Phi-1 TPS calculator

Open weights Microsoft Research 1.3B parameters October 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

818 of 818 cards that can run it

Smallest card that fits

Tesla C1080

4 GB · Q8_0 · 28.4 tok/s

Fastest card

B200

2,606 tok/s · 180 GB

Which GPUs can run Phi-1?

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
2,606 tok/s 1,564–4,170 · low confidence	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	2.1 GB	Q8_0	Comfortable
2,606 tok/s 1,564–4,170 · low confidence	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	2.1 GB	Q8_0	Comfortable
2,081 tok/s 1,249–3,330 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	2.1 GB	Q8_0	Comfortable
2,081 tok/s 1,249–3,330 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	2.1 GB	Q8_0	Comfortable
1,664 tok/s 999–2,663 · low confidence	Radeon Instinct MI300 AMD	128 GB	6,550 GB/s	Jan 2023	2.1 GB	Q8_0	Comfortable
1,593 tok/s 956–2,549 · low confidence	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	2.1 GB	Q8_0	Comfortable
1,593 tok/s 956–2,549 · low confidence	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	2.1 GB	Q8_0	Comfortable
1,525 tok/s 915–2,440 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	2.1 GB	Q8_0	Comfortable
1,353 tok/s 812–2,165 · low confidence	Radeon Instinct MI300A AMD	128 GB	5,325 GB/s	Dec 2023	2.1 GB	Q8_0	Comfortable
1,353 tok/s 812–2,165 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	2.1 GB	Q8_0	Comfortable
1,353 tok/s 812–2,165 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	2.1 GB	Q8_0	Comfortable
1,284 tok/s 770–2,054 · low confidence	H100 NVL 94 GB NVIDIA	94 GB	3,940 GB/s	Mar 2023	2.1 GB	Q8_0	Comfortable
1,095 tok/s 657–1,751 · low confidence	H100 PCIe 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	2.1 GB	Q8_0	Comfortable
1,095 tok/s 657–1,751 · low confidence	H100 SXM5 80 GB NVIDIA	80 GB	3,360 GB/s	Oct 2022	2.1 GB	Q8_0	Comfortable
1,095 tok/s 657–1,751 · low confidence	H100 SXM5 94 GB NVIDIA	94 GB	3,360 GB/s	Mar 2023	2.1 GB	Q8_0	Comfortable
1,095 tok/s 657–1,751 · low confidence	H100 SXM5 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	2.1 GB	Q8_0	Comfortable
1,095 tok/s 657–1,751 · low confidence	H800 SXM5 NVIDIA	80 GB	3,360 GB/s	Mar 2023	2.1 GB	Q8_0	Comfortable
834 tok/s 500–1,334 · low confidence	Radeon Instinct MI250 AMD	128 GB	3,280 GB/s	Nov 2021	2.1 GB	Q8_0	Comfortable
834 tok/s 500–1,334 · low confidence	Radeon Instinct MI250X AMD	128 GB	3,280 GB/s	Nov 2021	2.1 GB	Q8_0	Comfortable
695 tok/s 417–1,111 · low confidence	Data Center GPU Max 1550 Intel	128 GB	3,280 GB/s	Jan 2023	2.1 GB	Q8_0	Comfortable
680 tok/s 408–1,088 · low confidence	Data Center GPU Max Subsystem Intel	128 GB	3,210 GB/s	Jan 2023	2.1 GB	Q8_0	Comfortable
665 tok/s 399–1,063 · low confidence	A100 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Nov 2020	2.1 GB	Q8_0	Comfortable
665 tok/s 399–1,063 · low confidence	A100X NVIDIA	80 GB	2,040 GB/s	Jun 2021	2.1 GB	Q8_0	Comfortable
665 tok/s 399–1,063 · low confidence	A800 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Aug 2022	2.1 GB	Q8_0	Comfortable
665 tok/s 399–1,063 · low confidence	H100 CNX NVIDIA	80 GB	2,040 GB/s	Mar 2023	2.1 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: Microsoft Research
Organisation type: Industry
Country: United States of America
Published: 2 October 2023
Authors: Suriya Gunasekar, Yi Zhang, Jyoti Aneja, Caio César Teodoro Mendes, Allie Del Giorno, Sivakanth Gopi, Mojan Javaheripi, Piero Kauffmann, Gustavo de Rosa, Olli Saarikivi, Adil Salim, Shital Shah, Harkirat Singh Behl, Xin Wang, Sébastien Bubeck, Ronen Eldan, Adam Tauman Kalai, Yin Tat Lee, Yuanzhi Li

What it does

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

Domain: Language
Task: Language modeling/generation, Code generation

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: 1.3B
Training data: tokens
Epochs: 7.3

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: 3.3 × 10²⁰ FLOP
How it was established: Operation counting,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 A100
Chips used: 8
Wall-clock time: 103 hours
Power draw: 6.4 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 (unrestricted)
Training code: Unreleased
Hugging Face: microsoft

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: Textbooks Are All You Need
Last updated: 28 November 2025

The extremes

The ten fastest GPUs for Phi-1

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 Phi-1

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 you need to run it

Minimum card

Tesla C1080

Memory needed

2.1 GB

Fastest

2,606 tok/s

Phi-1 is small enough at 1.3B parameters that hardware is rarely the obstacle — 818 of the cards we track can run it, including cards several years old.

