P1-235B-A22B 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
Radeon Instinct MI250
128 GB · Q3_K_M · 69.1 tok/s
Fastest card
B200
143 tok/s · 180 GB
Which GPUs can run P1-235B-A22B?
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.
17 cards match
Calculating| Needs | Quantisation | Fit | |||||
|---|---|---|---|---|---|---|---|
|
143
tok/s
86–229 · low confidence |
B200 NVIDIA | 180 GB | 8,000 GB/s | Jan 2024 | 157.1 GB | Q5_K_M | Tight |
|
138
tok/s
83–221 · low confidence |
Radeon Instinct MI300 AMD | 128 GB | 6,550 GB/s | Jan 2023 | 102.4 GB | Q3_K_M | Tight |
|
120
tok/s
72–192 · low confidence |
H200 NVL NVIDIA | 141 GB | 4,890 GB/s | Nov 2024 | 116.0 GB | IQ4_XS | Tight |
|
120
tok/s
72–192 · low confidence |
H200 SXM 141 GB NVIDIA | 141 GB | 4,890 GB/s | Nov 2024 | 116.0 GB | IQ4_XS | Tight |
|
112
tok/s
67–180 · low confidence |
Radeon Instinct MI300A AMD | 128 GB | 5,325 GB/s | Dec 2023 | 102.4 GB | Q3_K_M | Tight |
|
80.1
tok/s
48–128 · low confidence |
B300 NVIDIA | 288 GB | 8,000 GB/s | Sep 2025 | 239.1 GB | Q8_0 | Tight |
|
74.3
tok/s
45–119 · low confidence |
Radeon Instinct MI300X AMD | 192 GB | 5,325 GB/s | Dec 2023 | 157.1 GB | Q5_K_M | Tight |
|
74.3
tok/s
45–119 · low confidence |
Radeon Instinct MI308X AMD | 192 GB | 5,325 GB/s | Dec 2023 | 157.1 GB | Q5_K_M | Tight |
|
69.1
tok/s
41–111 · low confidence |
Radeon Instinct MI250 AMD | 128 GB | 3,280 GB/s | Nov 2021 | 102.4 GB | Q3_K_M | Tight |
|
69.1
tok/s
41–111 · low confidence |
Radeon Instinct MI250X AMD | 128 GB | 3,280 GB/s | Nov 2021 | 102.4 GB | Q3_K_M | Tight |
|
68.1
tok/s
41–109 · low confidence |
Radeon Instinct MI325X AMD | 256 GB | 6,000 GB/s | Oct 2024 | 184.4 GB | Q6_K | Comfortable |
|
64.0
tok/s
38–102 · low confidence |
Radeon Instinct MI350X AMD | 288 GB | 8,190 GB/s | Jan 2025 | 239.1 GB | Q8_0 | Tight |
|
64.0
tok/s
38–102 · low confidence |
Radeon Instinct MI355X AMD | 288 GB | 8,190 GB/s | Jan 2025 | 239.1 GB | Q8_0 | Tight |
|
57.6
tok/s
35–92 · low confidence |
Data Center GPU Max 1550 Intel | 128 GB | 3,280 GB/s | Jan 2023 | 102.4 GB | Q3_K_M | Tight |
|
56.4
tok/s
34–90 · low confidence |
Data Center GPU Max Subsystem Intel | 128 GB | 3,210 GB/s | Jan 2023 | 102.4 GB | Q3_K_M | Tight |
|
7.4
tok/s
4–12 · low confidence |
GB10 NVIDIA | 128 GB | 273 GB/s | Oct 2025 | 102.4 GB | Q3_K_M | Tight |
|
7.4
tok/s
4–12 · low confidence |
Jetson T5000 NVIDIA | 128 GB | 273 GB/s | Aug 2025 | 102.4 GB | Q3_K_M | Tight |
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
- Shanghai AI Lab
- Organisation type
- Academia
- Country
- China
- Published
- 17 November 2025
- Authors
- Jiacheng Chen, Qianjia Cheng, Fangchen Yu, Haiyuan Wan, Yuchen Zhang, Shenghe Zheng, Junchi Yao, Qingyang Zhang, Haonan He, Yun Luo, Yufeng Zhao, Futing Wang, Li Sheng, Chengxing Xie, Yuxin Zuo, Yizhuo Li, Wenxauan Zeng, Yulun Wu, Rui Huang, Dongzhan Zhou, Kai Chen, Yu Qiao, Lei Bai, Yu Cheng, Ning Ding, Bowen Zhou, Peng Ye, Ganqu Cui
What it does
The problem areas the model was built for. A model can carry several of each.
