MiniCPM-2.4B TPS calculator

Open weights Tsinghua University,ModelBest 2.4B parameters June 2024

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 that can run it

818 cards we hold specifications for

Smallest card that fits

Tesla C1080

4 GB · Q8_0 · 15.1 tok/s

Fastest card

B200

1,387 tok/s · 180 GB

Which GPUs can run MiniCPM-2.4B?

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

818 cards match

Calculating

					Needs	Quantisation	Fit
1,387 tok/s 832–2,220 · low confidence	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	3.3 GB	Q8_0	Comfortable
1,387 tok/s 832–2,220 · low confidence	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	3.3 GB	Q8_0	Comfortable
1,108 tok/s 665–1,773 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	3.3 GB	Q8_0	Comfortable
1,108 tok/s 665–1,773 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	3.3 GB	Q8_0	Comfortable
886 tok/s 532–1,418 · low confidence	Radeon Instinct MI300 AMD	128 GB	6,550 GB/s	Jan 2023	3.3 GB	Q8_0	Comfortable
848 tok/s 509–1,357 · low confidence	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	3.3 GB	Q8_0	Comfortable
848 tok/s 509–1,357 · low confidence	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	3.3 GB	Q8_0	Comfortable
812 tok/s 487–1,299 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	3.3 GB	Q8_0	Comfortable
720 tok/s 432–1,153 · low confidence	Radeon Instinct MI300A AMD	128 GB	5,325 GB/s	Dec 2023	3.3 GB	Q8_0	Comfortable
720 tok/s 432–1,153 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	3.3 GB	Q8_0	Comfortable
720 tok/s 432–1,153 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	3.3 GB	Q8_0	Comfortable
683 tok/s 410–1,093 · low confidence	H100 NVL 94 GB NVIDIA	94 GB	3,940 GB/s	Mar 2023	3.3 GB	Q8_0	Comfortable
583 tok/s 350–932 · low confidence	H100 PCIe 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	3.3 GB	Q8_0	Comfortable
583 tok/s 350–932 · low confidence	H100 SXM5 80 GB NVIDIA	80 GB	3,360 GB/s	Oct 2022	3.3 GB	Q8_0	Comfortable
583 tok/s 350–932 · low confidence	H100 SXM5 94 GB NVIDIA	94 GB	3,360 GB/s	Mar 2023	3.3 GB	Q8_0	Comfortable
583 tok/s 350–932 · low confidence	H100 SXM5 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	3.3 GB	Q8_0	Comfortable
583 tok/s 350–932 · low confidence	H800 SXM5 NVIDIA	80 GB	3,360 GB/s	Mar 2023	3.3 GB	Q8_0	Comfortable
444 tok/s 266–710 · low confidence	Radeon Instinct MI250 AMD	128 GB	3,280 GB/s	Nov 2021	3.3 GB	Q8_0	Comfortable
444 tok/s 266–710 · low confidence	Radeon Instinct MI250X AMD	128 GB	3,280 GB/s	Nov 2021	3.3 GB	Q8_0	Comfortable
370 tok/s 222–592 · low confidence	Data Center GPU Max 1550 Intel	128 GB	3,280 GB/s	Jan 2023	3.3 GB	Q8_0	Comfortable
362 tok/s 217–579 · low confidence	Data Center GPU Max Subsystem Intel	128 GB	3,210 GB/s	Jan 2023	3.3 GB	Q8_0	Comfortable
354 tok/s 212–566 · low confidence	A100 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Nov 2020	3.3 GB	Q8_0	Comfortable
354 tok/s 212–566 · low confidence	A100X NVIDIA	80 GB	2,040 GB/s	Jun 2021	3.3 GB	Q8_0	Comfortable
354 tok/s 212–566 · low confidence	A800 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Aug 2022	3.3 GB	Q8_0	Comfortable
354 tok/s 212–566 · low confidence	H100 CNX NVIDIA	80 GB	2,040 GB/s	Mar 2023	3.3 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: Tsinghua University,ModelBest
Organisation type: Academia,Industry
Country: China
Published: 3 June 2024
Authors: Shengding Hu, Yuge Tu, Xu Han, Chaoqun He, Ganqu Cui, Xiang Long, Zhi Zheng, Yewei Fang, Yuxiang Huang, Weilin Zhao, Xinrong Zhang, Zheng Leng Thai, Kaihuo Zhang, Chongyi Wang, Yuan Yao, Chenyang Zhao, Jie Zhou, Jie Cai, Zhongwu Zhai, Ning Ding, Chao Jia, Guoyang Zeng, Dahai Li, Zhiyuan Liu, Maosong Sun

What it does

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

Domain: Language
Task: Language modeling/generation, Code generation, Translation

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: 2.4B
Training data: tokens
Batch size: 4,000,000

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: 1.6 × 10²² FLOP
How it was established: Operation counting

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

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: MiniCPM: Unveiling the Potential of Small Language Models with Scalable Training Strategies
Last updated: 28 November 2025

The extremes

The ten fastest GPUs that run MiniCPM-2.4B

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 MiniCPM-2.4B

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 it takes to run this model

Minimum card

Tesla C1080

Memory needed

3.3 GB

Fastest

1,387 tok/s

MiniCPM-2.4B is small enough at 2.4B parameters that hardware is rarely the obstacle — 818 of the cards we track can run it, including cards several years old.