The least hardware that works is a Tesla C1080. Its 4 GB is enough at Q8_0 compression, giving roughly 28.4 tokens per second.

At the other end, a B200 generates roughly 2,606 tokens per second on it, on the strength of 8,000 GB/s of memory bandwidth.

Where it came from

Phi-1 was published by Microsoft Research, in United States of America, in October 2023. industry is the category the publisher falls under.

It works in Language, and is recorded as doing language modeling/generation, Code generation.

Published weights mean the model runs on your machine rather than someone else's, which is what makes the hardware question below answerable at all. It is published under the microsoft organisation on Hugging Face.

Understanding the speeds

Across every card that can run it, the middle of the range is about 73.2 tokens per second, and 797 of them clear the ten tokens per second that roughly matches reading speed.

Every weight participates in every token here, so bandwidth is the whole story: the ranking below is effectively a ranking of memory throughput.

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 3.3 × 10²⁰ FLOP of computation, on NVIDIA A100 — a measure of what producing the model cost, not of how fast it answers.

Step by step

How to choose a GPU for Phi-1

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

Every card here has been checked against Phi-1 — around 2.1 GB at Q8_0. Capacity is the gate — a card either holds it or it does not.
02

Decide how long your conversations run

The conversation occupies memory too, and grows as it goes. Set the slider to the length you expect: at long context Phi-1 can slip off a card that handles short questions easily.
03

Choose how far you will compress it

Each card runs the least-compressed copy it can hold — Q8_0 on the smallest card that fits. Setting a floor drops the cards that only manage Phi-1 by squeezing it further than you would want.
04

Compare tokens per second, not specifications

Ranking by tokens per second for Phi-1 follows memory bandwidth, not core counts, which is why the B200 tops it at 2,606 tok/s.
05

Check the fit verdict before buying

The fit column separates cards that just manage Phi-1 from those with room to spare. Buy for the second if the context might grow.
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 Phi-1 is settled.

Answers

Phi-1 — common questions

Can I run Phi-1 on a 24 GB GPU?

Yes. A GeForce RTX 5090 D V2 with 24 GB runs it at Q8_0, using about 2.1 GB and generating roughly 437 tokens per second — a comfortable fit.

Is Phi-1 open source?

Its weights are published, so Phi-1 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 Phi-1 have?

Phi-1 has 1.3B parameters. 1.3B The architecture for our 1.3B parameter phi-1 model consists of 24 layers, hidden dimension of 2048, MLP-inner dimension of 8192, and 32 attention heads of dimension 64 each. 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 Phi-1?

Phi-1 was published by Microsoft Research, based in United States of America, categorised as industry.

When was Phi-1 released?

Phi-1 was published in October 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.

What is Phi-1 used for?

Phi-1 works in Language, and is recorded as handling language modeling/generation, Code generation. These are the areas it was designed around; they describe intent rather than a hard boundary.

Where can I download Phi-1?

Its weights are published under the microsoft organisation on Hugging Face. We do not host model files — this site calculates what hardware is needed to run them.

How much compute was used to train Phi-1?

Around 3.3 × 10²⁰ FLOP, on 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.

Can I run Phi-1 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 Phi-1 assume it is fully resident.

Would two GPUs run Phi-1 faster?

A second card roughly doubles the memory available but not the generation rate. With 818 cards already able to run Phi-1 alone, the case for pairing is weak.

Why does the quantisation differ between cards for Phi-1?

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

How accurate are these Phi-1 speed estimates?

Every figure is derived from memory bandwidth and model size, not benchmarked. That is why each is published as a range such as 1,564–4,170 tok/s on the B200 rather than a single number.

What GPU do I need to run Phi-1?

The smallest card in our catalogue that holds Phi-1 is the Tesla C1080, with 4 GB of memory. It runs the model at Q8_0 using about 2.1 GB, and produces roughly 28.4 tokens per second. 818 cards in total can run it.

How fast is Phi-1 on a GPU?

It depends on the card. The quickest we calculate is a B200 at about 2,606 tokens per second; the slowest that still runs it manages considerably less. Reading speed is around ten tokens per second, and 797 of the cards that can run Phi-1 clear that.

How much VRAM does Phi-1 need?

About 2.1 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 Phi-1 on a 8 GB GPU?

Yes. A CMP 170HX 8 GB with 8 GB runs it at Q8_0, using about 2.1 GB and generating roughly 485 tokens per second — a comfortable fit.

Can I run Phi-1 on a 12 GB GPU?

Yes. A GeForce RTX 3080 Ti with 12 GB runs it at Q8_0, using about 2.1 GB and generating roughly 297 tokens per second — a comfortable fit.

Can I run Phi-1 on a 16 GB GPU?

Yes. A Tesla V100 SXM2 16 GB with 16 GB runs it at Q8_0, using about 2.1 GB and generating roughly 368 tokens per second — a comfortable fit.

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