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
818 cards we hold specifications for
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
Kimi K2.5 reaches a parameter count of 1T. That is beyond what any single graphics card holds. Running it means either splitting it across several cards or renting hardware built for the job, and every card able to hold it alone is a datacentre part. The number that can: 0.
About this model
Kimi K2.5 was published by Moonshot, in the country recorded as China, during February 2026. 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.
The weights are published, so it can be downloaded and run on your own hardware indefinitely, offline, with no account attached. On Hugging Face it is published under the organisation moonshotai.
How it was trained
Training it took a computation budget of roughly 5.8 × 10²⁴ FLOP, on hardware recorded as NVIDIA H800 SXM5. That figure measures what producing the model cost, and has no bearing on how fast it answers.
The reason it appears in this catalogue at all: 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
Start from what it actually needs, which is the requirement of Kimi K2.5. Capacity is the gate — a card either holds it or it does not.
-
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 a card that seemed fine stops fitting Kimi K2.5.
-
03
Choose how far you will compress it
Each card runs the least-compressed copy it can hold. 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 Kimi K2.5. It will not match a gaming ordering, because generation is bound by memory bandwidth.
-
05
Look at the headroom, not just the fit
The fit column separates cards that just manage it from those with room to spare, in the case of Kimi K2.5. 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
Every card name links to its own page, which runs the same calculation across the whole model catalogue. A card is usually bought for more than one model, so it is worth a look before buying for Kimi K2.5.
Answers
Kimi K2.5 — common questions
Kimi K2.5— why does the quantisation differ between cards?
A larger card holds a more accurate copy. The number of compression levels used across the cards that run it: 1. Bigger cards get the more accurate version, and the quality floor above pins the comparison to one level.
Kimi K2.5— how accurate are these speed estimates?
They are calculated from specifications rather than measured, and each carries a range. One example: the range beneath each figure. The same model and card vary by thirty to fifty per cent depending on the inference software and its version.
Kimi K2.5— 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.
Kimi K2.5— how many parameters does it have?
It has a parameter count of 1T. "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.
Kimi K2.5— who created it?
It was published by Moonshot, based in China, an organisation categorised as industry.
Kimi K2.5— when was it released?
It was published in February 2026.
Kimi K2.5— what is it used for?
It works in the domain of Language, and is recorded as handling the task of language modeling/generation. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.
Kimi K2.5— where can I download it?
Its weights are published on Hugging Face, under the organisation moonshotai. We do not host model files — this site calculates what hardware is needed to run them.
Kimi K2.5— how much compute was used to train it?
Training consumed around 5.8 × 10²⁴ FLOP, on hardware recorded as 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.
Kimi K2.5— can I run it if it does not fit in my GPU?
It can be split between the card and system memory, but it generates painfully slowly that way. The nearest miss we calculate falls short by 370.7 GB. Every figure here assumes the whole model is resident on the card.
Kimi K2.5— would two GPUs run it faster?
A second card roughly doubles the memory available but not the generation rate. The number already able to run it alone: 0. So a second card is rarely the answer here.
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.