Kimi K2 Thinking 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 Thinking?
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
- 6 November 2025
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, Search, Quantitative reasoning, Code generation
- Base model
- Kimi K2
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
Total Parameters 1T Activated Parameters 32B
"Kimi K2 was pre-trained on 15.5T tokens" Training dataset size for Kimi K2 Thinking is not reported
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
- 4.2 × 10²⁴ FLOP
- How it was established
- Comparison with other models
Assuming the additional post-training contributed between 1% and 100% of Kimi K2's training compute (which we confidently estimate at 2.976e+24), we get a range of 3.0e24 to 6.0e24, and a geometric mean of 4.2e24.
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 (restricted use)
- Training code
- Unreleased
- Hugging Face
- moonshotai
modified MIT license (capped by 100M MAU or $20M monthly revenue) https://huggingface.co/moonshotai/Kimi-K2-Thinking
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
- Likely
Kimi K2 Thinking sets new records across benchmarks that assess reasoning, coding, and agent capabilities. K2 Thinking achieves 44.9% on HLE with tools, 60.2% on BrowseComp, and 71.3% on SWE-Bench Verified, demonstrating strong generalization as a state-of-the-art thinking agent model.
Sources
Where this record came from and when it was last checked.
- Reference
- Introducing Kimi K2 Thinking
- Last updated
- 3 December 2025
What the numbers mean
What it takes to run this model
Kimi K2 Thinking 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 Thinking was published by Moonshot, in the country recorded as China, during November 2025. 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, Question answering, Search, Quantitative reasoning, Code generation.
Rather than being trained from scratch, it is derived from Kimi K2. That is the usual way a specialised model is produced.
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 4.2 × 10²⁴ FLOP. 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: sOTA improvement.
Step by step
How to choose a GPU for Kimi K2 Thinking
The table above has already assessed every card we hold specifications for against this model. Getting to your answer takes six steps.
-
01
Read the memory figure first
Every card here has been checked against Kimi K2 Thinking. That figure, not the headline performance of a card, is what decides whether it runs.
-
02
Set the context length you will work at
The conversation occupies memory too, and grows as it goes. Set the slider to the length you expect, because at long context a card that handles short questions easily can be dropped by Kimi K2 Thinking.
-
03
Decide how much compression you will accept
The quantisation column varies by card, because a bigger card holds a more accurate copy. 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
Sort by speed
Ranking by tokens per second follows memory bandwidth rather than core counts, for Kimi K2 Thinking. It will not match a gaming ordering, because generation is bound by memory bandwidth.
-
05
Look at the headroom, not just the fit
A tight fit runs, but leaves nothing spare for a longer conversation, in the case of Kimi K2 Thinking. 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
Following a card through to its own page shows every other model it can hold, which is the question that follows once you have settled on Kimi K2 Thinking.
Answers
Kimi K2 Thinking — common questions
Kimi K2 Thinking— what is it used for?
It works in the domain of Language, and is recorded as handling the task of language modeling/generation, Question answering, Search, Quantitative reasoning, Code generation. These are the areas it was designed around; they describe intent rather than a hard boundary.
Kimi K2 Thinking— 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 Thinking— how much compute was used to train it?
Training consumed around 4.2 × 10²⁴ 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.
Kimi K2 Thinking— 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 346.5 GB. Every figure here assumes the whole model is resident on the card.
Kimi K2 Thinking— 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.
Kimi K2 Thinking— why does the quantisation differ between cards?
Because capacity varies, so does how hard it has to be squeezed. The number of distinct levels in the table above: 1. Bigger cards get the more accurate version, and the quality floor above pins the comparison to one level.
Kimi K2 Thinking— how accurate are these speed estimates?
These are estimates with real error bars, and any of them could reasonably land anywhere in its published range depending on which runtime you use. The fastest result here: 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 Thinking— 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 Thinking— how many parameters does it have?
It has a parameter count of 1T. Total Parameters 1T Activated Parameters 32B. 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 Thinking— who created it?
It was published by Moonshot, based in China, an organisation categorised as industry.
Kimi K2 Thinking— when was it released?
It was published in November 2025.
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.