Kimi K2.5 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
Which GPUs can run Kimi K2.5?
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.
0 cards match
Calculating| Needs | Quantisation | Fit | |||||
|---|---|---|---|---|---|---|---|
|
No card in our catalogue can run this model with these settings. |
|||||||
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
- Moonshot
- Organisation type
- Industry
- Country
- China
- Published
- 2 February 2026
- Authors
- Tongtong Bai, Yifan Bai, Yiping Bao, S.H. Cai, Yuan Cao, Y. Charles, H.S. Che, Cheng Chen, Guanduo Chen, Huarong Chen, Jia Chen, Jiahao Chen, Jianlong Chen, Jun Chen, Kefan Chen, Liang Chen, Ruijue Chen, Xinhao Chen, Yanru Chen, Yanxu Chen, Yicun Chen, Yimin Chen, Yingjiang Chen, Yuankun Chen, Yujie Chen, Yutian Chen, Zhirong Chen, Ziwei Chen, Dazhi Cheng, Minghan Chu, Jialei Cui, Jiaqi Deng, Muxi…
What it does
The problem areas the model was built for. A model can carry several of each.
- Domain
- Language
- Task
- Language modeling/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
- 1T
- Training data
- tokens
"The model comprises 1.04 trillion total parameters"
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
- 5.8 × 10²⁴ FLOP
Per section 3.2, "The joint pre-training stage continues from a near-end Kimi K2 checkpoint over additional 15T vision-text tokens at 4K sequence length" Kimi K2 was pretrained on 15T tokens. A near-end checkpoint of K2 was trained into K2.5 over another 15T tokens (or 15.2 to 15.5T tokens). This makes for a total of ~30T. There are an additional 1T tokens in "Stage 1" used to train the ViT encoder, which is likely much smaller than the full LLM, so we omit those tokens to calculate training c…
The training run
What it physically took to train: which chips, how many, for how long, and what that drew from the wall.
- Training hardware
- NVIDIA H800 SXM5
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)
- Hugging Face
- moonshotai
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
Cost-competitive and widely used in the open-weight AI industry
Sources
Where this record came from and when it was last checked.
- Reference
- Kimi K2.5: Visual Agentic Intelligence
- Last updated
- 28 May 2026
What the numbers mean
What it takes to run this model
At 1T parameters, Kimi K2.5 is beyond what any single graphics card holds. Running it means either splitting it across several cards or renting hardware built for the job — 0 of the cards we track can hold it on their own, and all of them are datacentre parts.
About this model
Kimi K2.5 was published by Moonshot, in China, in February 2026. It comes out of industry.
It works in Language, and is recorded as doing language modeling/generation.
The weights are published, so it can be downloaded and run on your own hardware indefinitely, offline, with no account attached. It is published under the moonshotai organisation on Hugging Face.
How it was trained
Training it took roughly 5.8 × 10²⁴ FLOP of computation, on NVIDIA H800 SXM5 — a measure of what producing the model cost, not of how fast it answers.
The reason it appears in this catalogue at all is discretionary.
Step by step
How to choose a GPU for Kimi K2.5
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 Kimi K2.5 actually needs. No amount of processing power compensates for a card that cannot hold it.
-
02
Decide how long your conversations run
Set the context to what you will actually use. The cache grows with the conversation, and it is the usual reason Kimi K2.5 stops fitting a card that seemed fine.
-
03
Choose how far you will compress it
Each card runs the least-compressed copy it can hold. Setting a floor drops the cards that only manage Kimi K2.5 by squeezing it further than you would want.
-
04
Compare tokens per second, not specifications
Ranking by tokens per second for Kimi K2.5 follows memory bandwidth, not core counts.
-
05
Look at the headroom, not just the fit
The fit column separates cards that just manage Kimi K2.5 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 Kimi K2.5 alone — a card is usually bought for more than one model.
Answers
Kimi K2.5 — common questions
Why does the quantisation differ between cards for Kimi K2.5?
A larger card holds a more accurate copy. Across the cards that run Kimi K2.5, 1 compression levels are used; the floor control above pins it to one.
How accurate are these Kimi K2.5 speed estimates?
They are calculated from specifications rather than measured, and each carries a range — the range beneath each figure, for instance. The same model and card vary by thirty to fifty per cent depending on the inference software and its version.
Is Kimi K2.5 open source?
Its weights are published, so Kimi K2.5 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 Kimi K2.5 have?
Kimi K2.5 has 1T parameters. "The model comprises 1.04 trillion total parameters". 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 Kimi K2.5?
Kimi K2.5 was published by Moonshot, based in China, categorised as industry.
When was Kimi K2.5 released?
Kimi K2.5 was published in February 2026.
What is Kimi K2.5 used for?
Kimi K2.5 works in Language, and is recorded as handling language modeling/generation. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.
Where can I download Kimi K2.5?
Its weights are published under the moonshotai 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 Kimi K2.5?
Around 5.8 × 10²⁴ FLOP, on NVIDIA H800 SXM5. 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 Kimi K2.5 if it does not fit in my GPU?
It can be split between the card and system memory, but Kimi K2.5 generates painfully slowly that way — the nearest miss we calculate is short by 370.7 GB. Nothing on this page assumes offloading.
Would two GPUs run Kimi K2.5 faster?
A second card roughly doubles the memory available but not the generation rate. With 0 cards already able to run Kimi K2.5 alone, the case for pairing is weak.
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.