OPT-IML (175B) TPS calculator

Open weights Meta AI 175B parameters December 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-IML (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: 22 December 2022
Authors: Srinivasan Iyer, Xi Victoria Lin, Ramakanth Pasunuru, Todor Mihaylov, Daniel Simig, Ping Yu, Kurt Shuster, Tianlu Wang, Qing Liu, Punit Singh Koura, Xian Li, Brian O'Horo, Gabriel Pereyra, Jeff Wang, Christopher Dewan, Asli Celikyilmaz, Luke Zettlemoyer, Ves Stoyanov

What it does

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

Domain: Language
Task: Language modeling
Base model: OPT-175B

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: 2,000,000,000 tokens
Batch size: 125

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: Operation counting
Fine-tuning compute: 2.1 × 10²¹ 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 A100
Chips used: 128
Chip-hours: 9,216
Wall-clock time: 72 hours
Power draw: 102.3 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)
Training code: Unreleased

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: Likely
Citations: 304

Sources

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

Reference: OPT-IML: Scaling Language Model Instruction Meta Learning through the Lens of Generalization
Last updated: 25 May 2026

The extremes

The ten fastest GPUs that run OPT-IML (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-IML (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

What it takes to run this model

Minimum card

H100 PCIe 96 GB

Memory needed

86.2 GB

Fastest

28.6 tok/s

OPT-IML (175B) reaches a parameter count of 175B. That puts it above consumer hardware, into the range where a card is bought for this purpose rather than repurposed for it. The number of cards we track that can hold it: 24.

The smallest card that holds it is H100 PCIe 96 GB, with a memory capacity of 96 GB, running it at a compression of Q3_K_M and producing around 21.9 tokens per second.

The fastest we calculate for it is Radeon Instinct MI300, generating roughly 28.6 tokens per second on the strength of a memory bandwidth of 6,550 GB/s.

Where it came from

OPT-IML (175B) was published by Meta AI, in the country recorded as United States of America, during December 2022. 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.

It builds on OPT-175B. That is why it shares the base model's general shape and size.

The weights are published, so it can be downloaded and run on your own hardware indefinitely, offline, with no account attached.

Understanding the speeds

The median result is around 14.5 tokens per second. Producing text faster than most people read it: 22 of them.

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 4.3 × 10²³ FLOP, on hardware recorded as NVIDIA A100. That figure measures what producing the model cost, and has no bearing on how fast it answers.

The training set ran to roughly 2,000,000,000 tokens of text.

Step by step

How to choose a GPU for OPT-IML (175B)

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

The table lists every card able to hold OPT-IML (175B), needing around 86.2 GB at a compression of Q3_K_M. No amount of processing power compensates for a card that cannot hold it.
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-IML (175B).
03

Choose how far you will compress it

Compression is what makes a model fit smaller cards, at some cost in accuracy, reaching a compression of Q3_K_M 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

Sort by speed to see how cards rank for OPT-IML (175B). It will not match a gaming ordering, because generation is bound by memory bandwidth. The card topping the list is Radeon Instinct MI300, at 28.6 tok/s.
05

Check the fit verdict before buying

Tight means it loads and works with no room to raise the context later, in the case of OPT-IML (175B). 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

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 you have settled on OPT-IML (175B).

Answers

OPT-IML (175B) — common questions

OPT-IML (175B)— 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.

OPT-IML (175B)— how many parameters does it have?

It has a parameter count of 175B. 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.

OPT-IML (175B)— who created it?

It was published by Meta AI, based in United States of America, an organisation categorised as industry.

OPT-IML (175B)— when was it released?

It was published in December 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.

OPT-IML (175B)— what is it used for?

It works in the domain of Language, and is recorded as handling the task of language modeling. A model can carry several of each, so these are the areas it was built for rather than a limit on what it will attempt.

OPT-IML (175B)— where can I download it?

The weights are published, though we do not hold a repository link for it. This site calculates hardware requirements rather than hosting model files.

OPT-IML (175B)— how much compute was used to train it?

Training consumed around 4.3 × 10²³ FLOP, on hardware recorded as NVIDIA A100. 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.

OPT-IML (175B)— 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 22.0 GB. Every figure here assumes the whole model is resident on the card.

OPT-IML (175B)— would two GPUs run it faster?

A second card roughly doubles the memory available but not the generation rate. The number already able to run it alone: 24. So a second card is rarely the answer here.

OPT-IML (175B)— why does the quantisation differ between cards?

Because capacity varies, so does how hard it has to be squeezed. The number of distinct levels in the table above: 4. Bigger cards get the more accurate version, and the quality floor above pins the comparison to one level.

OPT-IML (175B)— how accurate are these speed estimates?

Every figure is derived from memory bandwidth and model size, not benchmarked, which is why each is published as a range rather than a single number. One example: 17–46 tok/s on Radeon Instinct MI300. The same model and card vary by thirty to fifty per cent depending on the inference software and its version.

OPT-IML (175B)— what GPU do I need to run it?

The smallest card in our catalogue that holds it is H100 PCIe 96 GB, with a memory capacity of 96 GB. It runs the model at a compression of Q3_K_M using about 86.2 GB, and produces roughly 21.9 tokens per second. The number of cards able to run it in total: 24.

OPT-IML (175B)— how fast is it on a GPU?

It depends on the card. The quickest we calculate is 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 the number of cards clearing that: 22.

OPT-IML (175B)— how much VRAM does it need?

It needs about 86.2 GB at a compression of Q3_K_M, 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.

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