XuanYuan 2.0 TPS calculator

Open weights Du Xiaoman 176.2B parameters May 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

17 cards that can run it

818 cards we hold specifications for

Smallest card that fits

Radeon Instinct MI250

128 GB · Q4_K_M · 14.2 tok/s

Fastest card

Radeon Instinct MI300

28.4 tok/s · 128 GB

Which GPUs can run XuanYuan 2.0?

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.

17 cards match

Calculating
Needs Quantisation Fit
28.4 tok/s

17–45 · low confidence

Radeon Instinct MI300 AMD 128 GB 6,550 GB/s Jan 2023 107.3 GB Q4_K_M Tight
27.9 tok/s

17–45 · low confidence

B200 NVIDIA 180 GB 8,000 GB/s Jan 2024 148.3 GB Q6_K Tight
27.1 tok/s

16–43 · low confidence

H200 NVL NVIDIA 141 GB 4,890 GB/s Nov 2024 107.3 GB Q4_K_M Tight
27.1 tok/s

16–43 · low confidence

H200 SXM 141 GB NVIDIA 141 GB 4,890 GB/s Nov 2024 107.3 GB Q4_K_M Tight
23.1 tok/s

14–37 · low confidence

Radeon Instinct MI300A AMD 128 GB 5,325 GB/s Dec 2023 107.3 GB Q4_K_M Tight
19.2 tok/s

12–31 · low confidence

B300 NVIDIA 288 GB 8,000 GB/s Sep 2025 189.3 GB Q8_0 Comfortable
15.4 tok/s

9–25 · low confidence

Radeon Instinct MI350X AMD 288 GB 8,190 GB/s Jan 2025 189.3 GB Q8_0 Comfortable
15.4 tok/s

9–25 · low confidence

Radeon Instinct MI355X AMD 288 GB 8,190 GB/s Jan 2025 189.3 GB Q8_0 Comfortable
14.5 tok/s

9–23 · low confidence

Radeon Instinct MI300X AMD 192 GB 5,325 GB/s Dec 2023 148.3 GB Q6_K Tight
14.5 tok/s

9–23 · low confidence

Radeon Instinct MI308X AMD 192 GB 5,325 GB/s Dec 2023 148.3 GB Q6_K Tight
14.2 tok/s

9–23 · low confidence

Radeon Instinct MI250 AMD 128 GB 3,280 GB/s Nov 2021 107.3 GB Q4_K_M Tight
14.2 tok/s

9–23 · low confidence

Radeon Instinct MI250X AMD 128 GB 3,280 GB/s Nov 2021 107.3 GB Q4_K_M Tight
11.8 tok/s

7–19 · low confidence

Data Center GPU Max 1550 Intel 128 GB 3,280 GB/s Jan 2023 107.3 GB Q4_K_M Tight
11.6 tok/s

7–19 · low confidence

Data Center GPU Max Subsystem Intel 128 GB 3,210 GB/s Jan 2023 107.3 GB Q4_K_M Tight
11.3 tok/s

7–18 · low confidence

Radeon Instinct MI325X AMD 256 GB 6,000 GB/s Oct 2024 189.3 GB Q8_0 Comfortable
1.5 tok/s

1–2 · low confidence

GB10 NVIDIA 128 GB 273 GB/s Oct 2025 107.3 GB Q4_K_M Tight
1.5 tok/s

1–2 · low confidence

Jetson T5000 NVIDIA 128 GB 273 GB/s Aug 2025 107.3 GB Q4_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
Du Xiaoman
Organisation type
Industry
Country
China
Published
19 May 2023
Authors
Xuanyu Zhang, Qing Yang, Dongliang Xu

What it does

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

Domain
Language
Task
Language modeling/generation, Chat
Base model
BLOOM-176B

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
176.2B

176.2B

Training data
366,000,000,000 tokens

Table 2

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.

Fine-tuning compute
1.4 × 10²² FLOP

13B tokens for fine-tuning, per table 2 176B * 13B * 6 = 1.37e22

The training run

What it physically took to train: which chips, how many, for how long, and what that drew from the wall.

Training hardware
NVIDIA A100 SXM4 80 GB

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)

How it is classified

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

Record confidence
Confident
Citations
161

Sources

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

Reference
XuanYuan 2.0: A Large Chinese Financial Chat Model with Hundreds of Billions Parameters
Last updated
25 May 2026

The extremes

What the numbers mean

Hardware requirements in practice

Minimum card

Radeon Instinct MI250

Memory needed

107.3 GB

Fastest

28.4 tok/s

XuanYuan 2.0 sits at 176.2B parameters, which puts it above consumer hardware and into the range where a card is bought for this purpose rather than repurposed for it. 17 of the cards we track can hold it.

