InternLM2-20B TPS calculator

Open weights Shanghai AI Lab,SenseTime,Chinese University of Hong Kong (CUHK),Fudan University 20B parameters January 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

293 of 818 cards that can run it

Smallest card that fits

Quadro K6000

12 GB · Q3_K_M · 14.0 tok/s

Fastest card

B200

169 tok/s · 180 GB

Which GPUs can run InternLM2-20B?

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

293 cards match

Calculating

					Needs	Quantisation	Fit
169 tok/s 102–271 · low confidence	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	22.1 GB	Q8_0	Comfortable
169 tok/s 102–271 · low confidence	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	22.1 GB	Q8_0	Comfortable
135 tok/s 81–216 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	22.1 GB	Q8_0	Comfortable
135 tok/s 81–216 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	22.1 GB	Q8_0	Comfortable
108 tok/s 65–173 · low confidence	Radeon Instinct MI300 AMD	128 GB	6,550 GB/s	Jan 2023	22.1 GB	Q8_0	Comfortable
104 tok/s 62–166 · low confidence	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	22.1 GB	Q8_0	Comfortable
104 tok/s 62–166 · low confidence	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	22.1 GB	Q8_0	Comfortable
99.1 tok/s 59–159 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	22.1 GB	Q8_0	Comfortable
88.0 tok/s 53–141 · low confidence	Radeon Instinct MI300A AMD	128 GB	5,325 GB/s	Dec 2023	22.1 GB	Q8_0	Comfortable
88.0 tok/s 53–141 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	22.1 GB	Q8_0	Comfortable
88.0 tok/s 53–141 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	22.1 GB	Q8_0	Comfortable
83.4 tok/s 50–134 · low confidence	H100 NVL 94 GB NVIDIA	94 GB	3,940 GB/s	Mar 2023	22.1 GB	Q8_0	Comfortable
71.2 tok/s 43–114 · low confidence	H100 PCIe 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	22.1 GB	Q8_0	Comfortable
71.2 tok/s 43–114 · low confidence	H100 SXM5 80 GB NVIDIA	80 GB	3,360 GB/s	Oct 2022	22.1 GB	Q8_0	Comfortable
71.2 tok/s 43–114 · low confidence	H100 SXM5 94 GB NVIDIA	94 GB	3,360 GB/s	Mar 2023	22.1 GB	Q8_0	Comfortable
71.2 tok/s 43–114 · low confidence	H100 SXM5 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	22.1 GB	Q8_0	Comfortable
71.2 tok/s 43–114 · low confidence	H800 SXM5 NVIDIA	80 GB	3,360 GB/s	Mar 2023	22.1 GB	Q8_0	Comfortable
55.2 tok/s 33–88 · low confidence	Tesla V100 SXM2 16 GB NVIDIA	16 GB	1,130 GB/s	Nov 2019	12.8 GB	Q4_K_M	Tight
54.2 tok/s 33–87 · low confidence	Radeon Instinct MI250 AMD	128 GB	3,280 GB/s	Nov 2021	22.1 GB	Q8_0	Comfortable
54.2 tok/s 33–87 · low confidence	Radeon Instinct MI250X AMD	128 GB	3,280 GB/s	Nov 2021	22.1 GB	Q8_0	Comfortable
52.1 tok/s 31–83 · low confidence	GeForce RTX 3080 12 GB NVIDIA	12 GB	912 GB/s	Jan 2022	10.5 GB	Q3_K_M	Tight
52.1 tok/s 31–83 · low confidence	GeForce RTX 3080 Ti NVIDIA	12 GB	912 GB/s	May 2021	10.5 GB	Q3_K_M	Tight
46.9 tok/s 28–75 · low confidence	GeForce RTX 5080 NVIDIA	16 GB	960 GB/s	Jan 2025	12.8 GB	Q4_K_M	Tight
45.2 tok/s 27–72 · low confidence	Data Center GPU Max 1550 Intel	128 GB	3,280 GB/s	Jan 2023	22.1 GB	Q8_0	Comfortable
44.2 tok/s 27–71 · low confidence	Data Center GPU Max Subsystem Intel	128 GB	3,210 GB/s	Jan 2023	22.1 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: Shanghai AI Lab,SenseTime,Chinese University of Hong Kong (CUHK),Fudan University
Organisation type: Academia,Industry,Academia,Academia
Country: China, Hong Kong
Published: 12 January 2024
Authors: Zheng Cai, Maosong Cao, Haojiong Chen, Kai Chen, Keyu Chen, Xin Chen, Xun Chen, Zehui Chen, Zhi Chen, Pei Chu, Xiaoyi Dong, Haodong Duan, Qi Fan, Zhaoye Fei, Yang Gao, Jiaye Ge, Chenya Gu, Yuzhe Gu, Tao Gui, Aijia Guo, Qipeng Guo, Conghui He, Yingfan Hu, Ting Huang, Tao Jiang, Penglong Jiao, Zhenjiang Jin, Zhikai Lei, Jiaxing Li, Jingwen Li, Linyang Li, Shuaibin Li, Wei Li, Yining Li, Hongwei Liu,…

What it does

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

Domain: Language
Task: Chat, Language modeling/generation, Question answering

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: 20B
Training data: 2,600,000,000,000 tokens
Epochs: 1
Batch size: 5,000,000

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: 3.1 × 10²³ 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
Hugging Face: internlm

How it is classified

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

Likely above 10²³ FLOP: Yes
Record confidence: Confident

Sources

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

Reference: InternLM2 Technical Report
Last updated: 28 November 2025

The extremes

The ten fastest GPUs for InternLM2-20B

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 InternLM2-20B

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

Quadro K6000

Memory needed

10.5 GB

Fastest

169 tok/s

With 20B parameters, InternLM2-20B lands in the range a serious desktop card can handle once the weights are compressed. 293 of the cards we track can run it.

