AgentFounder-30B 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 · 22.2 tok/s
Fastest card
B200
113 tok/s · 180 GB
Which GPUs can run AgentFounder-30B?
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 | |||||
|---|---|---|---|---|---|---|---|
|
113
tok/s
68–181 · low confidence |
B200 NVIDIA | 180 GB | 8,000 GB/s | Jan 2024 | 32.8 GB | Q8_0 | Comfortable |
|
113
tok/s
68–181 · low confidence |
B300 NVIDIA | 288 GB | 8,000 GB/s | Sep 2025 | 32.8 GB | Q8_0 | Comfortable |
|
90.2
tok/s
54–144 · low confidence |
Radeon Instinct MI350X AMD | 288 GB | 8,190 GB/s | Jan 2025 | 32.8 GB | Q8_0 | Comfortable |
|
90.2
tok/s
54–144 · low confidence |
Radeon Instinct MI355X AMD | 288 GB | 8,190 GB/s | Jan 2025 | 32.8 GB | Q8_0 | Comfortable |
|
72.1
tok/s
43–115 · low confidence |
Radeon Instinct MI300 AMD | 128 GB | 6,550 GB/s | Jan 2023 | 32.8 GB | Q8_0 | Comfortable |
|
69.0
tok/s
41–110 · low confidence |
H200 NVL NVIDIA | 141 GB | 4,890 GB/s | Nov 2024 | 32.8 GB | Q8_0 | Comfortable |
|
69.0
tok/s
41–110 · low confidence |
H200 SXM 141 GB NVIDIA | 141 GB | 4,890 GB/s | Nov 2024 | 32.8 GB | Q8_0 | Comfortable |
|
66.1
tok/s
40–106 · low confidence |
Radeon Instinct MI325X AMD | 256 GB | 6,000 GB/s | Oct 2024 | 32.8 GB | Q8_0 | Comfortable |
|
58.6
tok/s
35–94 · low confidence |
Radeon Instinct MI300A AMD | 128 GB | 5,325 GB/s | Dec 2023 | 32.8 GB | Q8_0 | Comfortable |
|
58.6
tok/s
35–94 · low confidence |
Radeon Instinct MI300X AMD | 192 GB | 5,325 GB/s | Dec 2023 | 32.8 GB | Q8_0 | Comfortable |
|
58.6
tok/s
35–94 · low confidence |
Radeon Instinct MI308X AMD | 192 GB | 5,325 GB/s | Dec 2023 | 32.8 GB | Q8_0 | Comfortable |
|
55.6
tok/s
33–89 · low confidence |
H100 NVL 94 GB NVIDIA | 94 GB | 3,940 GB/s | Mar 2023 | 32.8 GB | Q8_0 | Comfortable |
|
47.4
tok/s
28–76 · low confidence |
H100 PCIe 96 GB NVIDIA | 96 GB | 3,360 GB/s | Mar 2023 | 32.8 GB | Q8_0 | Comfortable |
|
47.4
tok/s
28–76 · low confidence |
H100 SXM5 80 GB NVIDIA | 80 GB | 3,360 GB/s | Oct 2022 | 32.8 GB | Q8_0 | Comfortable |
|
47.4
tok/s
28–76 · low confidence |
H100 SXM5 94 GB NVIDIA | 94 GB | 3,360 GB/s | Mar 2023 | 32.8 GB | Q8_0 | Comfortable |
|
47.4
tok/s
28–76 · low confidence |
H100 SXM5 96 GB NVIDIA | 96 GB | 3,360 GB/s | Mar 2023 | 32.8 GB | Q8_0 | Comfortable |
|
47.4
tok/s
28–76 · low confidence |
H800 SXM5 NVIDIA | 80 GB | 3,360 GB/s | Mar 2023 | 32.8 GB | Q8_0 | Comfortable |
|
43.7
tok/s
26–70 · low confidence |
GeForce RTX 5090 D V2 NVIDIA | 24 GB | 1,340 GB/s | Aug 2025 | 18.8 GB | Q4_K_M | Tight |
|
39.8
tok/s
24–64 · low confidence |
A30X NVIDIA | 24 GB | 1,220 GB/s | Apr 2021 | 18.8 GB | Q4_K_M | Tight |
|
38.4
tok/s
23–61 · low confidence |
DRIVE A100 PROD NVIDIA | 32 GB | 1,870 GB/s | May 2020 | 25.8 GB | Q6_K | Tight |
|
38.4
tok/s
23–61 · low confidence |
GRID A100A NVIDIA | 32 GB | 1,870 GB/s | May 2020 | 25.8 GB | Q6_K | Tight |
|
36.7
tok/s
22–59 · low confidence |
GeForce RTX 5090 NVIDIA | 32 GB | 1,790 GB/s | Jan 2025 | 25.8 GB | Q6_K | Tight |
|
36.7
tok/s
22–59 · low confidence |
GeForce RTX 5090 D NVIDIA | 32 GB | 1,790 GB/s | Jan 2025 | 25.8 GB | Q6_K | Tight |
|
36.1
tok/s
22–58 · low confidence |
Radeon Instinct MI250 AMD | 128 GB | 3,280 GB/s | Nov 2021 | 32.8 GB | Q8_0 | Comfortable |
|
36.1
tok/s
22–58 · low confidence |
Radeon Instinct MI250X AMD | 128 GB | 3,280 GB/s | Nov 2021 | 32.8 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
