MiMo‑VL‑7B‑RL TPS calculator

Open weights Xiaomi Corp 7B parameters June 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

589 cards that can run it

818 cards we hold specifications for

Smallest card that fits

Tesla K20c

5 GB · Q3_K_M · 28.9 tok/s

Fastest card

B200

484 tok/s · 180 GB

Which GPUs can run MiMo‑VL‑7B‑RL?

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

589 cards match

Calculating

					Needs	Quantisation	Fit
484 tok/s 290–774 · low confidence	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	8.2 GB	Q8_0	Comfortable
484 tok/s 290–774 · low confidence	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	8.2 GB	Q8_0	Comfortable
387 tok/s 232–618 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	8.2 GB	Q8_0	Comfortable
387 tok/s 232–618 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	8.2 GB	Q8_0	Comfortable
309 tok/s 185–495 · low confidence	Radeon Instinct MI300 AMD	128 GB	6,550 GB/s	Jan 2023	8.2 GB	Q8_0	Comfortable
296 tok/s 178–473 · low confidence	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	8.2 GB	Q8_0	Comfortable
296 tok/s 178–473 · low confidence	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	8.2 GB	Q8_0	Comfortable
283 tok/s 170–453 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	8.2 GB	Q8_0	Comfortable
251 tok/s 151–402 · low confidence	Radeon Instinct MI300A AMD	128 GB	5,325 GB/s	Dec 2023	8.2 GB	Q8_0	Comfortable
251 tok/s 151–402 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	8.2 GB	Q8_0	Comfortable
251 tok/s 151–402 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	8.2 GB	Q8_0	Comfortable
238 tok/s 143–381 · low confidence	H100 NVL 94 GB NVIDIA	94 GB	3,940 GB/s	Mar 2023	8.2 GB	Q8_0	Comfortable
203 tok/s 122–325 · low confidence	H100 PCIe 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	8.2 GB	Q8_0	Comfortable
203 tok/s 122–325 · low confidence	H100 SXM5 80 GB NVIDIA	80 GB	3,360 GB/s	Oct 2022	8.2 GB	Q8_0	Comfortable
203 tok/s 122–325 · low confidence	H100 SXM5 94 GB NVIDIA	94 GB	3,360 GB/s	Mar 2023	8.2 GB	Q8_0	Comfortable
203 tok/s 122–325 · low confidence	H100 SXM5 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	8.2 GB	Q8_0	Comfortable
203 tok/s 122–325 · low confidence	H800 SXM5 NVIDIA	80 GB	3,360 GB/s	Mar 2023	8.2 GB	Q8_0	Comfortable
155 tok/s 93–248 · low confidence	Radeon Instinct MI250 AMD	128 GB	3,280 GB/s	Nov 2021	8.2 GB	Q8_0	Comfortable
155 tok/s 93–248 · low confidence	Radeon Instinct MI250X AMD	128 GB	3,280 GB/s	Nov 2021	8.2 GB	Q8_0	Comfortable
131 tok/s 79–210 · low confidence	CMP 170HX 8 GB NVIDIA	8 GB	1,490 GB/s	Sep 2021	6.6 GB	Q6_K	Tight
129 tok/s 77–206 · low confidence	Data Center GPU Max 1550 Intel	128 GB	3,280 GB/s	Jan 2023	8.2 GB	Q8_0	Comfortable
126 tok/s 76–202 · low confidence	Data Center GPU Max Subsystem Intel	128 GB	3,210 GB/s	Jan 2023	8.2 GB	Q8_0	Comfortable
123 tok/s 74–197 · low confidence	A100 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Nov 2020	8.2 GB	Q8_0	Comfortable
123 tok/s 74–197 · low confidence	A100X NVIDIA	80 GB	2,040 GB/s	Jun 2021	8.2 GB	Q8_0	Comfortable
123 tok/s 74–197 · low confidence	A800 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Aug 2022	8.2 GB	Q8_0	Comfortable

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: 4 June 2025
Authors: Xiaomi LLM-Core Team: Zihao Yue, Zhenru Lin, Yifan Song, Weikun Wang, Shuhuai Ren, Shuhao Gu, Shicheng Li, Peidian Li, Liang Zhao, Lei Li, Kainan Bao, Hao Tian, Hailin Zhang, Gang Wang, Dawei Zhu, Cici, Chenhong He, Bowen Ye, Bowen Shen, Zihan Zhang, Zihan Jiang, Zhixian Zheng, Zhichao Song, Zhenbo Luo, Yue Yu, Yudong Wang, Yuanyuan Tian, Yu Tu, Yihan Yan, Yi Huang, Xu Wang, Xinzhe Xu, Xingchen So…

What it does

The problem areas the model was built for. A model can carry several of each.

Domain: Vision, Multimodal, Language, Video
Task: Character recognition (OCR), Image captioning, Language modeling/generation, Question answering, Visual question answering, Video, Video description
Approach: Reinforcement learning
Base model: MiMo-VL-7B-SFT

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: 7B
Training data: tokens

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)
Training code: Unreleased
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: Confident

Sources

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

Reference: MiMo-VL Technical Report
Last updated: 28 November 2025

The extremes

The ten fastest GPUs that run MiMo‑VL‑7B‑RL

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‑VL‑7B‑RL

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

What you need to run it

Minimum card

Tesla K20c

Memory needed

4.1 GB

Fastest

484 tok/s

MiMo‑VL‑7B‑RL is small enough at 7B parameters that hardware is rarely the obstacle — 589 of the cards we track can run it, including cards several years old.

The least hardware that works is a Tesla K20c. Its 5 GB is enough at Q3_K_M compression, giving roughly 28.9 tokens per second.

A B200 is the fastest we calculate for it: about 484 tokens per second, from 8,000 GB/s of memory bandwidth.

