OpenPhenom-S/16 TPS calculator

Open weights Recursion Pharmaceuticals 178M parameters November 2024

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 that can run it

818 cards we hold specifications for

Smallest card that fits

Tesla C1080

4 GB · Q8_0 · 207 tok/s

Fastest card

B200

19,030 tok/s · 180 GB

Which GPUs can run OpenPhenom-S/16?

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

818 cards match

Calculating

					Needs	Quantisation	Fit
19,030 tok/s 11,418–30,448 · low confidence	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	0.9 GB	Q8_0	Comfortable
19,030 tok/s 11,418–30,448 · low confidence	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	0.9 GB	Q8_0	Comfortable
15,196 tok/s 9,118–24,314 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	0.9 GB	Q8_0	Comfortable
15,196 tok/s 9,118–24,314 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	0.9 GB	Q8_0	Comfortable
12,153 tok/s 7,292–19,445 · low confidence	Radeon Instinct MI300 AMD	128 GB	6,550 GB/s	Jan 2023	0.9 GB	Q8_0	Comfortable
11,632 tok/s 6,979–18,611 · low confidence	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	0.9 GB	Q8_0	Comfortable
11,632 tok/s 6,979–18,611 · low confidence	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	0.9 GB	Q8_0	Comfortable
11,133 tok/s 6,680–17,812 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	0.9 GB	Q8_0	Comfortable
9,880 tok/s 5,928–15,808 · low confidence	Radeon Instinct MI300A AMD	128 GB	5,325 GB/s	Dec 2023	0.9 GB	Q8_0	Comfortable
9,880 tok/s 5,928–15,808 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	0.9 GB	Q8_0	Comfortable
9,880 tok/s 5,928–15,808 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	0.9 GB	Q8_0	Comfortable
9,372 tok/s 5,623–14,996 · low confidence	H100 NVL 94 GB NVIDIA	94 GB	3,940 GB/s	Mar 2023	0.9 GB	Q8_0	Comfortable
7,993 tok/s 4,796–12,788 · low confidence	H100 PCIe 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	0.9 GB	Q8_0	Comfortable
7,993 tok/s 4,796–12,788 · low confidence	H100 SXM5 80 GB NVIDIA	80 GB	3,360 GB/s	Oct 2022	0.9 GB	Q8_0	Comfortable
7,993 tok/s 4,796–12,788 · low confidence	H100 SXM5 94 GB NVIDIA	94 GB	3,360 GB/s	Mar 2023	0.9 GB	Q8_0	Comfortable
7,993 tok/s 4,796–12,788 · low confidence	H100 SXM5 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	0.9 GB	Q8_0	Comfortable
7,993 tok/s 4,796–12,788 · low confidence	H800 SXM5 NVIDIA	80 GB	3,360 GB/s	Mar 2023	0.9 GB	Q8_0	Comfortable
6,086 tok/s 3,652–9,737 · low confidence	Radeon Instinct MI250 AMD	128 GB	3,280 GB/s	Nov 2021	0.9 GB	Q8_0	Comfortable
6,086 tok/s 3,652–9,737 · low confidence	Radeon Instinct MI250X AMD	128 GB	3,280 GB/s	Nov 2021	0.9 GB	Q8_0	Comfortable
5,072 tok/s 3,043–8,114 · low confidence	Data Center GPU Max 1550 Intel	128 GB	3,280 GB/s	Jan 2023	0.9 GB	Q8_0	Comfortable
4,963 tok/s 2,978–7,941 · low confidence	Data Center GPU Max Subsystem Intel	128 GB	3,210 GB/s	Jan 2023	0.9 GB	Q8_0	Comfortable
4,853 tok/s 2,912–7,764 · low confidence	A100 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Nov 2020	0.9 GB	Q8_0	Comfortable
4,853 tok/s 2,912–7,764 · low confidence	A100X NVIDIA	80 GB	2,040 GB/s	Jun 2021	0.9 GB	Q8_0	Comfortable
4,853 tok/s 2,912–7,764 · low confidence	A800 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Aug 2022	0.9 GB	Q8_0	Comfortable
4,853 tok/s 2,912–7,764 · low confidence	H100 CNX NVIDIA	80 GB	2,040 GB/s	Mar 2023	0.9 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: Recursion Pharmaceuticals
Organisation type: Industry
Country: United States of America
Published: 5 November 2024
Authors: OpenPhenom

What it does

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

Domain: Biology, Vision
Task: Image embedding

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: 178M
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: 3.2 × 10¹⁹ 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 H100 SXM5 80GB
Wall-clock time: 400 hours (16.7 days)

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)

How it is classified

Labels the source dataset applies when tracking notable models, and how confident it is in the entry.

Record confidence: Confident

Sources

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

Reference: Generative deep computer vision models
Last updated: 28 November 2025

The extremes

The ten fastest GPUs that run OpenPhenom-S/16

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 OpenPhenom-S/16

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

Tesla C1080

Memory needed

0.9 GB

Fastest

19,030 tok/s

OpenPhenom-S/16 is small enough at 178M parameters that hardware is rarely the obstacle — 818 of the cards we track can run it, including cards several years old.