The smallest card that holds it is the Tesla C1080 with 4 GB, running it at Q8_0 and producing around 15.1 tokens per second.

Top of the range is the B200, at roughly 1,387 tokens per second thanks to 8,000 GB/s of bandwidth.

Where it came from

MiniCPM-2.4B was published by Tsinghua University,ModelBest, in China, in June 2024. The organisation is categorised as academia,Industry.

It works in Language, and is recorded as doing language modeling/generation, Code generation, Translation.

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.

Understanding the speeds

The median result is around 39.0 tokens per second; 783 cards produce text faster than most people read it.

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

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.

Training and provenance

Producing it required around 1.6 × 10²² FLOP of arithmetic, which is a statement about the training budget rather than about inference.

Step by step

How to choose a GPU for MiniCPM-2.4B

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

Look at what MiniCPM-2.4B actually needs — around 3.3 GB at Q8_0. No amount of processing power compensates for a card that cannot hold it.
02

Decide how long your conversations run

Longer conversations cost memory on top of what the weights need. Move the slider to your real working length before trusting any row for MiniCPM-2.4B.
03

Set a quality floor

Each card runs the least-compressed copy it can hold — Q8_0 on the smallest card that fits. Setting a floor drops the cards that only manage MiniCPM-2.4B by squeezing it further than you would want.
04

Compare tokens per second, not specifications

Ranking by tokens per second for MiniCPM-2.4B follows memory bandwidth, not core counts, which is why the B200 tops it at 1,387 tok/s.
05

Look at the headroom, not just the fit

The fit column separates cards that just manage MiniCPM-2.4B from those with room to spare. Buy for the second if the context might grow.
06

See what else that card runs

Every card name links to its own page, which runs the same calculation across the whole model catalogue. Worth a look before buying for MiniCPM-2.4B alone — a card is usually bought for more than one model.

Answers

MiniCPM-2.4B — common questions

How much VRAM does MiniCPM-2.4B need?

About 3.3 GB at Q8_0 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 MiniCPM-2.4B on a 8 GB GPU?

Yes. A CMP 170HX 8 GB with 8 GB runs it at Q8_0, using about 3.3 GB and generating roughly 258 tokens per second — a comfortable fit.

Can I run MiniCPM-2.4B on a 12 GB GPU?

Yes. A GeForce RTX 3080 Ti with 12 GB runs it at Q8_0, using about 3.3 GB and generating roughly 158 tokens per second — a comfortable fit.

Can I run MiniCPM-2.4B on a 16 GB GPU?

Yes. A Tesla V100 SXM2 16 GB with 16 GB runs it at Q8_0, using about 3.3 GB and generating roughly 196 tokens per second — a comfortable fit.

Can I run MiniCPM-2.4B on a 24 GB GPU?

Yes. A GeForce RTX 5090 D V2 with 24 GB runs it at Q8_0, using about 3.3 GB and generating roughly 232 tokens per second — a comfortable fit.

Is MiniCPM-2.4B open source?

Its weights are published, so MiniCPM-2.4B 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 MiniCPM-2.4B have?

MiniCPM-2.4B has 2.4B parameters. Table 2. 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 MiniCPM-2.4B?

MiniCPM-2.4B was published by Tsinghua University,ModelBest, based in China, categorised as academia,Industry.

When was MiniCPM-2.4B released?

MiniCPM-2.4B was published in June 2024. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.

What is MiniCPM-2.4B used for?

MiniCPM-2.4B works in Language, and is recorded as handling language modeling/generation, Code generation, Translation. 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 MiniCPM-2.4B?

The weights for MiniCPM-2.4B are published, though we do not hold a repository link for it. This site calculates hardware requirements rather than hosting model files.

How much compute was used to train MiniCPM-2.4B?

Around 1.6 × 10²² 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.

Can I run MiniCPM-2.4B 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 MiniCPM-2.4B is rarely worth using. Every figure here assumes the whole model is on the card.

Would two GPUs run MiniCPM-2.4B faster?

A second card roughly doubles the memory available but not the generation rate. With 818 cards already able to run MiniCPM-2.4B alone, the case for pairing is weak.

Why does the quantisation differ between cards for MiniCPM-2.4B?

Each card is shown running the least-compressed copy it can hold, and MiniCPM-2.4B appears at 1 different compression levels across the cards that fit it. Bigger cards get the more accurate version.

How accurate are these MiniCPM-2.4B speed estimates?

These are estimates with real error bars. The fastest result here, 832–2,220 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 MiniCPM-2.4B?

The smallest card in our catalogue that holds MiniCPM-2.4B is the Tesla C1080, with 4 GB of memory. It runs the model at Q8_0 using about 3.3 GB, and produces roughly 15.1 tokens per second. 818 cards in total can run it.

How fast is MiniCPM-2.4B on a GPU?

It depends on the card. The quickest we calculate is a B200 at about 1,387 tokens per second; the slowest that still runs it manages considerably less. Reading speed is around ten tokens per second, and 783 of the cards that can run MiniCPM-2.4B clear that.

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