ERNIE-Doc Base (151M, WT103) TPS calculator

Open weights Baidu 151M parameters December 2020

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 · 244 tok/s

Fastest card

B200

22,439 tok/s · 180 GB

Which GPUs can run ERNIE-Doc Base (151M, WT103)?

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
22,439 tok/s 13,463–35,902 · low confidence	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	0.9 GB	Q8_0	Comfortable
22,439 tok/s 13,463–35,902 · low confidence	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	0.9 GB	Q8_0	Comfortable
17,918 tok/s 10,751–28,669 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	0.9 GB	Q8_0	Comfortable
17,918 tok/s 10,751–28,669 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	0.9 GB	Q8_0	Comfortable
14,330 tok/s 8,598–22,928 · low confidence	Radeon Instinct MI300 AMD	128 GB	6,550 GB/s	Jan 2023	0.9 GB	Q8_0	Comfortable
13,716 tok/s 8,229–21,945 · low confidence	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	0.9 GB	Q8_0	Comfortable
13,716 tok/s 8,229–21,945 · low confidence	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	0.9 GB	Q8_0	Comfortable
13,127 tok/s 7,876–21,003 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	0.9 GB	Q8_0	Comfortable
11,650 tok/s 6,990–18,640 · low confidence	Radeon Instinct MI300A AMD	128 GB	5,325 GB/s	Dec 2023	0.9 GB	Q8_0	Comfortable
11,650 tok/s 6,990–18,640 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	0.9 GB	Q8_0	Comfortable
11,650 tok/s 6,990–18,640 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	0.9 GB	Q8_0	Comfortable
11,051 tok/s 6,631–17,682 · low confidence	H100 NVL 94 GB NVIDIA	94 GB	3,940 GB/s	Mar 2023	0.9 GB	Q8_0	Comfortable
9,424 tok/s 5,655–15,079 · low confidence	H100 PCIe 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	0.9 GB	Q8_0	Comfortable
9,424 tok/s 5,655–15,079 · low confidence	H100 SXM5 80 GB NVIDIA	80 GB	3,360 GB/s	Oct 2022	0.9 GB	Q8_0	Comfortable
9,424 tok/s 5,655–15,079 · low confidence	H100 SXM5 94 GB NVIDIA	94 GB	3,360 GB/s	Mar 2023	0.9 GB	Q8_0	Comfortable
9,424 tok/s 5,655–15,079 · low confidence	H100 SXM5 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	0.9 GB	Q8_0	Comfortable
9,424 tok/s 5,655–15,079 · low confidence	H800 SXM5 NVIDIA	80 GB	3,360 GB/s	Mar 2023	0.9 GB	Q8_0	Comfortable
7,176 tok/s 4,306–11,481 · low confidence	Radeon Instinct MI250 AMD	128 GB	3,280 GB/s	Nov 2021	0.9 GB	Q8_0	Comfortable
7,176 tok/s 4,306–11,481 · low confidence	Radeon Instinct MI250X AMD	128 GB	3,280 GB/s	Nov 2021	0.9 GB	Q8_0	Comfortable
5,980 tok/s 3,588–9,568 · low confidence	Data Center GPU Max 1550 Intel	128 GB	3,280 GB/s	Jan 2023	0.9 GB	Q8_0	Comfortable
5,852 tok/s 3,511–9,364 · low confidence	Data Center GPU Max Subsystem Intel	128 GB	3,210 GB/s	Jan 2023	0.9 GB	Q8_0	Comfortable
5,722 tok/s 3,433–9,155 · low confidence	A100 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Nov 2020	0.9 GB	Q8_0	Comfortable
5,722 tok/s 3,433–9,155 · low confidence	A100X NVIDIA	80 GB	2,040 GB/s	Jun 2021	0.9 GB	Q8_0	Comfortable
5,722 tok/s 3,433–9,155 · low confidence	A800 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Aug 2022	0.9 GB	Q8_0	Comfortable
5,722 tok/s 3,433–9,155 · low confidence	H100 CNX NVIDIA	80 GB	2,040 GB/s	Mar 2023	0.9 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: 31 December 2020
Authors: Siyu Ding, Junyuan Shang, Shuohuan Wang, Yu Sun, Hao Tian, Hua Wu, Haifeng Wang

What it does

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

Domain: Language
Task: Language modeling, Language modeling/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: 151M
Training data: 103,000,000 tokens
Epochs: 18.4

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: 1.7 × 10¹⁸ 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 (unrestricted)
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
Citations: 64
Benchmark data: ERNIE-Doc (151M)

Sources

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

Reference: ERNIE-Doc: A Retrospective Long-Document Modeling Transformer
Last updated: 25 May 2026

The extremes

The ten fastest GPUs that run ERNIE-Doc Base (151M, WT103)

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-Doc Base (151M, WT103)

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

The hardware side

Minimum card

Tesla C1080

Memory needed

0.9 GB

Fastest

22,439 tok/s

ERNIE-Doc Base (151M, WT103) is small enough at 151M parameters that hardware is rarely the obstacle — 818 of the cards we track can run it, including cards several years old.

At the low end, a Tesla C1080 handles it — 4 GB, at Q8_0, for about 244 tokens per second.

A B200 is the fastest we calculate for it: about 22,439 tokens per second, from 8,000 GB/s of memory bandwidth.

