OpenELM-450M TPS calculator

Open weights Apple 450M parameters May 2024

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 · 81.9 tok/s

Fastest card

B200

7,529 tok/s · 180 GB

Which GPUs can run OpenELM-450M?

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
7,529 tok/s 4,518–12,047 · low confidence	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	1.2 GB	Q8_0	Comfortable
7,529 tok/s 4,518–12,047 · low confidence	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	1.2 GB	Q8_0	Comfortable
6,012 tok/s 3,607–9,620 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	1.2 GB	Q8_0	Comfortable
6,012 tok/s 3,607–9,620 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	1.2 GB	Q8_0	Comfortable
4,808 tok/s 2,885–7,694 · low confidence	Radeon Instinct MI300 AMD	128 GB	6,550 GB/s	Jan 2023	1.2 GB	Q8_0	Comfortable
4,602 tok/s 2,761–7,364 · low confidence	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	1.2 GB	Q8_0	Comfortable
4,602 tok/s 2,761–7,364 · low confidence	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	1.2 GB	Q8_0	Comfortable
4,405 tok/s 2,643–7,048 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	1.2 GB	Q8_0	Comfortable
3,909 tok/s 2,346–6,255 · low confidence	Radeon Instinct MI300A AMD	128 GB	5,325 GB/s	Dec 2023	1.2 GB	Q8_0	Comfortable
3,909 tok/s 2,346–6,255 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	1.2 GB	Q8_0	Comfortable
3,909 tok/s 2,346–6,255 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	1.2 GB	Q8_0	Comfortable
3,708 tok/s 2,225–5,933 · low confidence	H100 NVL 94 GB NVIDIA	94 GB	3,940 GB/s	Mar 2023	1.2 GB	Q8_0	Comfortable
3,162 tok/s 1,897–5,060 · low confidence	H100 PCIe 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	1.2 GB	Q8_0	Comfortable
3,162 tok/s 1,897–5,060 · low confidence	H100 SXM5 80 GB NVIDIA	80 GB	3,360 GB/s	Oct 2022	1.2 GB	Q8_0	Comfortable
3,162 tok/s 1,897–5,060 · low confidence	H100 SXM5 94 GB NVIDIA	94 GB	3,360 GB/s	Mar 2023	1.2 GB	Q8_0	Comfortable
3,162 tok/s 1,897–5,060 · low confidence	H100 SXM5 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	1.2 GB	Q8_0	Comfortable
3,162 tok/s 1,897–5,060 · low confidence	H800 SXM5 NVIDIA	80 GB	3,360 GB/s	Mar 2023	1.2 GB	Q8_0	Comfortable
2,408 tok/s 1,445–3,853 · low confidence	Radeon Instinct MI250 AMD	128 GB	3,280 GB/s	Nov 2021	1.2 GB	Q8_0	Comfortable
2,408 tok/s 1,445–3,853 · low confidence	Radeon Instinct MI250X AMD	128 GB	3,280 GB/s	Nov 2021	1.2 GB	Q8_0	Comfortable
2,007 tok/s 1,204–3,211 · low confidence	Data Center GPU Max 1550 Intel	128 GB	3,280 GB/s	Jan 2023	1.2 GB	Q8_0	Comfortable
1,964 tok/s 1,178–3,142 · low confidence	Data Center GPU Max Subsystem Intel	128 GB	3,210 GB/s	Jan 2023	1.2 GB	Q8_0	Comfortable
1,920 tok/s 1,152–3,072 · low confidence	A100 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Nov 2020	1.2 GB	Q8_0	Comfortable
1,920 tok/s 1,152–3,072 · low confidence	A100X NVIDIA	80 GB	2,040 GB/s	Jun 2021	1.2 GB	Q8_0	Comfortable
1,920 tok/s 1,152–3,072 · low confidence	A800 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Aug 2022	1.2 GB	Q8_0	Comfortable
1,920 tok/s 1,152–3,072 · low confidence	H100 CNX NVIDIA	80 GB	2,040 GB/s	Mar 2023	1.2 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: Apple
Organisation type: Industry
Country: United States of America
Published: 2 May 2024
Authors: Sachin Mehta, Mohammad Hossein Sekhavat, Qingqing Cao, Maxwell Horton, Yanzi Jin, Chenfan Sun, Iman Mirzadeh, Mahyar Najibi, Dmitry Belenko, Peter Zatloukal, Mohammad Rastegari

What it does

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

Domain: Language
Task: Language modeling/generation, Code generation, Question answering

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: 450M
Training data: tokens
Epochs: 1
Batch size: 4,000,000

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: 6.3 × 10²¹ FLOP
How it was established: Operation counting,Hardware

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 H100 SXM5 80GB
Chips used: 128
Wall-clock time: 72 hours
Power draw: 177.1 kW

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 (non-commercial)
Hugging Face: apple

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: OpenELM: An Efficient Language Model Family with Open Training and Inference Framework
Last updated: 28 November 2025

The extremes

The ten fastest GPUs that run OpenELM-450M

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 OpenELM-450M

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

1.2 GB

Fastest

7,529 tok/s

OpenELM-450M is small enough at 450M 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 81.9 tokens per second.

