MiMo-V2.5-Pro 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 MiMo-V2.5-Pro?
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
- Xiaomi Corp
- Organisation type
- Industry
- Country
- China
- Published
- 23 April 2026
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
- Numerical format
- FP8
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
- 27,000,000,000,000 tokens
"MiMo-V2.5-Pro is a 1.02T-parameter Mixture-of-Experts model with 42B active 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
- 6.8 × 10²⁴ FLOP
6 FLOPS/token/active parameter * 27e12 tokens * 42e9 active parameters = 6.804E24 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)
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
- Xiaomi MiMo-V2.5-Pro
- Last updated
- 19 June 2026
What the numbers mean
What you need to run it
MiMo-V2.5-Pro 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.
Background
MiMo-V2.5-Pro was published by Xiaomi Corp, in the country recorded as China, during April 2026. The category the publisher falls under is industry.
It works in the domain of Language, and is recorded as performing the task of language modeling/generation, Question answering.
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 it was trained
Training it took a computation budget of roughly 6.8 × 10²⁴ FLOP. That figure measures what producing the model cost, and has no bearing on how fast it answers.
The training set ran to roughly 27,000,000,000,000 tokens of text.
It is tracked in the underlying dataset for one reason in particular: discretionary.
Step by step
How to choose a GPU for MiMo-V2.5-Pro
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 MiMo-V2.5-Pro. Capacity is the gate — a card either holds it or it does not.
-
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 a card that seemed fine stops fitting MiMo-V2.5-Pro.
-
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
Rank by throughput rather than spec sheet
Sort by speed to see how cards rank for MiMo-V2.5-Pro. It will not match a gaming ordering, because generation is bound by memory bandwidth.
-
05
Read the fit column last
Tight means it loads and works with no room to raise the context later, in the case of MiMo-V2.5-Pro. 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
Open the card you have settled on
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 MiMo-V2.5-Pro.
Answers
MiMo-V2.5-Pro — common questions
MiMo-V2.5-Pro— 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 287.1 GB. Every figure here assumes the whole model is resident on the card.
MiMo-V2.5-Pro— 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.
MiMo-V2.5-Pro— why does the quantisation differ between cards?
Each card is shown running the least-compressed copy it can hold. The number of distinct compression levels across the cards that fit it: 1. Bigger cards get the more accurate version, and the quality floor above pins the comparison to one level.
MiMo-V2.5-Pro— 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.
MiMo-V2.5-Pro— 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.
MiMo-V2.5-Pro— how many parameters does it have?
It has a parameter count of 1T. "MiMo-V2.5-Pro is a 1.02T-parameter Mixture-of-Experts model with 42B active 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.
MiMo-V2.5-Pro— who created it?
It was published by Xiaomi Corp, based in China, an organisation categorised as industry.
MiMo-V2.5-Pro— when was it released?
It was published in April 2026.
MiMo-V2.5-Pro— 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. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.
MiMo-V2.5-Pro— where can I download it?
The weights are published, though we do not hold a repository link for it. This site calculates hardware requirements rather than hosting model files.
MiMo-V2.5-Pro— how much compute was used to train it?
Training consumed around 6.8 × 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.
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.