Yuan 2.0 TPS calculator

Open weights Inspur 102.6B parameters November 2023

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

43 cards that can run it

818 cards we hold specifications for

Smallest card that fits

Radeon Instinct MI200

64 GB · IQ4_XS · 13.0 tok/s

Fastest card

B200

33.0 tok/s · 180 GB

Which GPUs can run Yuan 2.0?

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

43 cards match

Calculating

					Needs	Quantisation	Fit
33.0 tok/s 20–53 · low confidence	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	110.5 GB	Q8_0	Comfortable
33.0 tok/s 20–53 · low confidence	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	110.5 GB	Q8_0	Comfortable
32.0 tok/s 19–51 · low confidence	H100 SXM5 80 GB NVIDIA	80 GB	3,360 GB/s	Oct 2022	62.8 GB	Q4_K_M	Tight
32.0 tok/s 19–51 · low confidence	H800 SXM5 NVIDIA	80 GB	3,360 GB/s	Mar 2023	62.8 GB	Q4_K_M	Tight
29.1 tok/s 17–46 · low confidence	H100 NVL 94 GB NVIDIA	94 GB	3,940 GB/s	Mar 2023	74.7 GB	Q5_K_M	Tight
26.4 tok/s 16–42 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	110.5 GB	Q8_0	Comfortable
26.4 tok/s 16–42 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	110.5 GB	Q8_0	Comfortable
24.8 tok/s 15–40 · low confidence	H100 PCIe 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	74.7 GB	Q5_K_M	Tight
24.8 tok/s 15–40 · low confidence	H100 SXM5 94 GB NVIDIA	94 GB	3,360 GB/s	Mar 2023	74.7 GB	Q5_K_M	Tight
24.8 tok/s 15–40 · low confidence	H100 SXM5 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	74.7 GB	Q5_K_M	Tight
21.1 tok/s 13–34 · low confidence	Radeon Instinct MI300 AMD	128 GB	6,550 GB/s	Jan 2023	110.5 GB	Q8_0	Tight
20.5 tok/s 12–33 · low confidence	H100 SXM5 64 GB NVIDIA	64 GB	2,020 GB/s	Mar 2023	56.8 GB	IQ4_XS	Tight
20.2 tok/s 12–32 · low confidence	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	110.5 GB	Q8_0	Tight
20.2 tok/s 12–32 · low confidence	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	110.5 GB	Q8_0	Tight
19.4 tok/s 12–31 · low confidence	A100 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Nov 2020	62.8 GB	Q4_K_M	Tight
19.4 tok/s 12–31 · low confidence	A100X NVIDIA	80 GB	2,040 GB/s	Jun 2021	62.8 GB	Q4_K_M	Tight
19.4 tok/s 12–31 · low confidence	A800 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Aug 2022	62.8 GB	Q4_K_M	Tight
19.4 tok/s 12–31 · low confidence	H100 CNX NVIDIA	80 GB	2,040 GB/s	Mar 2023	62.8 GB	Q4_K_M	Tight
19.4 tok/s 12–31 · low confidence	H100 PCIe 80 GB NVIDIA	80 GB	2,040 GB/s	Oct 2022	62.8 GB	Q4_K_M	Tight
19.4 tok/s 12–31 · low confidence	H800 PCIe 80 GB NVIDIA	80 GB	2,040 GB/s	Mar 2023	62.8 GB	Q4_K_M	Tight
19.3 tok/s 12–31 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	110.5 GB	Q8_0	Comfortable
18.5 tok/s 11–30 · low confidence	A100 PCIe 80 GB NVIDIA	80 GB	1,940 GB/s	Jun 2021	62.8 GB	Q4_K_M	Tight
18.5 tok/s 11–30 · low confidence	A800 PCIe 80 GB NVIDIA	80 GB	1,940 GB/s	Nov 2022	62.8 GB	Q4_K_M	Tight
17.2 tok/s 10–27 · low confidence	Radeon Instinct MI300A AMD	128 GB	5,325 GB/s	Dec 2023	110.5 GB	Q8_0	Tight
17.2 tok/s 10–27 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	110.5 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: Inspur
Organisation type: Industry
Country: China
Published: 27 November 2023
Authors: Shaohua Wu, Xudong Zhao, Shenling Wang, Jiangang Luo, Lingjun Li, Xi Chen, Bing Zhao, Wei Wang, Tong Yu, Rongguo Zhang, Jiahua Zhang, Chao Wang

