Pythia-12b TPS calculator

Open weights EleutherAI,Booz Allen Hamilton, McLean,University of Cambridge,Indraprastha Institute of Information Technology Delhi,Stability AI,datasaur.ai,University of Amsterdam 12B parameters April 2023

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

509 cards that can run it

818 cards we hold specifications for

Smallest card that fits

Xeon Phi 5110P

8 GB · Q3_K_M · 19.8 tok/s

Fastest card

B200

282 tok/s · 180 GB

Which GPUs can run Pythia-12b?

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

509 cards match

Calculating

					Needs	Quantisation	Fit
282 tok/s 169–452 · low confidence	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	13.5 GB	Q8_0	Comfortable
282 tok/s 169–452 · low confidence	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	13.5 GB	Q8_0	Comfortable
225 tok/s 135–361 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	13.5 GB	Q8_0	Comfortable
225 tok/s 135–361 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	13.5 GB	Q8_0	Comfortable
180 tok/s 108–289 · low confidence	Radeon Instinct MI300 AMD	128 GB	6,550 GB/s	Jan 2023	13.5 GB	Q8_0	Comfortable
173 tok/s 104–276 · low confidence	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	13.5 GB	Q8_0	Comfortable
173 tok/s 104–276 · low confidence	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	13.5 GB	Q8_0	Comfortable
165 tok/s 99–264 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	13.5 GB	Q8_0	Comfortable
147 tok/s 88–235 · low confidence	Radeon Instinct MI300A AMD	128 GB	5,325 GB/s	Dec 2023	13.5 GB	Q8_0	Comfortable
147 tok/s 88–235 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	13.5 GB	Q8_0	Comfortable
147 tok/s 88–235 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	13.5 GB	Q8_0	Comfortable
142 tok/s 85–227 · low confidence	CMP 170HX 8 GB NVIDIA	8 GB	1,490 GB/s	Sep 2021	6.6 GB	Q3_K_M	Tight
139 tok/s 83–222 · low confidence	H100 NVL 94 GB NVIDIA	94 GB	3,940 GB/s	Mar 2023	13.5 GB	Q8_0	Comfortable
127 tok/s 76–203 · low confidence	CMP 170HX 10 GB NVIDIA	10 GB	1,560 GB/s	Sep 2021	8.0 GB	Q4_K_M	Tight
119 tok/s 71–190 · low confidence	H100 PCIe 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	13.5 GB	Q8_0	Comfortable
119 tok/s 71–190 · low confidence	H100 SXM5 80 GB NVIDIA	80 GB	3,360 GB/s	Oct 2022	13.5 GB	Q8_0	Comfortable
119 tok/s 71–190 · low confidence	H100 SXM5 94 GB NVIDIA	94 GB	3,360 GB/s	Mar 2023	13.5 GB	Q8_0	Comfortable
119 tok/s 71–190 · low confidence	H100 SXM5 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	13.5 GB	Q8_0	Comfortable
119 tok/s 71–190 · low confidence	H800 SXM5 NVIDIA	80 GB	3,360 GB/s	Mar 2023	13.5 GB	Q8_0	Comfortable
90.3 tok/s 54–144 · low confidence	Radeon Instinct MI250 AMD	128 GB	3,280 GB/s	Nov 2021	13.5 GB	Q8_0	Comfortable
90.3 tok/s 54–144 · low confidence	Radeon Instinct MI250X AMD	128 GB	3,280 GB/s	Nov 2021	13.5 GB	Q8_0	Comfortable
75.3 tok/s 45–120 · low confidence	Data Center GPU Max 1550 Intel	128 GB	3,280 GB/s	Jan 2023	13.5 GB	Q8_0	Comfortable
73.6 tok/s 44–118 · low confidence	Data Center GPU Max Subsystem Intel	128 GB	3,210 GB/s	Jan 2023	13.5 GB	Q8_0	Comfortable
73.1 tok/s 44–117 · low confidence	RTX A5000-8Q NVIDIA	8 GB	768 GB/s	Apr 2021	6.6 GB	Q3_K_M	Tight
72.0 tok/s 43–115 · low confidence	A100 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Nov 2020	13.5 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: EleutherAI,Booz Allen Hamilton, McLean,University of Cambridge,Indraprastha Institute of Information Technology Delhi,Stability AI,datasaur.ai,University of Amsterdam
Organisation type: Research collective,Industry,Academia,Academia,Industry,Industry,Academia
Country: United States of America, United Kingdom of Great Britain and Northern Ireland, India, Netherlands
Published: 3 April 2023
Authors: Stella Biderman, Hailey Schoelkopf, Quentin Anthony, Herbie Bradley, Kyle O'Brien, Eric Hallahan, Mohammad Aflah Khan, Shivanshu Purohit, USVSN Sai Prashanth, Edward Raff, Aviya Skowron, Lintang Sutawika, Oskar van der Wal

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: 12B
Training data: 299,892,736,000 tokens
Epochs: 1
Batch size: 2,097,152

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: 2.2 × 10²² FLOP
How it was established: Operation counting

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 40 GB
Chips used: 256
Chip-hours: 72,300
Hardware utilisation: MFU 26.6%
Power draw: 204.1 kW
Cloud vendor: Amazon Web Services
Data centre: AWS US East

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)
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.