The smallest card that holds it is the Quadro K6000 with 12 GB, running it at Q3_K_M and producing around 14.0 tokens per second.

Top of the range is the B200, at roughly 169 tokens per second thanks to 8,000 GB/s of bandwidth.

Where it came from

InternLM2-20B was published by Shanghai AI Lab,SenseTime,Chinese University of Hong Kong (CUHK),Fudan University, in China, in January 2024. It comes out of academia,Industry,Academia,Academia.

It works in Language, and is recorded as doing chat, Language modeling/generation, Question answering.

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 internlm organisation on Hugging Face.

Understanding the speeds

Half the cards that hold it manage more than 20.6 tokens per second, and 248 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.

How it was trained

Producing it required around 3.1 × 10²³ FLOP of arithmetic, which is a statement about the training budget rather than about inference.

It was trained on about 2,600,000,000,000 tokens of text.

Step by step

How to choose a GPU for InternLM2-20B

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

Every card here has been checked against InternLM2-20B — around 10.5 GB at Q3_K_M. Capacity is the gate — a card either holds it or it does not.
02

Match the context to your actual use

The conversation occupies memory too, and grows as it goes. Set the slider to the length you expect: at long context InternLM2-20B can slip off a card that handles short questions easily.
03

Decide how much compression you will accept

The quantisation column varies by card, because a bigger card holds a more accurate copy of InternLM2-20B — Q3_K_M on the smallest card that fits. Set a floor to hold the comparison at one level.
04

Sort by speed

Sort by speed to see how cards rank for InternLM2-20B. It will not match a gaming ordering — generation is bound by memory bandwidth, which is why the B200 tops it at 169 tok/s.
05

Look at the headroom, not just the fit

The fit column separates cards that just manage InternLM2-20B 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 InternLM2-20B alone — a card is usually bought for more than one model.

Answers

InternLM2-20B — common questions

Can I run InternLM2-20B on a 16 GB GPU?

Yes. A Tesla V100 SXM2 16 GB with 16 GB runs it at Q4_K_M, using about 12.8 GB and generating roughly 55.2 tokens per second — a tight fit.

Can I run InternLM2-20B on a 24 GB GPU?

Yes. A GeForce RTX 5090 D V2 with 24 GB runs it at Q6_K, using about 17.5 GB and generating roughly 41.2 tokens per second — a comfortable fit.

Is InternLM2-20B open source?

Its weights are published, so InternLM2-20B 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 InternLM2-20B have?

InternLM2-20B has 20B parameters. 20B. 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 InternLM2-20B?

InternLM2-20B was published by Shanghai AI Lab,SenseTime,Chinese University of Hong Kong (CUHK),Fudan University, based in China, categorised as academia,Industry,Academia,Academia.

When was InternLM2-20B released?

InternLM2-20B was published in January 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 InternLM2-20B used for?

InternLM2-20B works in Language, and is recorded as handling chat, Language modeling/generation, Question answering. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.

Where can I download InternLM2-20B?

Its weights are published under the internlm 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 InternLM2-20B?

Around 3.1 × 10²³ 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 InternLM2-20B 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 InternLM2-20B is rarely worth using — the nearest miss we calculate is short by 2.9 GB. Every figure here assumes the whole model is on the card.

Would two GPUs run InternLM2-20B faster?

Capacity adds across cards; throughput does not. Since 293 of the cards we track already hold InternLM2-20B on their own, a second card is rarely the answer here.

Why does the quantisation differ between cards for InternLM2-20B?

A larger card holds a more accurate copy. Across the cards that run InternLM2-20B, 4 compression levels are used; the floor control above pins it to one.

How accurate are these InternLM2-20B speed estimates?

These are estimates with real error bars. The fastest result here, 102–271 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 InternLM2-20B?

The smallest card in our catalogue that holds InternLM2-20B is the Quadro K6000, with 12 GB of memory. It runs the model at Q3_K_M using about 10.5 GB, and produces roughly 14.0 tokens per second. 293 cards in total can run it.

How fast is InternLM2-20B on a GPU?

It depends on the card. The quickest we calculate is a B200 at about 169 tokens per second; the slowest that still runs it manages considerably less. Reading speed is around ten tokens per second, and 248 of the cards that can run InternLM2-20B clear that.

How much VRAM does InternLM2-20B need?

About 10.5 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 InternLM2-20B on a 12 GB GPU?

Yes. A GeForce RTX 3080 Ti with 12 GB runs it at Q3_K_M, using about 10.5 GB and generating roughly 52.1 tokens per second — a tight 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