gpt-oss-120b TPS calculator

Open weights OpenAI 116.8B parameters August 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

38 cards that can run it

818 cards we hold specifications for

Smallest card that fits

RTX PRO 5000 72 GB Blackwell

72 GB · IQ4_XS · 11.9 tok/s

Fastest card

H100 NVL 94 GB

33.0 tok/s · 94 GB

Which GPUs can run gpt-oss-120b?

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

38 cards match

Calculating

					Needs	Quantisation	Fit
33.0 tok/s 20–53 · low confidence	H100 NVL 94 GB NVIDIA	94 GB	3,940 GB/s	Mar 2023	71.4 GB	Q4_K_M	Tight
29.0 tok/s 17–46 · low confidence	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	125.8 GB	Q8_0	Comfortable
29.0 tok/s 17–46 · low confidence	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	125.8 GB	Q8_0	Comfortable
28.1 tok/s 17–45 · low confidence	H100 SXM5 80 GB NVIDIA	80 GB	3,360 GB/s	Oct 2022	71.4 GB	Q4_K_M	Tight
28.1 tok/s 17–45 · low confidence	H100 SXM5 94 GB NVIDIA	94 GB	3,360 GB/s	Mar 2023	71.4 GB	Q4_K_M	Tight
28.1 tok/s 17–45 · low confidence	H800 SXM5 NVIDIA	80 GB	3,360 GB/s	Mar 2023	71.4 GB	Q4_K_M	Tight
26.9 tok/s 16–43 · low confidence	Radeon Instinct MI300 AMD	128 GB	6,550 GB/s	Jan 2023	98.6 GB	Q6_K	Tight
23.2 tok/s 14–37 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	125.8 GB	Q8_0	Comfortable
23.2 tok/s 14–37 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	125.8 GB	Q8_0	Comfortable
21.9 tok/s 13–35 · low confidence	Radeon Instinct MI300A AMD	128 GB	5,325 GB/s	Dec 2023	98.6 GB	Q6_K	Tight
21.8 tok/s 13–35 · low confidence	H100 PCIe 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	85.0 GB	Q5_K_M	Tight
21.8 tok/s 13–35 · low confidence	H100 SXM5 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	85.0 GB	Q5_K_M	Tight
17.7 tok/s 11–28 · low confidence	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	125.8 GB	Q8_0	Tight
17.7 tok/s 11–28 · low confidence	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	125.8 GB	Q8_0	Tight
17.1 tok/s 10–27 · low confidence	A100 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Nov 2020	71.4 GB	Q4_K_M	Tight
17.1 tok/s 10–27 · low confidence	A100X NVIDIA	80 GB	2,040 GB/s	Jun 2021	71.4 GB	Q4_K_M	Tight
17.1 tok/s 10–27 · low confidence	A800 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Aug 2022	71.4 GB	Q4_K_M	Tight
17.1 tok/s 10–27 · low confidence	H100 CNX NVIDIA	80 GB	2,040 GB/s	Mar 2023	71.4 GB	Q4_K_M	Tight
17.1 tok/s 10–27 · low confidence	H100 PCIe 80 GB NVIDIA	80 GB	2,040 GB/s	Oct 2022	71.4 GB	Q4_K_M	Tight
17.1 tok/s 10–27 · low confidence	H800 PCIe 80 GB NVIDIA	80 GB	2,040 GB/s	Mar 2023	71.4 GB	Q4_K_M	Tight
17.0 tok/s 10–27 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	125.8 GB	Q8_0	Comfortable
16.2 tok/s 10–26 · low confidence	A100 PCIe 80 GB NVIDIA	80 GB	1,940 GB/s	Jun 2021	71.4 GB	Q4_K_M	Tight
16.2 tok/s 10–26 · low confidence	A800 PCIe 80 GB NVIDIA	80 GB	1,940 GB/s	Nov 2022	71.4 GB	Q4_K_M	Tight
15.1 tok/s 9–24 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	125.8 GB	Q8_0	Comfortable
15.1 tok/s 9–24 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	125.8 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: OpenAI
Organisation type: Industry
Country: United States of America
Published: 5 August 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, 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: 116.8B
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: 4.9 × 10²⁴ FLOP
How it was established: 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

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)

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: Discretionary
Record confidence: Confident

Sources

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

Reference: gpt-oss-120b & gpt-oss-20b Model Card
Last updated: 10 February 2026

The extremes

The ten fastest GPUs that run gpt-oss-120b

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 gpt-oss-120b

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

RTX PRO 5000 72 GB Blackwell

Memory needed

64.6 GB

Fastest

33.0 tok/s

gpt-oss-120b reaches a parameter count of 116.8B. 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: 38.

