. A minimum quality removes the ones that go too far.
-
04
Compare tokens per second, not specifications
Ranking by tokens per second for Tongyi DeepResearch follows memory bandwidth, not core counts, which is why the B200 tops it at 111 tok/s.
-
05
Check the fit verdict before buying
The fit column separates cards that just manage Tongyi DeepResearch from those with room to spare. Buy for the second if the context might grow.
-
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 Tongyi DeepResearch is settled.
Answers
Tongyi DeepResearch — common questions
What GPU do I need to run Tongyi DeepResearch?
The smallest card in our catalogue that holds Tongyi DeepResearch is the RTX A4500, with 20 GB of memory. It runs the model at IQ4_XS using about 17.4 GB, and produces roughly 21.8 tokens per second. 132 cards in total can run it.
How fast is Tongyi DeepResearch on a GPU?
It depends on the card. The quickest we calculate is a 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 104 of the cards that can run Tongyi DeepResearch clear that.
How much VRAM does Tongyi DeepResearch need?
About 17.4 GB at IQ4_XS 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 Tongyi DeepResearch on a 24 GB GPU?
Yes. A GeForce RTX 5090 D V2 with 24 GB runs it at Q4_K_M, using about 19.2 GB and generating roughly 43.0 tokens per second — a tight fit.
Is Tongyi DeepResearch open source?
Its weights are published, so Tongyi DeepResearch 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 Tongyi DeepResearch have?
Tongyi DeepResearch has 30.5B parameters. 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.
Who created Tongyi DeepResearch?
Tongyi DeepResearch was published by Alibaba, based in China, categorised as industry.
When was Tongyi DeepResearch released?
Tongyi DeepResearch was published in October 2025.
What is Tongyi DeepResearch used for?
Tongyi DeepResearch works in Language, and is recorded as handling 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.
Where can I download Tongyi DeepResearch?
Its weights are published under the Alibaba-NLP organisation on Hugging Face. We do not host model files — this site calculates what hardware is needed to run them.
Can I run Tongyi DeepResearch 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 Tongyi DeepResearch is rarely worth using — the nearest miss we calculate is short by 4.8 GB. Every figure here assumes the whole model is on the card.
Would two GPUs run Tongyi DeepResearch faster?
Two cards buy memory rather than speed. That matters for Tongyi DeepResearch only if one card cannot hold it — 132 can, so a second adds little.
Why does the quantisation differ between cards for Tongyi DeepResearch?
Because capacity varies, so does how hard Tongyi DeepResearch has to be squeezed — 5 distinct levels appear in the table above. Set a minimum quality to compare at one.
How accurate are these Tongyi DeepResearch speed estimates?
They are calculated from specifications rather than measured, and each carries a range — 67–178 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.
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.