ERNIE-4.5-0.3B TPS calculator

Open weights Baidu 360M 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

818 cards that can run it

818 cards we hold specifications for

Smallest card that fits

Tesla C1080

4 GB · Q8_0 · 102 tok/s

Fastest card

B200

9,412 tok/s · 180 GB

Which GPUs can run ERNIE-4.5-0.3B?

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
9,412 tok/s 5,647–15,059 · low confidence	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	1.1 GB	Q8_0	Comfortable
9,412 tok/s 5,647–15,059 · low confidence	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	1.1 GB	Q8_0	Comfortable
7,516 tok/s 4,509–12,025 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	1.1 GB	Q8_0	Comfortable
7,516 tok/s 4,509–12,025 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	1.1 GB	Q8_0	Comfortable
6,011 tok/s 3,606–9,617 · low confidence	Radeon Instinct MI300 AMD	128 GB	6,550 GB/s	Jan 2023	1.1 GB	Q8_0	Comfortable
5,753 tok/s 3,452–9,205 · low confidence	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	1.1 GB	Q8_0	Comfortable
5,753 tok/s 3,452–9,205 · low confidence	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	1.1 GB	Q8_0	Comfortable
5,506 tok/s 3,304–8,809 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	1.1 GB	Q8_0	Comfortable
4,886 tok/s 2,932–7,818 · low confidence	Radeon Instinct MI300A AMD	128 GB	5,325 GB/s	Dec 2023	1.1 GB	Q8_0	Comfortable
4,886 tok/s 2,932–7,818 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	1.1 GB	Q8_0	Comfortable
4,886 tok/s 2,932–7,818 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	1.1 GB	Q8_0	Comfortable
4,635 tok/s 2,781–7,416 · low confidence	H100 NVL 94 GB NVIDIA	94 GB	3,940 GB/s	Mar 2023	1.1 GB	Q8_0	Comfortable
3,953 tok/s 2,372–6,325 · low confidence	H100 PCIe 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	1.1 GB	Q8_0	Comfortable
3,953 tok/s 2,372–6,325 · low confidence	H100 SXM5 80 GB NVIDIA	80 GB	3,360 GB/s	Oct 2022	1.1 GB	Q8_0	Comfortable
3,953 tok/s 2,372–6,325 · low confidence	H100 SXM5 94 GB NVIDIA	94 GB	3,360 GB/s	Mar 2023	1.1 GB	Q8_0	Comfortable
3,953 tok/s 2,372–6,325 · low confidence	H100 SXM5 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	1.1 GB	Q8_0	Comfortable
3,953 tok/s 2,372–6,325 · low confidence	H800 SXM5 NVIDIA	80 GB	3,360 GB/s	Mar 2023	1.1 GB	Q8_0	Comfortable
3,010 tok/s 1,806–4,816 · low confidence	Radeon Instinct MI250 AMD	128 GB	3,280 GB/s	Nov 2021	1.1 GB	Q8_0	Comfortable
3,010 tok/s 1,806–4,816 · low confidence	Radeon Instinct MI250X AMD	128 GB	3,280 GB/s	Nov 2021	1.1 GB	Q8_0	Comfortable
2,508 tok/s 1,505–4,013 · low confidence	Data Center GPU Max 1550 Intel	128 GB	3,280 GB/s	Jan 2023	1.1 GB	Q8_0	Comfortable
2,455 tok/s 1,473–3,928 · low confidence	Data Center GPU Max Subsystem Intel	128 GB	3,210 GB/s	Jan 2023	1.1 GB	Q8_0	Comfortable
2,400 tok/s 1,440–3,840 · low confidence	A100 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Nov 2020	1.1 GB	Q8_0	Comfortable
2,400 tok/s 1,440–3,840 · low confidence	A100X NVIDIA	80 GB	2,040 GB/s	Jun 2021	1.1 GB	Q8_0	Comfortable
2,400 tok/s 1,440–3,840 · low confidence	A800 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Aug 2022	1.1 GB	Q8_0	Comfortable
2,400 tok/s 1,440–3,840 · low confidence	H100 CNX NVIDIA	80 GB	2,040 GB/s	Mar 2023	1.1 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: Baidu
Organisation type: Industry
Country: China
Published: 29 June 2025

What it does

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

Domain: Language
Task: Language modeling/generation, Quantitative reasoning, Code generation, Translation, Question answering
Numerical format: FP8

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: 360M
Training data: tokens
Batch size: 8,000,000

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: baidu

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: ERNIE 4.5 Technical Report
Last updated: 28 November 2025

The extremes

The ten fastest GPUs that run ERNIE-4.5-0.3B

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 ERNIE-4.5-0.3B

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

1.1 GB

Fastest

9,412 tok/s

ERNIE-4.5-0.3B is small enough at 360M 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 102 tokens per second.

The quickest result comes from a B200 at around 9,412 tokens per second — its 8,000 GB/s of bandwidth is what buys that.