- Domain
- Language
- Task
- Question answering
- Base model
- Qwen3-235B-A22B
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
- 235B
- Training data
- tokens
MoE: P1-235B-A22B has 235B total, 22B active parameters. Lightweight variant P1-30B-A3B has 30B total, 3B active. (https://arxiv.org/abs/2511.13612)
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)
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
- Discretionary
- Record confidence
- Likely
Sources
Where this record came from and when it was last checked.
- Reference
- P1: Mastering Physics Olympiads with Reinforcement Learning
- Last updated
- 8 April 2026
The extremes
The ten fastest GPUs that run P1-235B-A22B
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 B200 180 GB · 8,000 GB/s · Q5_K_M 143 tok/s
- 02 Radeon Instinct MI300 128 GB · 6,550 GB/s · Q3_K_M 138 tok/s
- 03 H200 NVL 141 GB · 4,890 GB/s · IQ4_XS 120 tok/s
- 04 H200 SXM 141 GB 141 GB · 4,890 GB/s · IQ4_XS 120 tok/s
- 05 Radeon Instinct MI300A 128 GB · 5,325 GB/s · Q3_K_M 112 tok/s
- 06 B300 288 GB · 8,000 GB/s · Q8_0 80.1 tok/s
- 07 Radeon Instinct MI300X 192 GB · 5,325 GB/s · Q5_K_M 74.3 tok/s
- 08 Radeon Instinct MI308X 192 GB · 5,325 GB/s · Q5_K_M 74.3 tok/s
- 09 Radeon Instinct MI250 128 GB · 3,280 GB/s · Q3_K_M 69.1 tok/s
- 10 Radeon Instinct MI250X 128 GB · 3,280 GB/s · Q3_K_M 69.1 tok/s
The smallest GPUs that still run P1-235B-A22B
The cheapest route in, by memory capacity. A tight fit runs the model but leaves nothing spare for a longer conversation.
- 01 GB10 128 GB · needs 102.4 GB · Q3_K_M · tight 7.4 tok/s
- 02 Jetson T5000 128 GB · needs 102.4 GB · Q3_K_M · tight 7.4 tok/s
- 03 Radeon Instinct MI300A 128 GB · needs 102.4 GB · Q3_K_M · tight 112 tok/s
- 04 Data Center GPU Max 1550 128 GB · needs 102.4 GB · Q3_K_M · tight 57.6 tok/s
- 05 Data Center GPU Max Subsystem 128 GB · needs 102.4 GB · Q3_K_M · tight 56.4 tok/s
- 06 Radeon Instinct MI300 128 GB · needs 102.4 GB · Q3_K_M · tight 138 tok/s
- 07 Radeon Instinct MI250 128 GB · needs 102.4 GB · Q3_K_M · tight 69.1 tok/s
- 08 Radeon Instinct MI250X 128 GB · needs 102.4 GB · Q3_K_M · tight 69.1 tok/s
- 09 H200 NVL 141 GB · needs 116.0 GB · IQ4_XS · tight 120 tok/s
- 10 H200 SXM 141 GB 141 GB · needs 116.0 GB · IQ4_XS · tight 120 tok/s
What the numbers mean
What it takes to run this model
Minimum card
Radeon Instinct MI250
Memory needed
102.4 GB
Fastest
143 tok/s
At 235B parameters, P1-235B-A22B is beyond what any single graphics card holds. Running it means either splitting it across several cards or renting hardware built for the job — 17 of the cards we track can hold it on their own, and all of them are datacentre parts.
The smallest card that holds it is the Radeon Instinct MI250 with 128 GB, running it at Q3_K_M and producing around 69.1 tokens per second.