- 16 September 2025
- Authors
- Liangcai Su, Zhen Zhang, Guangyu Li, Zhuo Chen, Chenxi Wang, Maojia Song, Xinyu Wang, Kuan Li, Jialong Wu, Xuanzhong Chen, Zile Qiao, Zhongwang Zhang, Huifeng Yin, Shihao Cai, Runnan Fang, Zhengwei Tao, Wenbiao Yin, Chenxiong Qian, Yong Jiang, Pengjun Xie, Fei Huang, Jingren Zhou
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, System control, Quantitative reasoning, Mathematical reasoning, Code generation, Search
- 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
- 30B
- Training data
- 315,000,000,000 tokens
30B-A3B
We train AgentFounder models with data volumes ranging from 0B to 315B tokens Agentic CPT Stage 1: We process approximately 200B tokens Agentic CPT Stage 2: We further refine these capabilities using 100B 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
- 6.5 × 10²³ FLOP
- How it was established
- Operation counting
- Fine-tuning compute
- 5.7 × 10²¹ FLOP
6.48e+23 FLOP [base model compute] + 5.67e+21 FLOP = 6.5367e+23 FLOP
6 FLOP/parameter/token * 3000000000 active parameters * 315000000000 tokens = 5.67e+21 FLOP
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
"We evaluate our AgentFounder-30B on 10 benchmarks and achieve state-of-the-art performance while retains strong tool-use ability, notably 39.9% on BrowseComp-en, 43.3% on BrowseComp-zh, and 31.5% Pass@1 on HLE."
Sources
Where this record came from and when it was last checked.
- Reference
- Scaling Agents via Continual Pre-training
- Last updated
- 18 December 2025
The extremes
The ten fastest GPUs that run AgentFounder-30B
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_0 113 tok/s
- 02 B200 180 GB · 8,000 GB/s · Q8_0 113 tok/s
- 03 Radeon Instinct MI350X 288 GB · 8,190 GB/s · Q8_0 90.2 tok/s
- 04 Radeon Instinct MI355X 288 GB · 8,190 GB/s · Q8_0 90.2 tok/s
- 05 Radeon Instinct MI300 128 GB · 6,550 GB/s · Q8_0 72.1 tok/s
- 06 H200 NVL 141 GB · 4,890 GB/s · Q8_0 69.0 tok/s
- 07 H200 SXM 141 GB 141 GB · 4,890 GB/s · Q8_0 69.0 tok/s
- 08 Radeon Instinct MI325X 256 GB · 6,000 GB/s · Q8_0 66.1 tok/s
- 09 Radeon Instinct MI300A 128 GB · 5,325 GB/s · Q8_0 58.6 tok/s
- 10 Radeon Instinct MI300X 192 GB · 5,325 GB/s · Q8_0 58.6 tok/s
The smallest GPUs that still run AgentFounder-30B
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 17.1 GB · IQ4_XS · tight 12.5 tok/s
- 02 RTX 4000 SFF Ada Generation 20 GB · needs 17.1 GB · IQ4_XS · tight 9.7 tok/s
- 03 Radeon RX 7900 XT 20 GB · needs 17.1 GB · IQ4_XS · tight 21.6 tok/s
- 04 A10M 20 GB · needs 17.1 GB · IQ4_XS · tight 17.3 tok/s
- 05 GeForce RTX 3080 Ti 20 GB 20 GB · needs 17.1 GB · IQ4_XS · tight 26.4 tok/s
- 06 RTX A4500 20 GB · needs 17.1 GB · IQ4_XS · tight 22.2 tok/s
- 07 Arc Pro B60 24 GB · needs 18.8 GB · Q4_K_M · tight 9.7 tok/s
- 08 GeForce RTX 5090 D V2 24 GB · needs 18.8 GB · Q4_K_M · tight 43.7 tok/s
- 09 RTX PRO 4000 Blackwell SFF 24 GB · needs 18.8 GB · Q4_K_M · tight 14.1 tok/s
- 10 GeForce RTX 5090 Mobile 24 GB · needs 18.8 GB · Q4_K_M · tight 29.2 tok/s
What the numbers mean
Hardware requirements in practice
Minimum card
RTX A4500
Memory needed
17.1 GB
Fastest
113 tok/s
With 30B parameters, AgentFounder-30B 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 entry point is the RTX A4500: 20 GB of memory, IQ4_XS compression, roughly 22.2 tokens per second.
