OPT-175B TPS calculator

Open weights Meta AI 175B parameters May 2022

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

24 cards that can run it

818 cards we hold specifications for

Smallest card that fits

H100 PCIe 96 GB

96 GB · Q3_K_M · 21.9 tok/s

Fastest card

Radeon Instinct MI300

28.6 tok/s · 128 GB

Which GPUs can run OPT-175B?

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

24 cards match

Calculating

					Needs	Quantisation	Fit
28.6 tok/s 17–46 · low confidence	Radeon Instinct MI300 AMD	128 GB	6,550 GB/s	Jan 2023	106.6 GB	Q4_K_M	Tight
28.1 tok/s 17–45 · low confidence	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	147.3 GB	Q6_K	Tight
27.3 tok/s 16–44 · low confidence	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	106.6 GB	Q4_K_M	Tight
27.3 tok/s 16–44 · low confidence	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	106.6 GB	Q4_K_M	Tight
23.2 tok/s 14–37 · low confidence	Radeon Instinct MI300A AMD	128 GB	5,325 GB/s	Dec 2023	106.6 GB	Q4_K_M	Tight
21.9 tok/s 13–35 · low confidence	H100 PCIe 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	86.2 GB	Q3_K_M	Tight
21.9 tok/s 13–35 · low confidence	H100 SXM5 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	86.2 GB	Q3_K_M	Tight
19.4 tok/s 12–31 · low confidence	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	188.1 GB	Q8_0	Comfortable
15.5 tok/s 9–25 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	188.1 GB	Q8_0	Comfortable
15.5 tok/s 9–25 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	188.1 GB	Q8_0	Comfortable
14.6 tok/s 9–23 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	147.3 GB	Q6_K	Tight
14.6 tok/s 9–23 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	147.3 GB	Q6_K	Tight
14.3 tok/s 9–23 · low confidence	Radeon Instinct MI250 AMD	128 GB	3,280 GB/s	Nov 2021	106.6 GB	Q4_K_M	Tight
14.3 tok/s 9–23 · low confidence	Radeon Instinct MI250X AMD	128 GB	3,280 GB/s	Nov 2021	106.6 GB	Q4_K_M	Tight
11.9 tok/s 7–19 · low confidence	Data Center GPU Max 1550 Intel	128 GB	3,280 GB/s	Jan 2023	106.6 GB	Q4_K_M	Tight
11.7 tok/s 7–19 · low confidence	RTX PRO 6000 Blackwell NVIDIA	96 GB	1,790 GB/s	Mar 2025	86.2 GB	Q3_K_M	Tight
11.7 tok/s 7–19 · low confidence	RTX PRO 6000 Blackwell Max-Q NVIDIA	96 GB	1,790 GB/s	Mar 2025	86.2 GB	Q3_K_M	Tight
11.7 tok/s 7–19 · low confidence	RTX PRO 6000 Blackwell Server NVIDIA	96 GB	1,790 GB/s	Mar 2025	86.2 GB	Q3_K_M	Tight
11.7 tok/s 7–19 · low confidence	RTX PRO 6000D Blackwell Max-Q NVIDIA	96 GB	1,790 GB/s	Mar 2025	86.2 GB	Q3_K_M	Tight
11.7 tok/s 7–19 · low confidence	Data Center GPU Max Subsystem Intel	128 GB	3,210 GB/s	Jan 2023	106.6 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	188.1 GB	Q8_0	Comfortable
10.4 tok/s 6–17 · low confidence	Data Center GPU Max 1350 Intel	96 GB	2,460 GB/s	Jan 2023	86.2 GB	Q3_K_M	Tight
1.5 tok/s 1–2 · low confidence	GB10 NVIDIA	128 GB	273 GB/s	Oct 2025	106.6 GB	Q4_K_M	Tight
1.5 tok/s 1–2 · low confidence	Jetson T5000 NVIDIA	128 GB	273 GB/s	Aug 2025	106.6 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: Meta AI
Organisation type: Industry
Country: United States of America
Published: 2 May 2022
Authors: Susan Zhang∗ , Stephen Roller∗ , Naman Goyal∗ , Mikel Artetxe, Moya Chen, Shuohui Chen, Christopher Dewan, Mona Diab, Xian Li, Xi Victoria Lin, Todor Mihaylov, Myle Ott† , Sam Shleifer† , Kurt Shuster, Daniel Simig, Punit Singh Koura, Anjali Sridhar, Tianlu Wang, Luke Zettlemoyer

What it does

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

Domain: Language
Task: Language modeling, Chat, Language modeling/generation, Question answering
Approach: Self-supervised learning
Numerical format: FP16

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: 175B
Training data: 180,000,000,000 tokens
Epochs: 1.67
Batch size: 2,000,000

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: 4.3 × 10²³ FLOP
How it was established: Reported