The entry point is the Tesla C1080: 4 GB of memory, Q8_0 compression, roughly 207 tokens per second.

Top of the range is the B200, at roughly 19,030 tokens per second thanks to 8,000 GB/s of bandwidth.

Background

OpenPhenom-S/16 was published by Recursion Pharmaceuticals, in United States of America, in November 2024. It comes out of industry.

It works in Biology, Vision, and is recorded as doing image embedding.

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 534.4 tokens per second; 818 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.

How it was trained

The training run consumed about 3.2 × 10¹⁹ FLOP, on NVIDIA H100 SXM5 80GB. That figure describes the cost of creating it and has no bearing on how quickly it generates text.

Step by step

How to choose a GPU for OpenPhenom-S/16

The table above has already assessed every card we hold specifications for against this model. Getting to your answer takes six steps.

01

Read the memory figure first

Look at what OpenPhenom-S/16 actually needs — around 0.9 GB at Q8_0. No amount of processing power compensates for a card that cannot hold it.
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 OpenPhenom-S/16.
03

Set a quality floor

Compression is what makes OpenPhenom-S/16 fit smaller cards, at some cost in accuracy — Q8_0 on the smallest card that fits. A minimum quality removes the ones that go too far.
04

Compare tokens per second, not specifications

Ranking by tokens per second for OpenPhenom-S/16 follows memory bandwidth, not core counts, which is why the B200 tops it at 19,030 tok/s.
05

Read the fit column last

The fit column separates cards that just manage OpenPhenom-S/16 from those with room to spare. Buy for the second if the context might grow.
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 OpenPhenom-S/16.

Answers

OpenPhenom-S/16 — common questions

How much compute was used to train OpenPhenom-S/16?

Around 3.2 × 10¹⁹ 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 OpenPhenom-S/16 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. Our figures for OpenPhenom-S/16 assume it is fully resident.

Would two GPUs run OpenPhenom-S/16 faster?

Capacity adds across cards; throughput does not. Since 818 of the cards we track already hold OpenPhenom-S/16 on their own, a second card is rarely the answer here.

Why does the quantisation differ between cards for OpenPhenom-S/16?

Because capacity varies, so does how hard OpenPhenom-S/16 has to be squeezed — 1 distinct levels appear in the table above. Set a minimum quality to compare at one.

How accurate are these OpenPhenom-S/16 speed estimates?

They are calculated from specifications rather than measured, and each carries a range — 11,418–30,448 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 OpenPhenom-S/16?

The smallest card in our catalogue that holds OpenPhenom-S/16 is the Tesla C1080, with 4 GB of memory. It runs the model at Q8_0 using about 0.9 GB, and produces roughly 207 tokens per second. 818 cards in total can run it.

How fast is OpenPhenom-S/16 on a GPU?

It depends on the card. The quickest we calculate is a B200 at about 19,030 tokens per second; the slowest that still runs it manages considerably less. Reading speed is around ten tokens per second, and 818 of the cards that can run OpenPhenom-S/16 clear that.

How much VRAM does OpenPhenom-S/16 need?

About 0.9 GB at Q8_0 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 OpenPhenom-S/16 on a 8 GB GPU?

Yes. A CMP 170HX 8 GB with 8 GB runs it at Q8_0, using about 0.9 GB and generating roughly 3,544 tokens per second — a comfortable fit.

Can I run OpenPhenom-S/16 on a 12 GB GPU?

Yes. A GeForce RTX 3080 Ti with 12 GB runs it at Q8_0, using about 0.9 GB and generating roughly 2,170 tokens per second — a comfortable fit.

Can I run OpenPhenom-S/16 on a 16 GB GPU?

Yes. A Tesla V100 SXM2 16 GB with 16 GB runs it at Q8_0, using about 0.9 GB and generating roughly 2,688 tokens per second — a comfortable fit.

Can I run OpenPhenom-S/16 on a 24 GB GPU?

Yes. A GeForce RTX 5090 D V2 with 24 GB runs it at Q8_0, using about 0.9 GB and generating roughly 3,188 tokens per second — a comfortable fit.

Is OpenPhenom-S/16 open source?

Its weights are published, so OpenPhenom-S/16 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 OpenPhenom-S/16 have?

OpenPhenom-S/16 has 178M parameters. Checked using HuggingFace Library API. 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 OpenPhenom-S/16?

OpenPhenom-S/16 was published by Recursion Pharmaceuticals, based in United States of America, categorised as industry.

When was OpenPhenom-S/16 released?

OpenPhenom-S/16 was published in November 2024. 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 OpenPhenom-S/16 used for?

OpenPhenom-S/16 works in Biology, Vision, and is recorded as handling image embedding. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.

Where can I download OpenPhenom-S/16?

The weights for OpenPhenom-S/16 are published, though we do not hold a repository link for it. This site calculates hardware requirements rather than hosting model files.

Source

Original publication

Record last updated 28 November 2025

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