MiMo-V2-Flash 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
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
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.
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
"We present MiMo-V2-Flash, a Mixture-of-Experts (MoE) model with 309B total parameters and 15B 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
- 2.4 × 10²⁴ FLOP
6 * 15e9 active parameters * 27e12 tokens = 2.43e+24
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 for 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.
- 01 B200 180 GB · 8,000 GB/s · Q3_K_M 29.6 tok/s
- 02 B300 288 GB · 8,000 GB/s · Q5_K_M 19.6 tok/s
- 03 Radeon Instinct MI350X 288 GB · 8,190 GB/s · Q5_K_M 15.6 tok/s
- 04 Radeon Instinct MI355X 288 GB · 8,190 GB/s · Q5_K_M 15.6 tok/s
- 05 Radeon Instinct MI300X 192 GB · 5,325 GB/s · IQ4_XS 14.0 tok/s
- 06 Radeon Instinct MI308X 192 GB · 5,325 GB/s · IQ4_XS 14.0 tok/s
- 07 Radeon Instinct MI325X 256 GB · 6,000 GB/s · Q5_K_M 11.5 tok/s
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.
- 01 B200 180 GB · needs 151.7 GB · Q3_K_M · tight 29.6 tok/s
- 02 Radeon Instinct MI300X 192 GB · needs 169.7 GB · IQ4_XS · tight 14.0 tok/s
- 03 Radeon Instinct MI308X 192 GB · needs 169.7 GB · IQ4_XS · tight 14.0 tok/s
- 04 Radeon Instinct MI325X 256 GB · needs 223.6 GB · Q5_K_M · tight 11.5 tok/s
- 05 B300 288 GB · needs 223.6 GB · Q5_K_M · tight 19.6 tok/s
- 06 Radeon Instinct MI350X 288 GB · needs 223.6 GB · Q5_K_M · tight 15.6 tok/s
- 07 Radeon Instinct MI355X 288 GB · needs 223.6 GB · Q5_K_M · tight 15.6 tok/s
What the numbers mean
The hardware side
Minimum card
B200
Memory needed
151.7 GB
Fastest
29.6 tok/s
At 309B parameters, MiMo-V2-Flash is beyond what any single graphics card holds. Running it means either splitting it across several cards or renting hardware built for the job — 7 of the cards we track can hold it on their own, and all of them are datacentre parts.
At the low end, a B200 handles it — 180 GB, at Q3_K_M, for about 29.6 tokens per second.
At the other end, a B200 generates roughly 29.6 tokens per second on it, on the strength of 8,000 GB/s of memory bandwidth.
Where it came from
MiMo-V2-Flash was published by Xiaomi Corp, in China, in December 2025. 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 XiaomiMiMo organisation on Hugging Face.
Understanding the speeds
Across every card that can run it, the middle of the range is about 15.6 tokens per second, and 7 of them clear the ten tokens per second that roughly matches reading speed.
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 around 2.4 × 10²⁴ FLOP of arithmetic, which is a statement about the training budget rather than about inference.
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 that can hold MiMo-V2-Flash — around 151.7 GB at Q3_K_M. That figure, not the card's headline performance, is what decides whether it runs.
-
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 MiMo-V2-Flash stops fitting a card that seemed fine.
-
03
Choose how far you will compress it
Compression is what makes MiMo-V2-Flash fit smaller cards, at some cost in accuracy — Q3_K_M on the smallest card that fits. A minimum quality removes the ones that go too far.
-
04
Rank by throughput rather than spec sheet
Ranking by tokens per second for MiMo-V2-Flash follows memory bandwidth, not core counts, which is why the B200 tops it at 29.6 tok/s.
-
05
Read the fit column last
A tight fit runs MiMo-V2-Flash but leaves nothing spare for a longer conversation; comfortable has headroom. If you expect to grow the context, buy for comfortable.
-
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 MiMo-V2-Flash is settled.
Answers
MiMo-V2-Flash — common questions
Can I run MiMo-V2-Flash 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 MiMo-V2-Flash is rarely worth using — the nearest miss we calculate is short by 60.7 GB. Every figure here assumes the whole model is on the card.
Would two GPUs run MiMo-V2-Flash faster?
Capacity adds across cards; throughput does not. Since 7 of the cards we track already hold MiMo-V2-Flash on their own, a second card is rarely the answer here.
Why does the quantisation differ between cards for MiMo-V2-Flash?
Because capacity varies, so does how hard MiMo-V2-Flash has to be squeezed — 3 distinct levels appear in the table above. Set a minimum quality to compare at one.
How accurate are these MiMo-V2-Flash speed estimates?
These are estimates with real error bars. The fastest result here, 18–47 tok/s on the B200, could reasonably land anywhere in its published range depending on which runtime you use.
What GPU do I need to run MiMo-V2-Flash?
The smallest card in our catalogue that holds MiMo-V2-Flash is the B200, with 180 GB of memory. It runs the model at Q3_K_M using about 151.7 GB, and produces roughly 29.6 tokens per second. 7 cards in total can run it.
How fast is MiMo-V2-Flash on a GPU?
It depends on the card. The quickest we calculate is a 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 7 of the cards that can run MiMo-V2-Flash clear that.
How much VRAM does MiMo-V2-Flash need?
About 151.7 GB at Q3_K_M compression, 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.
Is MiMo-V2-Flash open source?
Its weights are published, so MiMo-V2-Flash 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 MiMo-V2-Flash have?
MiMo-V2-Flash has 309B parameters. "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.
Who created MiMo-V2-Flash?
MiMo-V2-Flash was published by Xiaomi Corp, based in China, categorised as industry.
When was MiMo-V2-Flash released?
MiMo-V2-Flash was published in December 2025.
What is MiMo-V2-Flash used for?
MiMo-V2-Flash 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 MiMo-V2-Flash?
Its weights are published under the XiaomiMiMo 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 MiMo-V2-Flash?
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.
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.