The entry point is RTX PRO 5000 72 GB Blackwell, with a memory capacity of 72 GB, running it at a compression of IQ4_XS and producing around 11.9 tokens per second.

The quickest result comes from H100 NVL 94 GB, generating roughly 33.0 tokens per second on the strength of a memory bandwidth of 3,940 GB/s.

Where it came from

gpt-oss-120b was published by OpenAI, in the country recorded as United States of America, during August 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, 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.

Understanding the speeds

Across every card that can run it, the middle of the range sits at 17.1 tokens per second. Producing text faster than most people read it: 36 of them.

It is a dense model, so every parameter is read for every token produced. That makes speed track memory bandwidth almost exactly — a card with twice the bandwidth generates roughly twice as fast.

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.

What went into building it

Training it took a computation budget of roughly 4.9 × 10²⁴ FLOP, on hardware recorded as NVIDIA H100 SXM5 80GB. That figure measures what producing the model cost, and has no bearing on how fast it answers.

The reason it appears in this catalogue at all: discretionary.

Step by step

How to choose a GPU for gpt-oss-120b

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 gpt-oss-120b, needing around 64.6 GB at a compression of IQ4_XS. Capacity is the gate — a card either holds it or it does not.
02

Decide how long your conversations run

Longer conversations cost memory on top of what the weights need. Move the slider to your real working length before trusting any row for gpt-oss-120b.
03

Decide how much compression you will accept

Each card runs the least-compressed copy it can hold, 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

Sort by speed to see how cards rank for gpt-oss-120b. It will not match a gaming ordering, because generation is bound by memory bandwidth. The card topping the list is H100 NVL 94 GB, at 33.0 tok/s.
05

Look at the headroom, not just the fit

A tight fit runs, but leaves nothing spare for a longer conversation, in the case of gpt-oss-120b. 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

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 you have settled on gpt-oss-120b.

Answers

gpt-oss-120b — common questions

gpt-oss-120b— 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: 20–53 tok/s on H100 NVL 94 GB. The same model and card vary by thirty to fifty per cent depending on the inference software and its version.

gpt-oss-120b— what GPU do I need to run it?

The smallest card in our catalogue that holds it is RTX PRO 5000 72 GB Blackwell, with a memory capacity of 72 GB. It runs the model at a compression of IQ4_XS using about 64.6 GB, and produces roughly 11.9 tokens per second. The number of cards able to run it in total: 38.

gpt-oss-120b— how fast is it on a GPU?

It depends on the card. The quickest we calculate is H100 NVL 94 GB, at about 33.0 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: 36.

gpt-oss-120b— how much VRAM does it need?

It needs about 64.6 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.

gpt-oss-120b— 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.

gpt-oss-120b— how many parameters does it have?

It has a parameter count of 116.8B. Total parameters: 116.83B. 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.

gpt-oss-120b— who created it?

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

gpt-oss-120b— when was it released?

It was published in August 2025.

gpt-oss-120b— what is it used for?

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

gpt-oss-120b— 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.

gpt-oss-120b— how much compute was used to train it?

Training consumed around 4.9 × 10²⁴ FLOP, on hardware recorded as 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.

gpt-oss-120b— can I run it if it does not fit in my GPU?

It can be split between the card and system memory, but it generates painfully slowly that way. The nearest miss we calculate falls short by 13.8 GB. Every figure here assumes the whole model is resident on the card.

gpt-oss-120b— would two GPUs run it faster?

Capacity adds across cards; throughput does not. The number of cards already holding it on their own: 38. So a second card is rarely the answer here.

gpt-oss-120b— 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: 5. Bigger cards get the more accurate version, and the quality floor above pins the comparison to one level.

Source

Original publication

Record last updated 10 February 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