The quickest result comes from a B200 at around 7,529 tokens per second — its 8,000 GB/s of bandwidth is what buys that.

Background

OpenELM-450M was published by Apple, in United States of America, in May 2024. industry is the category the publisher falls under.

It works in Language, and is recorded as doing language modeling/generation, Code generation, 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. It is published under the apple organisation on Hugging Face.

Reading the throughput figures

Half the cards that hold it manage more than 211.4 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.

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.

How it was trained

Producing it required around 6.3 × 10²¹ FLOP of arithmetic, on NVIDIA H100 SXM5 80GB, which is a statement about the training budget rather than about inference.

Step by step

How to choose a GPU for OpenELM-450M

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

Every card here has been checked against OpenELM-450M — around 1.2 GB at Q8_0. Capacity is the gate — a card either holds it or it does not.
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 OpenELM-450M can slip off a card that handles short questions easily.
03

Decide how much compression you will accept

Each card runs the least-compressed copy it can hold — Q8_0 on the smallest card that fits. Setting a floor drops the cards that only manage OpenELM-450M by squeezing it further than you would want.
04

Sort by speed

Sort by speed to see how cards rank for OpenELM-450M. It will not match a gaming ordering — generation is bound by memory bandwidth, which is why the B200 tops it at 7,529 tok/s.
05

Check the fit verdict before buying

A tight fit runs OpenELM-450M but leaves nothing spare for a longer conversation; comfortable has headroom. If you expect to grow the context, buy for comfortable.
06

Open the card you have settled on

Following a card through to its own page shows every other model it can hold, which is the question that follows once OpenELM-450M is settled.

Answers

OpenELM-450M — common questions

What is OpenELM-450M used for?

OpenELM-450M works in Language, and is recorded as handling language modeling/generation, Code generation, Question answering. These are the areas it was designed around; they describe intent rather than a hard boundary.

Where can I download OpenELM-450M?

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

How much compute was used to train OpenELM-450M?

Around 6.3 × 10²¹ FLOP, on NVIDIA H100 SXM5 80GB. 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 OpenELM-450M 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 OpenELM-450M assume it is fully resident.

Would two GPUs run OpenELM-450M faster?

Two cards buy memory rather than speed. That matters for OpenELM-450M only if one card cannot hold it — 818 can, so a second adds little.

Why does the quantisation differ between cards for OpenELM-450M?

A larger card holds a more accurate copy. Across the cards that run OpenELM-450M, 1 compression levels are used; the floor control above pins it to one.

How accurate are these OpenELM-450M speed estimates?

They are calculated from specifications rather than measured, and each carries a range — 4,518–12,047 tok/s on the B200, for instance. The same model and card vary by thirty to fifty per cent depending on the inference software and its version.

What GPU do I need to run OpenELM-450M?

The smallest card in our catalogue that holds OpenELM-450M is the Tesla C1080, with 4 GB of memory. It runs the model at Q8_0 using about 1.2 GB, and produces roughly 81.9 tokens per second. 818 cards in total can run it.

How fast is OpenELM-450M on a GPU?

It depends on the card. The quickest we calculate is a B200 at about 7,529 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 OpenELM-450M clear that.

How much VRAM does OpenELM-450M need?

About 1.2 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 OpenELM-450M on a 8 GB GPU?

Yes. A CMP 170HX 8 GB with 8 GB runs it at Q8_0, using about 1.2 GB and generating roughly 1,402 tokens per second — a comfortable fit.

Can I run OpenELM-450M on a 12 GB GPU?

Yes. A GeForce RTX 3080 Ti with 12 GB runs it at Q8_0, using about 1.2 GB and generating roughly 859 tokens per second — a comfortable fit.

Can I run OpenELM-450M on a 16 GB GPU?

Yes. A Tesla V100 SXM2 16 GB with 16 GB runs it at Q8_0, using about 1.2 GB and generating roughly 1,064 tokens per second — a comfortable fit.

Can I run OpenELM-450M on a 24 GB GPU?

Yes. A GeForce RTX 5090 D V2 with 24 GB runs it at Q8_0, using about 1.2 GB and generating roughly 1,261 tokens per second — a comfortable fit.

Is OpenELM-450M open source?

Its weights are published, so OpenELM-450M 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 OpenELM-450M have?

OpenELM-450M has 450M parameters. 0.45B (Table 4a). 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 OpenELM-450M?

OpenELM-450M was published by Apple, based in United States of America, categorised as industry.

When was OpenELM-450M released?

OpenELM-450M was published in May 2024. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.

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