The entry point is the Radeon Instinct MI250: 128 GB of memory, Q4_K_M compression, roughly 14.2 tokens per second.

A Radeon Instinct MI300 is the fastest we calculate for it: about 28.4 tokens per second, from 6,550 GB/s of memory bandwidth.

About this model

XuanYuan 2.0 was published by Du Xiaoman, in China, in May 2023. It comes out of industry.

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

It is derived from BLOOM-176B rather than trained from scratch, which is the usual way a specialised model is produced.

Because its weights were released, nothing about running it depends on a provider staying available — it is yours once downloaded.

How fast it runs, and why

Half the cards that hold it manage more than 14.5 tokens per second, and 15 exceed reading speed outright.

It is a dense model, so every parameter is read for every token produced. That makes speed track memory bandwidth almost exactly — a card with twice the bandwidth generates roughly twice as fast.

Without the attention layout on record, the memory column is an approximation. It is close enough to choose hardware by, and least reliable at long context.

Training and provenance

The training set ran to roughly 366,000,000,000 tokens.

Step by step

How to choose a GPU for XuanYuan 2.0

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

  1. 01

    Check what it needs before anything else

    The table lists every card that can hold XuanYuan 2.0 — around 107.3 GB at Q4_K_M. That figure, not the card's headline performance, is what decides whether it runs.

  2. 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 XuanYuan 2.0 can slip off a card that handles short questions easily.

  3. 03

    Choose how far you will compress it

    Each card runs the least-compressed copy it can hold — Q4_K_M on the smallest card that fits. Setting a floor drops the cards that only manage XuanYuan 2.0 by squeezing it further than you would want.

  4. 04

    Sort by speed

    The speed ordering for XuanYuan 2.0 is effectively an ordering by memory bandwidth, which is why the Radeon Instinct MI300 tops it at 28.4 tok/s.

  5. 05

    Look at the headroom, not just the fit

    Tight means XuanYuan 2.0 loads and works, with no room to raise the context later. Comfortable means you can. The difference matters more than a few tokens per second.

  6. 06

    Open the card you have settled on

    Each card page repeats this sweep for every model we hold. It answers what else the hardware is good for, beyond XuanYuan 2.0.

Answers

XuanYuan 2.0 — common questions

01

Who created XuanYuan 2.0?

XuanYuan 2.0 was published by Du Xiaoman, based in China, categorised as industry.

02

When was XuanYuan 2.0 released?

XuanYuan 2.0 was published in May 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.

03

What is XuanYuan 2.0 used for?

XuanYuan 2.0 works in Language, and is recorded as handling language modeling/generation, Chat. These are the areas it was designed around; they describe intent rather than a hard boundary.

04

Where can I download XuanYuan 2.0?

The weights for XuanYuan 2.0 are published, though we do not hold a repository link for it. This site calculates hardware requirements rather than hosting model files.

05

Can I run XuanYuan 2.0 if it does not fit in my GPU?

It can be split between the card and system memory, but XuanYuan 2.0 generates painfully slowly that way — the nearest miss we calculate is short by 20.9 GB. Nothing on this page assumes offloading.

06

Would two GPUs run XuanYuan 2.0 faster?

A second card roughly doubles the memory available but not the generation rate. With 17 cards already able to run XuanYuan 2.0 alone, the case for pairing is weak.

07

Why does the quantisation differ between cards for XuanYuan 2.0?

Each card is shown running the least-compressed copy it can hold, and XuanYuan 2.0 appears at 3 different compression levels across the cards that fit it. Bigger cards get the more accurate version.

08

How accurate are these XuanYuan 2.0 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 17–45 tok/s on the Radeon Instinct MI300 rather than a single number.

09

What GPU do I need to run XuanYuan 2.0?

The smallest card in our catalogue that holds XuanYuan 2.0 is the Radeon Instinct MI250, with 128 GB of memory. It runs the model at Q4_K_M using about 107.3 GB, and produces roughly 14.2 tokens per second. 17 cards in total can run it.

10

How fast is XuanYuan 2.0 on a GPU?

It depends on the card. The quickest we calculate is a Radeon Instinct MI300 at about 28.4 tokens per second; the slowest that still runs it manages considerably less. Reading speed is around ten tokens per second, and 15 of the cards that can run XuanYuan 2.0 clear that.

11

How much VRAM does XuanYuan 2.0 need?

About 107.3 GB at Q4_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.

12

Is XuanYuan 2.0 open source?

Its weights are published, so XuanYuan 2.0 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.

13

How many parameters does XuanYuan 2.0 have?

XuanYuan 2.0 has 176.2B parameters. 176.2B. 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.

Source

Original publication

Record last updated 25 May 2026

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.