Top of the range is the B200, at roughly 113 tokens per second thanks to 8,000 GB/s of bandwidth.
About this model
AgentFounder-30B was published by Alibaba, in China, in September 2025. industry is the category the publisher falls under.
It works in Language, and is recorded as doing language modeling/generation, Question answering, System control, Quantitative reasoning, Mathematical reasoning, Code generation, Search.
It is derived from Qwen3-30B-A3B rather than trained from scratch, which is the usual way a specialised model is produced.
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 Alibaba-NLP organisation on Hugging Face.
How fast it runs, and why
The median result is around 22.0 tokens per second; 104 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.
How it was trained
Producing it required around 6.5 × 10²³ FLOP of arithmetic, which is a statement about the training budget rather than about inference.
Around 315,000,000,000 tokens went into training it.
The reason it appears in this catalogue at all is sOTA improvement.
Step by step
How to choose a GPU for AgentFounder-30B
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
Every card here has been checked against AgentFounder-30B — around 17.1 GB at IQ4_XS. Capacity is the gate — a card either holds it or it does not.
-
02
Match the context to your actual use
Longer conversations cost memory on top of what the weights need. Move the slider to your real working length before trusting any row for AgentFounder-30B.
-
03
Choose how far you will compress it
Compression is what makes AgentFounder-30B 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
Sort by speed
Ranking by tokens per second for AgentFounder-30B follows memory bandwidth, not core counts, which is why the B200 tops it at 113 tok/s.
-
05
Check the fit verdict before buying
The fit column separates cards that just manage AgentFounder-30B from those with room to spare. Buy for the second if the context might grow.
-
06
Open the card you have settled on
Each card page repeats this sweep for every model we hold. It answers what else the hardware is good for, beyond AgentFounder-30B.
Answers
AgentFounder-30B — common questions
How many parameters does AgentFounder-30B have?
AgentFounder-30B has 30B parameters. 30B-A3B. 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 AgentFounder-30B?
AgentFounder-30B was published by Alibaba, based in China, categorised as industry.
When was AgentFounder-30B released?
AgentFounder-30B was published in September 2025.
What is AgentFounder-30B used for?
AgentFounder-30B works in Language, and is recorded as handling language modeling/generation, Question answering, System control, Quantitative reasoning, Mathematical reasoning, Code generation, Search. 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 AgentFounder-30B?
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.
How much compute was used to train AgentFounder-30B?
Around 6.5 × 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 AgentFounder-30B 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 4.4 GB. Our figures for AgentFounder-30B assume it is fully resident.
Would two GPUs run AgentFounder-30B faster?
Capacity adds across cards; throughput does not. Since 132 of the cards we track already hold AgentFounder-30B on their own, a second card is rarely the answer here.
Why does the quantisation differ between cards for AgentFounder-30B?
A larger card holds a more accurate copy. Across the cards that run AgentFounder-30B, 5 compression levels are used; the floor control above pins it to one.
How accurate are these AgentFounder-30B speed estimates?
They are calculated from specifications rather than measured, and each carries a range — 68–181 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 AgentFounder-30B?
The smallest card in our catalogue that holds AgentFounder-30B is the RTX A4500, with 20 GB of memory. It runs the model at IQ4_XS using about 17.1 GB, and produces roughly 22.2 tokens per second. 132 cards in total can run it.
How fast is AgentFounder-30B on a GPU?
It depends on the card. The quickest we calculate is a B200 at about 113 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 AgentFounder-30B clear that.
How much VRAM does AgentFounder-30B need?
About 17.1 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 AgentFounder-30B on a 24 GB GPU?
Yes. A GeForce RTX 5090 D V2 with 24 GB runs it at Q4_K_M, using about 18.8 GB and generating roughly 43.7 tokens per second — a tight fit.
Is AgentFounder-30B open source?
Its weights are published, so AgentFounder-30B 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.
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.