At the other end, a B200 generates roughly 143 tokens per second on it, on the strength of 8,000 GB/s of memory bandwidth.
About this model
P1-235B-A22B was published by Shanghai AI Lab, in China, in November 2025. It comes out of academia.
It works in Language, and is recorded as doing question answering.
It is derived from Qwen3-235B-A22B rather than trained from scratch, which is the usual way a specialised model is produced.
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.
How fast it runs, and why
Half the cards that hold it manage more than 69.1 tokens per second, and 15 exceed reading speed outright.
Mixture-of-experts routing is why the speeds here look high for the parameter count. Only a fraction is read per token, but the whole thing has to be loaded.
Memory here is estimated from size rather than computed from the architecture, which is not recorded for this model — the numbers are indicative rather than exact.
Training and provenance
The reason it appears in this catalogue at all is discretionary.
Step by step
How to choose a GPU for P1-235B-A22B
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 P1-235B-A22B — around 102.4 GB at Q3_K_M. That figure, not the card's headline performance, is what decides whether it runs.
-
02
Match the context to your actual use
Set the context to what you will actually use. The cache grows with the conversation, and it is the usual reason P1-235B-A22B stops fitting a card that seemed fine.
-
03
Choose how far you will compress it
Compression is what makes P1-235B-A22B fit smaller cards, at some cost in accuracy — Q3_K_M on the smallest card that fits. A minimum quality removes the ones that go too far.
-
04
Sort by speed
The speed ordering for P1-235B-A22B is effectively an ordering by memory bandwidth, which is why the B200 tops it at 143 tok/s.
-
05
Look at the headroom, not just the fit
Tight means P1-235B-A22B loads and works, with no room to raise the context later. Comfortable means you can. The difference matters more than a few tokens per second.
-
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 P1-235B-A22B alone — a card is usually bought for more than one model.
Answers
P1-235B-A22B — common questions
What GPU do I need to run P1-235B-A22B?
The smallest card in our catalogue that holds P1-235B-A22B is the Radeon Instinct MI250, with 128 GB of memory. It runs the model at Q3_K_M using about 102.4 GB, and produces roughly 69.1 tokens per second. 17 cards in total can run it.
How fast is P1-235B-A22B on a GPU?
It depends on the card. The quickest we calculate is a B200 at about 143 tokens per second; the slowest that still runs it manages considerably less. Reading speed is around ten tokens per second, and 15 of the cards that can run P1-235B-A22B clear that.
How much VRAM does P1-235B-A22B need?
About 102.4 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.
Is P1-235B-A22B open source?
Its weights are published, so P1-235B-A22B 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 P1-235B-A22B have?
P1-235B-A22B has 235B parameters. MoE: P1-235B-A22B has 235B total, 22B active parameters. Lightweight variant P1-30B-A3B has 30B total, 3B active. (https://arxiv.org/abs/2511.13612). 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 P1-235B-A22B?
P1-235B-A22B was published by Shanghai AI Lab, based in China, categorised as academia.
When was P1-235B-A22B released?
P1-235B-A22B was published in November 2025.
What is P1-235B-A22B used for?
P1-235B-A22B works in Language, and is recorded as handling question answering. These are the areas it was designed around; they describe intent rather than a hard boundary.
Where can I download P1-235B-A22B?
The weights for P1-235B-A22B are published, though we do not hold a repository link for it. This site calculates hardware requirements rather than hosting model files.
Can I run P1-235B-A22B 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 P1-235B-A22B is rarely worth using — the nearest miss we calculate is short by 43.3 GB. Every figure here assumes the whole model is on the card.
Would two GPUs run P1-235B-A22B faster?
Two cards buy memory rather than speed. That matters for P1-235B-A22B only if one card cannot hold it — 17 can, so a second adds little.
Why does the quantisation differ between cards for P1-235B-A22B?
Because capacity varies, so does how hard P1-235B-A22B has to be squeezed — 5 distinct levels appear in the table above. Set a minimum quality to compare at one.
How accurate are these P1-235B-A22B speed estimates?
They are calculated from specifications rather than measured, and each carries a range — 86–229 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.