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
Chips used: 1,024
Chip-hours: 812,544
Wall-clock time: 794 hours (33.1 days)
Hardware utilisation: HFU 47.1%
Power draw: 822.7 kW
Compute cost: $733,635

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)
Training code: Open source

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
Why it is tracked: Significant use,Highly cited
Record confidence: Confident
Citations: 4,716
Benchmark data: OPT-175B

Sources

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

Reference: OPT: Open Pre-trained Transformer Language Models
Last updated: 25 May 2026

The extremes

The ten fastest GPUs that run OPT-175B

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 OPT-175B

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

Hardware requirements in practice

Minimum card

H100 PCIe 96 GB

Memory needed

86.2 GB

Fastest

28.6 tok/s

OPT-175B sits at 175B parameters, which puts it above consumer hardware and into the range where a card is bought for this purpose rather than repurposed for it. 24 of the cards we track can hold it.

The entry point is the H100 PCIe 96 GB: 96 GB of memory, Q3_K_M compression, roughly 21.9 tokens per second.

A Radeon Instinct MI300 is the fastest we calculate for it: about 28.6 tokens per second, from 6,550 GB/s of memory bandwidth.

What this model is

OPT-175B was published by Meta AI, in United States of America, in May 2022. The organisation is categorised as industry.

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

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.

What decides the speed

Across every card that can run it, the middle of the range is about 14.5 tokens per second, and 22 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.

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

Training it took roughly 4.3 × 10²³ FLOP of computation, on NVIDIA A100 SXM4 80 GB — a measure of what producing the model cost, not of how fast it answers.

It was trained on about 180,000,000,000 tokens of text.

Its inclusion criterion is significant use,Highly cited.

Step by step

How to choose a GPU for OPT-175B

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 OPT-175B — around 86.2 GB at Q3_K_M. Capacity is the gate — a card either holds it or it does not.
02

Match the context to your actual use

Longer conversations cost memory on top of what the weights need. Move the slider to your real working length before trusting any row for OPT-175B.
03

Set a quality floor

The quantisation column varies by card, because a bigger card holds a more accurate copy of OPT-175B — Q3_K_M on the smallest card that fits. Set a floor to hold the comparison at one level.
04

Compare tokens per second, not specifications

The speed ordering for OPT-175B is effectively an ordering by memory bandwidth, which is why the Radeon Instinct MI300 tops it at 28.6 tok/s.
05

Read the fit column last

The fit column separates cards that just manage OPT-175B from those with room to spare. Buy for the second if the context might grow.
06

Check the card from the other side

Every card name links to its own page, which runs the same calculation across the whole model catalogue. Worth a look before buying for OPT-175B alone — a card is usually bought for more than one model.

Answers

OPT-175B — common questions

Where can I download OPT-175B?

The weights for OPT-175B 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 OPT-175B?

Around 4.3 × 10²³ FLOP, on NVIDIA A100 SXM4 80 GB. 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 OPT-175B 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 — the nearest miss we calculate is short by 22.0 GB. Our figures for OPT-175B assume it is fully resident.

Would two GPUs run OPT-175B faster?

A second card roughly doubles the memory available but not the generation rate. With 24 cards already able to run OPT-175B alone, the case for pairing is weak.

Why does the quantisation differ between cards for OPT-175B?

Because capacity varies, so does how hard OPT-175B has to be squeezed — 4 distinct levels appear in the table above. Set a minimum quality to compare at one.

How accurate are these OPT-175B 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 17–46 tok/s on the Radeon Instinct MI300 rather than a single number.

What GPU do I need to run OPT-175B?

The smallest card in our catalogue that holds OPT-175B is the H100 PCIe 96 GB, with 96 GB of memory. It runs the model at Q3_K_M using about 86.2 GB, and produces roughly 21.9 tokens per second. 24 cards in total can run it.

How fast is OPT-175B on a GPU?

It depends on the card. The quickest we calculate is a Radeon Instinct MI300 at about 28.6 tokens per second; the slowest that still runs it manages considerably less. Reading speed is around ten tokens per second, and 22 of the cards that can run OPT-175B clear that.

How much VRAM does OPT-175B need?

About 86.2 GB at Q3_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.

Is OPT-175B open source?

Its weights are published, so OPT-175B 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 OPT-175B have?

OPT-175B has 175B parameters. "In line with Meta AI’s commitment to open science, we are sharing Open Pretrained Transformer (OPT-175B), a language model with 175 billion parameters trained on publicly available data sets". 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 OPT-175B?

OPT-175B was published by Meta AI, based in United States of America, categorised as industry.

When was OPT-175B released?

OPT-175B was published in May 2022. 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 OPT-175B used for?

OPT-175B works in Language, and is recorded as handling language modeling, Chat, Language modeling/generation, Question answering. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.

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