Record confidence: Confident
Citations: 1,862
Benchmark data: Pythia-12b

Sources

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

Reference: Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling
Last updated: 25 May 2026

The extremes

The ten fastest GPUs that run Pythia-12b

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 Pythia-12b

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

Xeon Phi 5110P

Memory needed

6.6 GB

Fastest

282 tok/s

Pythia-12b is small enough at 12B parameters that hardware is rarely the obstacle — 509 of the cards we track can run it, including cards several years old.

The entry point is the Xeon Phi 5110P: 8 GB of memory, Q3_K_M compression, roughly 19.8 tokens per second.

The quickest result comes from a B200 at around 282 tokens per second — its 8,000 GB/s of bandwidth is what buys that.

Background

Pythia-12b was published by EleutherAI,Booz Allen Hamilton, McLean,University of Cambridge,Indraprastha Institute of Information Technology Delhi,Stability AI,datasaur.ai,University of Amsterdam, in United States of America, in April 2023. The organisation is categorised as research collective,Industry,Academia,Academia,Industry,Industry,Academia.

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.

Reading the throughput figures

The median result is around 20.8 tokens per second; 455 cards produce text faster than most people read it.

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.

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.

How it was trained

The training run consumed about 2.2 × 10²² FLOP, on NVIDIA A100 SXM4 40 GB. That figure describes the cost of creating it and has no bearing on how quickly it generates text.

The training set ran to roughly 299,892,736,000 tokens.

Step by step

How to choose a GPU for Pythia-12b

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 Pythia-12b — around 6.6 GB at Q3_K_M. Capacity is the gate — a card either holds it or it does not.
02

Set the context length you will work at

The conversation occupies memory too, and grows as it goes. Set the slider to the length you expect: at long context Pythia-12b can slip off a card that handles short questions easily.
03

Set a quality floor

The quantisation column varies by card, because a bigger card holds a more accurate copy of Pythia-12b — Q3_K_M on the smallest card that fits. Set a floor to hold the comparison at one level.
04

Rank by throughput rather than spec sheet

The speed ordering for Pythia-12b is effectively an ordering by memory bandwidth, which is why the B200 tops it at 282 tok/s.
05

Check the fit verdict before buying

Tight means Pythia-12b 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

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 Pythia-12b is settled.

Answers

Pythia-12b — common questions

What is Pythia-12b used for?

Pythia-12b works in Language, and is recorded as handling language modeling/generation, Question answering. 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.

Where can I download Pythia-12b?

The weights for Pythia-12b 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 Pythia-12b?

Around 2.2 × 10²² FLOP, on NVIDIA A100 SXM4 40 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 Pythia-12b 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 2.6 GB. Our figures for Pythia-12b assume it is fully resident.

Would two GPUs run Pythia-12b faster?

Two cards buy memory rather than speed. That matters for Pythia-12b only if one card cannot hold it — 509 can, so a second adds little.

Why does the quantisation differ between cards for Pythia-12b?

Because capacity varies, so does how hard Pythia-12b has to be squeezed — 5 distinct levels appear in the table above. Set a minimum quality to compare at one.

How accurate are these Pythia-12b speed estimates?

These are estimates with real error bars. The fastest result here, 169–452 tok/s on the B200, could reasonably land anywhere in its published range depending on which runtime you use.

What GPU do I need to run Pythia-12b?

The smallest card in our catalogue that holds Pythia-12b is the Xeon Phi 5110P, with 8 GB of memory. It runs the model at Q3_K_M using about 6.6 GB, and produces roughly 19.8 tokens per second. 509 cards in total can run it.

How fast is Pythia-12b on a GPU?

It depends on the card. The quickest we calculate is a B200 at about 282 tokens per second; the slowest that still runs it manages considerably less. Reading speed is around ten tokens per second, and 455 of the cards that can run Pythia-12b clear that.

How much VRAM does Pythia-12b need?

About 6.6 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.

Can I run Pythia-12b on a 8 GB GPU?

Yes. A CMP 170HX 8 GB with 8 GB runs it at Q3_K_M, using about 6.6 GB and generating roughly 142 tokens per second — a tight fit.

Can I run Pythia-12b on a 12 GB GPU?

Yes. A GeForce RTX 3080 Ti with 12 GB runs it at Q6_K, using about 10.8 GB and generating roughly 46.8 tokens per second — a tight fit.

Can I run Pythia-12b on a 16 GB GPU?

Yes. A Tesla V100 SXM2 16 GB with 16 GB runs it at Q8_0, using about 13.5 GB and generating roughly 39.9 tokens per second — a tight fit.

Can I run Pythia-12b on a 24 GB GPU?

Yes. A GeForce RTX 5090 D V2 with 24 GB runs it at Q8_0, using about 13.5 GB and generating roughly 47.3 tokens per second — a comfortable fit.

Is Pythia-12b open source?

Its weights are published, so Pythia-12b 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 Pythia-12b have?

Pythia-12b has 12B parameters. See Table 1 for non-embedding parameters. 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 Pythia-12b?

Pythia-12b was published by EleutherAI,Booz Allen Hamilton, McLean,University of Cambridge,Indraprastha Institute of Information Technology Delhi,Stability AI,datasaur.ai,University of Amsterdam, based in United States of America, categorised as research collective,Industry,Academia,Academia,Industry,Industry,Academia.

When was Pythia-12b released?

Pythia-12b was published in April 2023. 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 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