What it does

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

Domain: Language
Task: Language modeling/generation, Translation, Code 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: 102.6B
Training data: tokens
Epochs: 1

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: 1.8 × 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: Open source
Hugging Face: IEITYuan

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: YUAN 2.0: A Large Language Model with Localized Filtering-based Attention
Last updated: 28 November 2025

The extremes

The ten fastest GPUs that run Yuan 2.0

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 Yuan 2.0

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

Radeon Instinct MI200

Memory needed

56.8 GB

Fastest

33.0 tok/s

Yuan 2.0 reaches a parameter count of 102.6B. That puts it above consumer hardware, into the range where a card is bought for this purpose rather than repurposed for it. The number of cards we track that can hold it: 43.

The smallest card that holds it is Radeon Instinct MI200, with a memory capacity of 64 GB, running it at a compression of IQ4_XS and producing around 13.0 tokens per second.

The fastest we calculate for it is B200, generating roughly 33.0 tokens per second on the strength of a memory bandwidth of 8,000 GB/s.

About this model

Yuan 2.0 was published by Inspur, in the country recorded as China, during November 2023. The publishing organisation is categorised as industry.

It works in the domain of Language, and is recorded as performing the task of language modeling/generation, Translation, Code generation.

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. On Hugging Face it is published under the organisation IEITYuan.

How fast it runs, and why

Half the cards that hold it manage more than 18.5 tokens per second. Clearing the ten tokens per second that roughly matches reading speed: 37 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.

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

The training run consumed about 1.8 × 10²³ 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 Yuan 2.0

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

01

Read the memory figure first

The table lists every card able to hold Yuan 2.0, needing around 56.8 GB at a compression of IQ4_XS. 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 Yuan 2.0.
03

Set a quality floor

The quantisation column varies by card, because a bigger card holds a more accurate copy, reaching a compression of IQ4_XS 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

Compare tokens per second, not specifications

Sort by speed to see how cards rank for Yuan 2.0. It will not match a gaming ordering, because generation is bound by memory bandwidth. The card topping the list is B200, at 33.0 tok/s.
05

Read the fit column last

The fit column separates cards that just manage it from those with room to spare, in the case of Yuan 2.0. 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 Yuan 2.0.

Answers

Yuan 2.0 — common questions

Yuan 2.0— can I run it if it does not fit in my GPU?

Only by offloading, which is usually a false economy: the part held in system memory drags the whole thing down. The nearest miss we calculate falls short by 19.6 GB. Every figure here assumes the whole model is resident on the card.

Yuan 2.0— would two GPUs run it faster?

A second card roughly doubles the memory available but not the generation rate. The number already able to run it alone: 43. So a second card is rarely the answer here.

Yuan 2.0— why does the quantisation differ between cards?

Each card is shown running the least-compressed copy it can hold. The number of distinct compression levels across the cards that fit it: 4. Bigger cards get the more accurate version, and the quality floor above pins the comparison to one level.

Yuan 2.0— how accurate are these speed estimates?

They are calculated from specifications rather than measured, and each carries a range. One example: 20–53 tok/s on B200. The same model and card vary by thirty to fifty per cent depending on the inference software and its version.

Yuan 2.0— what GPU do I need to run it?

The smallest card in our catalogue that holds it is Radeon Instinct MI200, with a memory capacity of 64 GB. It runs the model at a compression of IQ4_XS using about 56.8 GB, and produces roughly 13.0 tokens per second. The number of cards able to run it in total: 43.

Yuan 2.0— how fast is it on a GPU?

It depends on the card. The quickest we calculate is B200, at about 33.0 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: 37.

Yuan 2.0— how much VRAM does it need?

It needs about 56.8 GB at a compression of IQ4_XS, 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.

Yuan 2.0— 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.

Yuan 2.0— how many parameters does it have?

It has a parameter count of 102.6B. 102.6 billion. 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.

Yuan 2.0— who created it?

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

Yuan 2.0— when was it released?

It was published in November 2023. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.

Yuan 2.0— what is it used for?

It works in the domain of Language, and is recorded as handling the task of language modeling/generation, Translation, Code generation. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.

Yuan 2.0— where can I download it?

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

Yuan 2.0— how much compute was used to train it?

Training consumed around 1.8 × 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.

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