What this model is

ERNIE-4.5-0.3B was published by Baidu, in China, in June 2025. It comes out of industry.

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

Because its weights were released, nothing about running it depends on a provider staying available — it is yours once downloaded. It is published under the baidu organisation on Hugging Face.

What decides the speed

Half the cards that hold it manage more than 264.3 tokens per second, and 817 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.

Memory here is estimated from size rather than computed from the architecture, which is not recorded for this model — the numbers are indicative rather than exact.

Step by step

How to choose a GPU for ERNIE-4.5-0.3B

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 ERNIE-4.5-0.3B — around 1.1 GB at Q8_0. Capacity is the gate — a card either holds it or it does not.
02

Set the context length you will work at

The conversation occupies memory too, and grows as it goes. Set the slider to the length you expect: at long context ERNIE-4.5-0.3B can slip off a card that handles short questions easily.
03

Set a quality floor

Compression is what makes ERNIE-4.5-0.3B fit smaller cards, at some cost in accuracy — Q8_0 on the smallest card that fits. A minimum quality removes the ones that go too far.
04

Compare tokens per second, not specifications

Sort by speed to see how cards rank for ERNIE-4.5-0.3B. It will not match a gaming ordering — generation is bound by memory bandwidth, which is why the B200 tops it at 9,412 tok/s.
05

Look at the headroom, not just the fit

A tight fit runs ERNIE-4.5-0.3B but leaves nothing spare for a longer conversation; comfortable has headroom. If you expect to grow the context, buy for comfortable.
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 ERNIE-4.5-0.3B alone — a card is usually bought for more than one model.

Answers

ERNIE-4.5-0.3B — common questions

Can I run ERNIE-4.5-0.3B on a 12 GB GPU?

Yes. A GeForce RTX 3080 Ti with 12 GB runs it at Q8_0, using about 1.1 GB and generating roughly 1,073 tokens per second — a comfortable fit.

Can I run ERNIE-4.5-0.3B on a 16 GB GPU?

Yes. A Tesla V100 SXM2 16 GB with 16 GB runs it at Q8_0, using about 1.1 GB and generating roughly 1,329 tokens per second — a comfortable fit.

Can I run ERNIE-4.5-0.3B on a 24 GB GPU?

Yes. A GeForce RTX 5090 D V2 with 24 GB runs it at Q8_0, using about 1.1 GB and generating roughly 1,576 tokens per second — a comfortable fit.

Is ERNIE-4.5-0.3B open source?

Its weights are published, so ERNIE-4.5-0.3B 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 ERNIE-4.5-0.3B have?

ERNIE-4.5-0.3B has 360M parameters. 0,36B dense. 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 ERNIE-4.5-0.3B?

ERNIE-4.5-0.3B was published by Baidu, based in China, categorised as industry.

When was ERNIE-4.5-0.3B released?

ERNIE-4.5-0.3B was published in June 2025.

What is ERNIE-4.5-0.3B used for?

ERNIE-4.5-0.3B works in Language, and is recorded as handling language modeling/generation, Quantitative reasoning, Code generation, Translation, Question answering. These are the areas it was designed around; they describe intent rather than a hard boundary.

Where can I download ERNIE-4.5-0.3B?

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

Can I run ERNIE-4.5-0.3B 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 ERNIE-4.5-0.3B is rarely worth using. Every figure here assumes the whole model is on the card.

Would two GPUs run ERNIE-4.5-0.3B faster?

Capacity adds across cards; throughput does not. Since 818 of the cards we track already hold ERNIE-4.5-0.3B on their own, a second card is rarely the answer here.

Why does the quantisation differ between cards for ERNIE-4.5-0.3B?

Each card is shown running the least-compressed copy it can hold, and ERNIE-4.5-0.3B appears at 1 different compression levels across the cards that fit it. Bigger cards get the more accurate version.

How accurate are these ERNIE-4.5-0.3B 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 5,647–15,059 tok/s on the B200 rather than a single number.

What GPU do I need to run ERNIE-4.5-0.3B?

The smallest card in our catalogue that holds ERNIE-4.5-0.3B is the Tesla C1080, with 4 GB of memory. It runs the model at Q8_0 using about 1.1 GB, and produces roughly 102 tokens per second. 818 cards in total can run it.

How fast is ERNIE-4.5-0.3B on a GPU?

It depends on the card. The quickest we calculate is a B200 at about 9,412 tokens per second; the slowest that still runs it manages considerably less. Reading speed is around ten tokens per second, and 817 of the cards that can run ERNIE-4.5-0.3B clear that.

How much VRAM does ERNIE-4.5-0.3B need?

About 1.1 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 ERNIE-4.5-0.3B on a 8 GB GPU?

Yes. A CMP 170HX 8 GB with 8 GB runs it at Q8_0, using about 1.1 GB and generating roughly 1,753 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