gpt-oss-20b TPS calculator
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 we hold specifications for
Smallest card that fits
Xeon Phi 7120P
16 GB · Q4_K_M · 10.7 tok/s
Fastest card
B200
162 tok/s · 180 GB
Which GPUs can run gpt-oss-20b?
Set the inputs, read the answer
A longer conversation needs more memory, which can push this model off smaller cards.
Hides cards that would only fit the model by compressing it below this point.
241 cards match
Calculating| Needs | Quantisation | Fit | |||||
|---|---|---|---|---|---|---|---|
|
162
tok/s
97–259 · low confidence |
B200 NVIDIA | 180 GB | 8,000 GB/s | Jan 2024 | 23.1 GB | Q8_0 | Comfortable |
|
162
tok/s
97–259 · low confidence |
B300 NVIDIA | 288 GB | 8,000 GB/s | Sep 2025 | 23.1 GB | Q8_0 | Comfortable |
|
129
tok/s
78–207 · low confidence |
Radeon Instinct MI350X AMD | 288 GB | 8,190 GB/s | Jan 2025 | 23.1 GB | Q8_0 | Comfortable |
|
129
tok/s
78–207 · low confidence |
Radeon Instinct MI355X AMD | 288 GB | 8,190 GB/s | Jan 2025 | 23.1 GB | Q8_0 | Comfortable |
|
103
tok/s
62–166 · low confidence |
Radeon Instinct MI300 AMD | 128 GB | 6,550 GB/s | Jan 2023 | 23.1 GB | Q8_0 | Comfortable |
|
99.1
tok/s
59–158 · low confidence |
H200 NVL NVIDIA | 141 GB | 4,890 GB/s | Nov 2024 | 23.1 GB | Q8_0 | Comfortable |
|
99.1
tok/s
59–158 · low confidence |
H200 SXM 141 GB NVIDIA | 141 GB | 4,890 GB/s | Nov 2024 | 23.1 GB | Q8_0 | Comfortable |
|
94.8
tok/s
57–152 · low confidence |
Radeon Instinct MI325X AMD | 256 GB | 6,000 GB/s | Oct 2024 | 23.1 GB | Q8_0 | Comfortable |
|
84.1
tok/s
50–135 · low confidence |
Radeon Instinct MI300A AMD | 128 GB | 5,325 GB/s | Dec 2023 | 23.1 GB | Q8_0 | Comfortable |
|
84.1
tok/s
50–135 · low confidence |
Radeon Instinct MI300X AMD | 192 GB | 5,325 GB/s | Dec 2023 | 23.1 GB | Q8_0 | Comfortable |
|
84.1
tok/s
50–135 · low confidence |
Radeon Instinct MI308X AMD | 192 GB | 5,325 GB/s | Dec 2023 | 23.1 GB | Q8_0 | Comfortable |
|
79.8
tok/s
48–128 · low confidence |
H100 NVL 94 GB NVIDIA | 94 GB | 3,940 GB/s | Mar 2023 | 23.1 GB | Q8_0 | Comfortable |
|
68.1
tok/s
41–109 · low confidence |
H100 PCIe 96 GB NVIDIA | 96 GB | 3,360 GB/s | Mar 2023 | 23.1 GB | Q8_0 | Comfortable |
|
68.1
tok/s
41–109 · low confidence |
H100 SXM5 80 GB NVIDIA | 80 GB | 3,360 GB/s | Oct 2022 | 23.1 GB | Q8_0 | Comfortable |
|
68.1
tok/s
41–109 · low confidence |
H100 SXM5 94 GB NVIDIA | 94 GB | 3,360 GB/s | Mar 2023 | 23.1 GB | Q8_0 | Comfortable |
|
68.1
tok/s
41–109 · low confidence |
H100 SXM5 96 GB NVIDIA | 96 GB | 3,360 GB/s | Mar 2023 | 23.1 GB | Q8_0 | Comfortable |
|
68.1
tok/s
41–109 · low confidence |
H800 SXM5 NVIDIA | 80 GB | 3,360 GB/s | Mar 2023 | 23.1 GB | Q8_0 | Comfortable |
|
52.8
tok/s
32–85 · low confidence |
Tesla V100 SXM2 16 GB NVIDIA | 16 GB | 1,130 GB/s | Nov 2019 | 13.3 GB | Q4_K_M | Tight |
|
51.8
tok/s
31–83 · low confidence |
Radeon Instinct MI250 AMD | 128 GB | 3,280 GB/s | Nov 2021 | 23.1 GB | Q8_0 | Comfortable |
|
51.8
tok/s
31–83 · low confidence |
Radeon Instinct MI250X AMD | 128 GB | 3,280 GB/s | Nov 2021 | 23.1 GB | Q8_0 | Comfortable |