What this model is

MiMo‑VL‑7B‑RL was published by Xiaomi Corp, in China, in June 2025. The organisation is categorised as industry.

It works in Vision, Multimodal, Language, Video, and is recorded as doing character recognition (OCR), Image captioning, Language modeling/generation, Question answering, Visual question answering, Video, Video description.

It builds on MiMo-VL-7B-SFT, which is why it shares that model's general shape and size.

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.

What decides the speed

Half the cards that hold it manage more than 26.1 tokens per second, and 559 exceed reading speed outright.

Being dense, it reads all of itself per token, which is why the ordering by speed below follows the ordering by memory bandwidth so closely.

Its internal architecture is not on file, so memory is approximated from the parameter count and marked accordingly. Expect the real figure to differ, more so at long context.

Step by step

How to choose a GPU for MiMo‑VL‑7B‑RL

The table above has already assessed every card we hold specifications for against this model. Getting to your answer takes six steps.

01

Start from the memory column

Look at what MiMo‑VL‑7B‑RL actually needs — around 4.1 GB at Q3_K_M. No amount of processing power compensates for a card that cannot hold it.
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‑VL‑7B‑RL stops fitting a card that seemed fine.
03

Choose how far you will compress it

Each card runs the least-compressed copy it can hold — Q3_K_M on the smallest card that fits. Setting a floor drops the cards that only manage MiMo‑VL‑7B‑RL by squeezing it further than you would want.
04

Compare tokens per second, not specifications

Sort by speed to see how cards rank for MiMo‑VL‑7B‑RL. It will not match a gaming ordering — generation is bound by memory bandwidth, which is why the B200 tops it at 484 tok/s.
05

Check the fit verdict before buying

The fit column separates cards that just manage MiMo‑VL‑7B‑RL from those with room to spare. Buy for the second if the context might grow.
06

Open the card you have settled on

Every card name links to its own page, which runs the same calculation across the whole model catalogue. Worth a look before buying for MiMo‑VL‑7B‑RL alone — a card is usually bought for more than one model.

Answers

MiMo‑VL‑7B‑RL — common questions

Can I run MiMo‑VL‑7B‑RL on a 16 GB GPU?

Yes. A Tesla V100 SXM2 16 GB with 16 GB runs it at Q8_0, using about 8.2 GB and generating roughly 68.4 tokens per second — a comfortable fit.

Can I run MiMo‑VL‑7B‑RL on a 24 GB GPU?

Yes. A GeForce RTX 5090 D V2 with 24 GB runs it at Q8_0, using about 8.2 GB and generating roughly 81.1 tokens per second — a comfortable fit.

Is MiMo‑VL‑7B‑RL open source?

Its weights are published, so MiMo‑VL‑7B‑RL 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‑VL‑7B‑RL have?

MiMo‑VL‑7B‑RL has 7B 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‑VL‑7B‑RL?

MiMo‑VL‑7B‑RL was published by Xiaomi Corp, based in China, categorised as industry.

When was MiMo‑VL‑7B‑RL released?

MiMo‑VL‑7B‑RL was published in June 2025.

What is MiMo‑VL‑7B‑RL used for?

MiMo‑VL‑7B‑RL works in Vision, Multimodal, Language, Video, and is recorded as handling character recognition (OCR), Image captioning, Language modeling/generation, Question answering, Visual question answering, Video, Video description. A model can carry several of each, so these are the areas it was built for rather than a limit on what it will attempt.

Where can I download MiMo‑VL‑7B‑RL?

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.

Can I run MiMo‑VL‑7B‑RL if it does not fit in my GPU?

It can be split between the card and system memory, but MiMo‑VL‑7B‑RL generates painfully slowly that way — the nearest miss we calculate is short by 1.3 GB. Nothing on this page assumes offloading.

Would two GPUs run MiMo‑VL‑7B‑RL faster?

Two cards buy memory rather than speed. That matters for MiMo‑VL‑7B‑RL only if one card cannot hold it — 589 can, so a second adds little.

Why does the quantisation differ between cards for MiMo‑VL‑7B‑RL?

Each card is shown running the least-compressed copy it can hold, and MiMo‑VL‑7B‑RL appears at 4 different compression levels across the cards that fit it. Bigger cards get the more accurate version.

How accurate are these MiMo‑VL‑7B‑RL speed estimates?

Every figure is derived from memory bandwidth and model size, not benchmarked. That is why each is published as a range such as 290–774 tok/s on the B200 rather than a single number.

What GPU do I need to run MiMo‑VL‑7B‑RL?

The smallest card in our catalogue that holds MiMo‑VL‑7B‑RL is the Tesla K20c, with 5 GB of memory. It runs the model at Q3_K_M using about 4.1 GB, and produces roughly 28.9 tokens per second. 589 cards in total can run it.

How fast is MiMo‑VL‑7B‑RL on a GPU?

It depends on the card. The quickest we calculate is a B200 at about 484 tokens per second; the slowest that still runs it manages considerably less. Reading speed is around ten tokens per second, and 559 of the cards that can run MiMo‑VL‑7B‑RL clear that.

How much VRAM does MiMo‑VL‑7B‑RL need?

About 4.1 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.

Can I run MiMo‑VL‑7B‑RL on a 8 GB GPU?

Yes. A CMP 170HX 8 GB with 8 GB runs it at Q6_K, using about 6.6 GB and generating roughly 131 tokens per second — a tight fit.

Can I run MiMo‑VL‑7B‑RL on a 12 GB GPU?

Yes. A GeForce RTX 3080 Ti with 12 GB runs it at Q8_0, using about 8.2 GB and generating roughly 55.2 tokens per second — a comfortable fit.

Source

Original publication

Record last updated 28 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.

All AI models