ERNIE-4.5-300B-A47B TPS calculator

Open weights Baidu 300B 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

7 cards that can run it

818 cards we hold specifications for

Smallest card that fits

B200

180 GB · IQ4_XS · 154 tok/s

Fastest card

B200

154 tok/s · 180 GB

Which GPUs can run ERNIE-4.5-300B-A47B?

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

7 cards match

Calculating

					Needs	Quantisation	Fit
154 tok/s 92–247 · low confidence	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	153.0 GB	IQ4_XS	Tight
91.2 tok/s 55–146 · low confidence	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	240.3 GB	Q6_K	Tight
75.2 tok/s 45–120 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	170.5 GB	Q4_K_M	Tight
75.2 tok/s 45–120 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	170.5 GB	Q4_K_M	Tight
72.8 tok/s 44–116 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	240.3 GB	Q6_K	Tight
72.8 tok/s 44–116 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	240.3 GB	Q6_K	Tight
65.6 tok/s 39–105 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	205.4 GB	Q5_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: 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: 300B
Training data: tokens

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: 2.8 × 10²⁴ FLOP

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 H800 SXM5
Hardware utilisation: MFU 47.0%

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.

Likely above 10²³ FLOP: Yes
Record confidence: Speculative

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-4.5-300B-A47B

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-4.5-300B-A47B

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

B200

Memory needed

153.0 GB

Fastest

154 tok/s

ERNIE-4.5-300B-A47B reaches a parameter count of 300B. That is beyond what any single graphics card holds. Running it means either splitting it across several cards or renting hardware built for the job, and every card able to hold it alone is a datacentre part. The number that can: 7.

At the low end it is handled by B200, with a memory capacity of 180 GB, running it at a compression of IQ4_XS and producing around 154 tokens per second.

The fastest we calculate for it is B200, generating roughly 154 tokens per second on the strength of a memory bandwidth of 8,000 GB/s.

What this model is

ERNIE-4.5-300B-A47B was published by Baidu, in the country recorded as China, during June 2025. It comes out of an organisation categorised as industry.

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

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 baidu.

What decides the speed

The median result is around 75.2 tokens per second. Exceeding reading speed outright: 7 of them.

Mixture-of-experts routing is why the speeds here look high for the parameter count. Only a fraction is read per token, but the whole thing has to be loaded.

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.

How it was trained

Producing it required arithmetic totalling around 2.8 × 10²⁴ FLOP, on hardware recorded as NVIDIA H800 SXM5. 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 ERNIE-4.5-300B-A47B

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

Start from what it actually needs, which is the requirement of ERNIE-4.5-300B-A47B, needing around 153.0 GB at a compression of IQ4_XS. That figure, not the headline performance of a card, is what decides whether it runs.
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, because at long context a card that handles short questions easily can be dropped by ERNIE-4.5-300B-A47B.
03

Decide how much compression you will accept

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

Sort by speed

The speed ordering is effectively an ordering by memory bandwidth, for ERNIE-4.5-300B-A47B. It will not match a gaming ordering, because generation is bound by memory bandwidth. The card topping the list is B200, at 154 tok/s.
05

Check the fit verdict before buying

A tight fit runs, but leaves nothing spare for a longer conversation, in the case of ERNIE-4.5-300B-A47B. 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

See what else that card runs

Every card name links to its own page, which runs the same calculation across the whole model catalogue. A card is usually bought for more than one model, so it is worth a look before buying for ERNIE-4.5-300B-A47B.

Answers

ERNIE-4.5-300B-A47B — common questions

ERNIE-4.5-300B-A47B— when was it released?

It was published in June 2025.

ERNIE-4.5-300B-A47B— what is it used for?

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

ERNIE-4.5-300B-A47B— where can I download it?

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

ERNIE-4.5-300B-A47B— how much compute was used to train it?

Training consumed around 2.8 × 10²⁴ FLOP, on hardware recorded as NVIDIA H800 SXM5. 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.

ERNIE-4.5-300B-A47B— 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 43.6 GB. Every figure here assumes the whole model is resident on the card.

ERNIE-4.5-300B-A47B— would two GPUs run it faster?

Capacity adds across cards; throughput does not. The number of cards already holding it on their own: 7. So a second card is rarely the answer here.

ERNIE-4.5-300B-A47B— 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.

ERNIE-4.5-300B-A47B— how accurate are these speed estimates?

These are estimates with real error bars, and any of them could reasonably land anywhere in its published range depending on which runtime you use. The fastest result here: 92–247 tok/s on B200. The same model and card vary by thirty to fifty per cent depending on the inference software and its version.

ERNIE-4.5-300B-A47B— what GPU do I need to run it?

The smallest card in our catalogue that holds it is B200, with a memory capacity of 180 GB. It runs the model at a compression of IQ4_XS using about 153.0 GB, and produces roughly 154 tokens per second. The number of cards able to run it in total: 7.

ERNIE-4.5-300B-A47B— how fast is it on a GPU?

It depends on the card. The quickest we calculate is B200, at about 154 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: 7.

ERNIE-4.5-300B-A47B— how much VRAM does it need?

It needs about 153.0 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.

ERNIE-4.5-300B-A47B— 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.

ERNIE-4.5-300B-A47B— how many parameters does it have?

It has a parameter count of 300B. MoE total parameters: 300B active parameters: 47B. 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.

ERNIE-4.5-300B-A47B— who created it?

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

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