|
44.9
tok/s
27–72 · low confidence |
GeForce RTX 5080 NVIDIA | 16 GB | 960 GB/s | Jan 2025 | 13.3 GB | Q4_K_M | Tight |
|
43.2
tok/s
26–69 · low confidence |
Data Center GPU Max 1550 Intel | 128 GB | 3,280 GB/s | Jan 2023 | 23.1 GB | Q8_0 | Comfortable |
|
42.3
tok/s
25–68 · low confidence |
Data Center GPU Max Subsystem Intel | 128 GB | 3,210 GB/s | Jan 2023 | 23.1 GB | Q8_0 | Comfortable |
|
41.9
tok/s
25–67 · low confidence |
Tesla V100 DGXS 16 GB NVIDIA | 16 GB | 897 GB/s | Mar 2018 | 13.3 GB | Q4_K_M | Tight |
|
41.9
tok/s
25–67 · low confidence |
Tesla V100 PCIe 16 GB NVIDIA | 16 GB | 897 GB/s | Jun 2017 | 13.3 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
- 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
- 20.9B
- Training data
- tokens
Total parameters: 20.91B
(pretraining FLOPs)/(6*3.6B active parameters)
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
- 5.5 × 10²³ FLOP
- How it was established
- Hardware
"The training run for gpt-oss-120b required 2.1 million H100-hours to complete, with gpt-oss-20b needing almost 10x fewer" assuming "almost 10x fewer" means ~9x fewer: 4.94e24/9 = 5.49e23
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-20b
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.
- 01 B300 288 GB · 8,000 GB/s · Q8_0 162 tok/s
- 02 B200 180 GB · 8,000 GB/s · Q8_0 162 tok/s
- 03 Radeon Instinct MI350X 288 GB · 8,190 GB/s · Q8_0 129 tok/s
- 04 Radeon Instinct MI355X 288 GB · 8,190 GB/s · Q8_0 129 tok/s
- 05 Radeon Instinct MI300 128 GB · 6,550 GB/s · Q8_0 103 tok/s
- 06 H200 NVL 141 GB · 4,890 GB/s · Q8_0 99.1 tok/s
- 07 H200 SXM 141 GB 141 GB · 4,890 GB/s · Q8_0 99.1 tok/s
- 08 Radeon Instinct MI325X 256 GB · 6,000 GB/s · Q8_0 94.8 tok/s
- 09 Radeon Instinct MI300A 128 GB · 5,325 GB/s · Q8_0 84.1 tok/s
- 10 Radeon Instinct MI300X 192 GB · 5,325 GB/s · Q8_0 84.1 tok/s
The smallest GPUs that still run gpt-oss-20b
The cheapest route in, by memory capacity. A tight fit runs the model but leaves nothing spare for a longer conversation.
- 01 Ryzen AI Z2 Extreme GPU 16 GB · needs 13.3 GB · Q4_K_M · tight 9.3 tok/s
- 02 Radeon RX 7700 16 GB · needs 13.3 GB · Q4_K_M · tight 22.7 tok/s
- 03 Arc Pro B50 16 GB · needs 13.3 GB · Q4_K_M · tight 6.8 tok/s
- 04 RTX PRO 2000 Blackwell 16 GB · needs 13.3 GB · Q4_K_M · tight 13.5 tok/s
- 05 Ryzen Z2 Extreme GPU 16 GB · needs 13.3 GB · Q4_K_M · tight 4.7 tok/s
- 06 Radeon RX 9060 XT 16 GB 16 GB · needs 13.3 GB · Q4_K_M · tight 11.8 tok/s
- 07 GeForce RTX 5060 Ti 16 GB 16 GB · needs 13.3 GB · Q4_K_M · tight 21.0 tok/s
- 08 GeForce RTX 5080 Mobile 16 GB · needs 13.3 GB · Q4_K_M · tight 41.9 tok/s
- 09 Radeon RX 9070 16 GB · needs 13.3 GB · Q4_K_M · tight 23.5 tok/s
- 10 Radeon RX 9070 XT 16 GB · needs 13.3 GB · Q4_K_M · tight 23.5 tok/s
What the numbers mean
What you need to run it
Minimum card
Xeon Phi 7120P
Memory needed
13.3 GB
Fastest
162 tok/s
With 20.9B parameters, gpt-oss-20b lands in the range a serious desktop card can handle once the weights are compressed. 241 of the cards we track can run it.