Where it came from

ERNIE-Doc Base (151M, WT103) was published by Baidu, in China, in December 2020. It comes out of industry.

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

Published weights mean the model runs on your machine rather than someone else's, which is what makes the hardware question below answerable at all.

Understanding the speeds

Across every card that can run it, the middle of the range is about 630.1 tokens per second, and 818 of them clear the ten tokens per second that roughly matches reading speed.

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.

What went into building it

The training run consumed about 1.7 × 10¹⁸ FLOP. That figure describes the cost of creating it and has no bearing on how quickly it generates text.

It was trained on about 103,000,000 tokens of text.

Step by step

How to choose a GPU for ERNIE-Doc Base (151M, WT103)

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

01

Start from the memory column

Every card here has been checked against ERNIE-Doc Base (151M, WT103) — around 0.9 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

Set the context to what you will actually use. The cache grows with the conversation, and it is the usual reason ERNIE-Doc Base (151M, WT103) stops fitting a card that seemed fine.
03

Decide how much compression you will accept

The quantisation column varies by card, because a bigger card holds a more accurate copy of ERNIE-Doc Base (151M, WT103) — Q8_0 on the smallest card that fits. Set a floor to hold the comparison at one level.
04

Rank by throughput rather than spec sheet

The speed ordering for ERNIE-Doc Base (151M, WT103) is effectively an ordering by memory bandwidth, which is why the B200 tops it at 22,439 tok/s.
05

Look at the headroom, not just the fit

A tight fit runs ERNIE-Doc Base (151M, WT103) but leaves nothing spare for a longer conversation; comfortable has headroom. If you expect to grow the context, buy for comfortable.
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 ERNIE-Doc Base (151M, WT103) is settled.

Answers

ERNIE-Doc Base (151M, WT103) — common questions

How fast is ERNIE-Doc Base (151M, WT103) on a GPU?

It depends on the card. The quickest we calculate is a B200 at about 22,439 tokens per second; the slowest that still runs it manages considerably less. Reading speed is around ten tokens per second, and 818 of the cards that can run ERNIE-Doc Base (151M, WT103) clear that.

How much VRAM does ERNIE-Doc Base (151M, WT103) need?

About 0.9 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-Doc Base (151M, WT103) on a 8 GB GPU?

Yes. A CMP 170HX 8 GB with 8 GB runs it at Q8_0, using about 0.9 GB and generating roughly 4,179 tokens per second — a comfortable fit.

Can I run ERNIE-Doc Base (151M, WT103) on a 12 GB GPU?

Yes. A GeForce RTX 3080 Ti with 12 GB runs it at Q8_0, using about 0.9 GB and generating roughly 2,559 tokens per second — a comfortable fit.

Can I run ERNIE-Doc Base (151M, WT103) on a 16 GB GPU?

Yes. A Tesla V100 SXM2 16 GB with 16 GB runs it at Q8_0, using about 0.9 GB and generating roughly 3,169 tokens per second — a comfortable fit.

Can I run ERNIE-Doc Base (151M, WT103) on a 24 GB GPU?

Yes. A GeForce RTX 5090 D V2 with 24 GB runs it at Q8_0, using about 0.9 GB and generating roughly 3,758 tokens per second — a comfortable fit.

Is ERNIE-Doc Base (151M, WT103) open source?

Its weights are published, so ERNIE-Doc Base (151M, WT103) 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-Doc Base (151M, WT103) have?

ERNIE-Doc Base (151M, WT103) has 151M parameters. 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-Doc Base (151M, WT103)?

ERNIE-Doc Base (151M, WT103) was published by Baidu, based in China, categorised as industry.

When was ERNIE-Doc Base (151M, WT103) released?

ERNIE-Doc Base (151M, WT103) was published in December 2020. 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 ERNIE-Doc Base (151M, WT103) used for?

ERNIE-Doc Base (151M, WT103) works in Language, and is recorded as handling language modeling, Language modeling/generation. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.

Where can I download ERNIE-Doc Base (151M, WT103)?

The weights for ERNIE-Doc Base (151M, WT103) 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 ERNIE-Doc Base (151M, WT103)?

Around 1.7 × 10¹⁸ 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 ERNIE-Doc Base (151M, WT103) if it does not fit in my GPU?

Only by offloading, which is usually a false economy: the part in system memory drags the whole thing down. Our figures for ERNIE-Doc Base (151M, WT103) assume it is fully resident.

Would two GPUs run ERNIE-Doc Base (151M, WT103) faster?

Two cards buy memory rather than speed. That matters for ERNIE-Doc Base (151M, WT103) only if one card cannot hold it — 818 can, so a second adds little.

Why does the quantisation differ between cards for ERNIE-Doc Base (151M, WT103)?

A larger card holds a more accurate copy. Across the cards that run ERNIE-Doc Base (151M, WT103), 1 compression levels are used; the floor control above pins it to one.

How accurate are these ERNIE-Doc Base (151M, WT103) speed estimates?

These are estimates with real error bars. The fastest result here, 13,463–35,902 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 ERNIE-Doc Base (151M, WT103)?

The smallest card in our catalogue that holds ERNIE-Doc Base (151M, WT103) is the Tesla C1080, with 4 GB of memory. It runs the model at Q8_0 using about 0.9 GB, and produces roughly 244 tokens per second. 818 cards in total can run it.

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.

All AI models