MiMo-V2-Flash TPS calculator

Open weights Xiaomi Corp 309B parameters December 2025

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

7 cards that can run it

818 cards we hold specifications for

Smallest card that fits

B200

180 GB · Q3_K_M · 29.6 tok/s

Fastest card

B200

29.6 tok/s · 180 GB

Which GPUs can run MiMo-V2-Flash?

Set the inputs, read the answer

Context length tokens

A longer conversation needs more memory, which can push this model off smaller cards.

Minimum quality

Hides cards that would only fit the model by compressing it below this point.

Search cards

Card memory

Also show cards that cannot run it

7 cards match

Calculating

					Needs	Quantisation	Fit
29.6 tok/s 18–47 · low confidence	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	151.7 GB	Q3_K_M	Tight
19.6 tok/s 12–31 · low confidence	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	223.6 GB	Q5_K_M	Tight
15.6 tok/s 9–25 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	223.6 GB	Q5_K_M	Tight
15.6 tok/s 9–25 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	223.6 GB	Q5_K_M	Tight
14.0 tok/s 8–22 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	169.7 GB	IQ4_XS	Tight
14.0 tok/s 8–22 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	169.7 GB	IQ4_XS	Tight
11.5 tok/s 7–18 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	223.6 GB	Q5_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: Xiaomi Corp
Organisation type: Industry
Country: China
Published: 16 December 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

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: 309B
Training data: tokens

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: 2.4 × 10²⁴ 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)
Hugging Face: XiaomiMiMo

How it is classified

Labels the source dataset applies when tracking notable models, and how confident it is in the entry.

Record confidence: Likely

Sources

Where this record came from and when it was last checked.

Reference: MiMo-V2-Flash Technical Report
Last updated: 19 June 2026

The extremes

The ten fastest GPUs that run MiMo-V2-Flash

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.

The smallest GPUs that still run MiMo-V2-Flash

The cheapest route in, by memory capacity. A tight fit runs the model but leaves nothing spare for a longer conversation.

What the numbers mean

The hardware side

Minimum card

B200

Memory needed

151.7 GB

Fastest

29.6 tok/s

MiMo-V2-Flash reaches a parameter count of 309B. 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: 7.

At the low end it is handled by B200, with a memory capacity of 180 GB, running it at a compression of Q3_K_M and producing around 29.6 tokens per second.

At the other end sits B200, generating roughly 29.6 tokens per second on the strength of a memory bandwidth of 8,000 GB/s.

Where it came from

MiMo-V2-Flash was published by Xiaomi Corp, in the country recorded as China, during December 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.

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 XiaomiMiMo.

Understanding the speeds

Across every card that can run it, the middle of the range sits at 15.6 tokens per second. Clearing the ten tokens per second that roughly matches reading speed: 7 of them.

Every weight participates in every token here, so bandwidth is the whole story: the ranking below is effectively a ranking of memory throughput.

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

Producing it required arithmetic totalling around 2.4 × 10²⁴ FLOP. That figure measures what producing the model cost, and has no bearing on how fast it answers.

Step by step

How to choose a GPU for MiMo-V2-Flash

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

The table lists every card able to hold MiMo-V2-Flash, needing around 151.7 GB at a compression of Q3_K_M. 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-Flash.
03

Choose how far you will compress it

Compression is what makes a model fit smaller cards, at some cost in accuracy, reaching a compression of Q3_K_M on the smallest card that fits. 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

Ranking by tokens per second follows memory bandwidth rather than core counts, for MiMo-V2-Flash. It will not match a gaming ordering, because generation is bound by memory bandwidth. The card topping the list is B200, at 29.6 tok/s.
05

Read the fit column last

A tight fit runs, but leaves nothing spare for a longer conversation, in the case of MiMo-V2-Flash. 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 MiMo-V2-Flash.

Answers

MiMo-V2-Flash — common questions

MiMo-V2-Flash— can I run it 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 model is rarely worth using. The nearest miss we calculate falls short by 60.7 GB. Every figure here assumes the whole model is resident on the card.

MiMo-V2-Flash— would two GPUs run it faster?

Capacity adds across cards; throughput does not. The number of cards already holding it on their own: 7. So a second card is rarely the answer here.

MiMo-V2-Flash— 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: 3. Bigger cards get the more accurate version, and the quality floor above pins the comparison to one level.

MiMo-V2-Flash— 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: 18–47 tok/s on B200. The same model and card vary by thirty to fifty per cent depending on the inference software and its version.

MiMo-V2-Flash— what GPU do I need to run it?

The smallest card in our catalogue that holds it is B200, with a memory capacity of 180 GB. It runs the model at a compression of Q3_K_M using about 151.7 GB, and produces roughly 29.6 tokens per second. The number of cards able to run it in total: 7.

MiMo-V2-Flash— how fast is it on a GPU?

It depends on the card. The quickest we calculate is B200, at about 29.6 tokens per second; the slowest that still runs it manages considerably less. Reading speed is around ten tokens per second, and the number of cards clearing that: 7.

MiMo-V2-Flash— how much VRAM does it need?

It needs about 151.7 GB at a compression of Q3_K_M, 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.

MiMo-V2-Flash— 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-Flash— how many parameters does it have?

It has a parameter count of 309B. "We present MiMo-V2-Flash, a Mixture-of-Experts (MoE) model with 309B total parameters and 15B 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-Flash— who created it?

It was published by Xiaomi Corp, based in China, an organisation categorised as industry.

MiMo-V2-Flash— when was it released?

It was published in December 2025.

MiMo-V2-Flash— 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.

MiMo-V2-Flash— where can I download it?

Its weights are published on Hugging Face, under the organisation XiaomiMiMo. We do not host model files — this site calculates what hardware is needed to run them.

MiMo-V2-Flash— how much compute was used to train it?

Training consumed around 2.4 × 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.

Source

Original publication

Record last updated 19 June 2026

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.

All AI models