The least hardware that works is a Xeon Phi 7120P. Its 16 GB is enough at Q4_K_M compression, giving roughly 10.7 tokens per second.
A B200 is the fastest we calculate for it: about 162 tokens per second, from 8,000 GB/s of memory bandwidth.
Where it came from
gpt-oss-20b was published by OpenAI, in United States of America, in August 2025. The organisation is categorised as industry.
It works in Language, and is recorded as doing language modeling/generation, Question answering.
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 21.0 tokens per second; 198 cards produce text faster than most people read it.
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.
What went into building it
Training it took roughly 5.5 × 10²³ FLOP of computation, on NVIDIA H100 SXM5 80GB — a measure of what producing the model cost, not of how fast it answers.
Its inclusion criterion is discretionary.
Step by step
How to choose a GPU for gpt-oss-20b
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 gpt-oss-20b — around 13.3 GB at Q4_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 gpt-oss-20b.
-
03
Decide how much compression you will accept
Each card runs the least-compressed copy it can hold — Q4_K_M on the smallest card that fits. Setting a floor drops the cards that only manage gpt-oss-20b by squeezing it further than you would want.
-
04
Compare tokens per second, not specifications
Ranking by tokens per second for gpt-oss-20b follows memory bandwidth, not core counts, which is why the B200 tops it at 162 tok/s.
-
05
Look at the headroom, not just the fit
Tight means gpt-oss-20b loads and works, with no room to raise the context later. Comfortable means you can. The difference matters more than a few tokens per second.
-
06
See what else that card runs
Each card page repeats this sweep for every model we hold. It answers what else the hardware is good for, beyond gpt-oss-20b.
Answers
gpt-oss-20b — common questions
How many parameters does gpt-oss-20b have?
gpt-oss-20b has 20.9B parameters. Total parameters: 20.91B. 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 gpt-oss-20b?
gpt-oss-20b was published by OpenAI, based in United States of America, categorised as industry.
When was gpt-oss-20b released?
gpt-oss-20b was published in August 2025.
What is gpt-oss-20b used for?
gpt-oss-20b works in Language, and is recorded as handling language modeling/generation, Question answering. These are the areas it was designed around; they describe intent rather than a hard boundary.
Where can I download gpt-oss-20b?
The weights for gpt-oss-20b 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 gpt-oss-20b?
Around 5.5 × 10²³ 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 gpt-oss-20b if it does not fit in my GPU?
It can be split between the card and system memory, but gpt-oss-20b generates painfully slowly that way — the nearest miss we calculate is short by 2.5 GB. Nothing on this page assumes offloading.
Would two GPUs run gpt-oss-20b faster?
A second card roughly doubles the memory available but not the generation rate. With 241 cards already able to run gpt-oss-20b alone, the case for pairing is weak.
Why does the quantisation differ between cards for gpt-oss-20b?
Each card is shown running the least-compressed copy it can hold, and gpt-oss-20b appears at 4 different compression levels across the cards that fit it. Bigger cards get the more accurate version.
How accurate are these gpt-oss-20b speed estimates?
They are calculated from specifications rather than measured, and each carries a range — 97–259 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 gpt-oss-20b?
The smallest card in our catalogue that holds gpt-oss-20b is the Xeon Phi 7120P, with 16 GB of memory. It runs the model at Q4_K_M using about 13.3 GB, and produces roughly 10.7 tokens per second. 241 cards in total can run it.
How fast is gpt-oss-20b on a GPU?
It depends on the card. The quickest we calculate is a B200 at about 162 tokens per second; the slowest that still runs it manages considerably less. Reading speed is around ten tokens per second, and 198 of the cards that can run gpt-oss-20b clear that.
How much VRAM does gpt-oss-20b need?
About 13.3 GB at Q4_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.
Can I run gpt-oss-20b on a 16 GB GPU?
Yes. A Tesla V100 SXM2 16 GB with 16 GB runs it at Q4_K_M, using about 13.3 GB and generating roughly 52.8 tokens per second — a tight fit.
Can I run gpt-oss-20b on a 24 GB GPU?
Yes. A GeForce RTX 5090 D V2 with 24 GB runs it at Q6_K, using about 18.2 GB and generating roughly 39.4 tokens per second — a tight fit.
Is gpt-oss-20b open source?
Its weights are published, so gpt-oss-20b 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.
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.