Pharia-1-LLM-7B TPS calculator

Open weights Aleph Alpha 7B parameters August 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

589 cards that can run it

818 cards we hold specifications for

Smallest card that fits

Tesla K20c

5 GB · Q3_K_M · 28.7 tok/s

Fastest card

B200

481 tok/s · 180 GB

Which GPUs can run Pharia-1-LLM-7B?

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

589 cards match

Calculating

					Needs	Quantisation	Fit
481 tok/s 289–770 · low confidence	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	8.2 GB	Q8_0	Comfortable
481 tok/s 289–770 · low confidence	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	8.2 GB	Q8_0	Comfortable
384 tok/s 231–615 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	8.2 GB	Q8_0	Comfortable
384 tok/s 231–615 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	8.2 GB	Q8_0	Comfortable
307 tok/s 184–492 · low confidence	Radeon Instinct MI300 AMD	128 GB	6,550 GB/s	Jan 2023	8.2 GB	Q8_0	Comfortable
294 tok/s 176–471 · low confidence	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	8.2 GB	Q8_0	Comfortable
294 tok/s 176–471 · low confidence	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	8.2 GB	Q8_0	Comfortable
281 tok/s 169–450 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	8.2 GB	Q8_0	Comfortable
250 tok/s 150–400 · low confidence	Radeon Instinct MI300A AMD	128 GB	5,325 GB/s	Dec 2023	8.2 GB	Q8_0	Comfortable
250 tok/s 150–400 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	8.2 GB	Q8_0	Comfortable
250 tok/s 150–400 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	8.2 GB	Q8_0	Comfortable
237 tok/s 142–379 · low confidence	H100 NVL 94 GB NVIDIA	94 GB	3,940 GB/s	Mar 2023	8.2 GB	Q8_0	Comfortable
202 tok/s 121–323 · low confidence	H100 PCIe 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	8.2 GB	Q8_0	Comfortable
202 tok/s 121–323 · low confidence	H100 SXM5 80 GB NVIDIA	80 GB	3,360 GB/s	Oct 2022	8.2 GB	Q8_0	Comfortable
202 tok/s 121–323 · low confidence	H100 SXM5 94 GB NVIDIA	94 GB	3,360 GB/s	Mar 2023	8.2 GB	Q8_0	Comfortable
202 tok/s 121–323 · low confidence	H100 SXM5 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	8.2 GB	Q8_0	Comfortable
202 tok/s 121–323 · low confidence	H800 SXM5 NVIDIA	80 GB	3,360 GB/s	Mar 2023	8.2 GB	Q8_0	Comfortable
154 tok/s 92–246 · low confidence	Radeon Instinct MI250 AMD	128 GB	3,280 GB/s	Nov 2021	8.2 GB	Q8_0	Comfortable
154 tok/s 92–246 · low confidence	Radeon Instinct MI250X AMD	128 GB	3,280 GB/s	Nov 2021	8.2 GB	Q8_0	Comfortable
130 tok/s 78–208 · low confidence	CMP 170HX 8 GB NVIDIA	8 GB	1,490 GB/s	Sep 2021	6.6 GB	Q6_K	Tight
128 tok/s 77–205 · low confidence	Data Center GPU Max 1550 Intel	128 GB	3,280 GB/s	Jan 2023	8.2 GB	Q8_0	Comfortable
126 tok/s 75–201 · low confidence	Data Center GPU Max Subsystem Intel	128 GB	3,210 GB/s	Jan 2023	8.2 GB	Q8_0	Comfortable
123 tok/s 74–196 · low confidence	A100 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Nov 2020	8.2 GB	Q8_0	Comfortable
123 tok/s 74–196 · low confidence	A100X NVIDIA	80 GB	2,040 GB/s	Jun 2021	8.2 GB	Q8_0	Comfortable
123 tok/s 74–196 · low confidence	A800 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Aug 2022	8.2 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: Aleph Alpha
Organisation type: Industry
Country: Germany
Published: 26 August 2024

What it does

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

Domain: Language
Task: Language modeling/generation, Translation, 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: 7B
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: 4.4 × 10²³ FLOP
How it was established: Reported

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 80 GB,NVIDIA H100 SXM5 80GB
Chips used: 256

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)
Training code: Open (non-commercial)
Hugging Face: Aleph-Alpha

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
Record confidence: Confident

Sources

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

Reference: Introducing Pharia-1-LLM: transparent and compliant
Last updated: 28 November 2025

The extremes

The ten fastest GPUs that run Pharia-1-LLM-7B

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 Pharia-1-LLM-7B

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 K20c

Memory needed

4.1 GB

Fastest

481 tok/s

Pharia-1-LLM-7B is small enough at 7B parameters that hardware is rarely the obstacle — 589 of the cards we track can run it, including cards several years old.

The least hardware that works is a Tesla K20c. Its 5 GB is enough at Q3_K_M compression, giving roughly 28.7 tokens per second.

The quickest result comes from a B200 at around 481 tokens per second — its 8,000 GB/s of bandwidth is what buys that.

Where it came from

Pharia-1-LLM-7B was published by Aleph Alpha, in Germany, in August 2024. industry is the category the publisher falls under.

It works in Language, and is recorded as doing language modeling/generation, Translation, Question answering.

Because its weights were released, nothing about running it depends on a provider staying available — it is yours once downloaded. It is published under the Aleph-Alpha organisation on Hugging Face.

Understanding the speeds

Half the cards that hold it manage more than 26.0 tokens per second, and 559 exceed reading speed outright.

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

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.

Training and provenance

The training run consumed about 4.4 × 10²³ FLOP, on NVIDIA A100 SXM4 80 GB,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 Pharia-1-LLM-7B

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

Every card here has been checked against Pharia-1-LLM-7B — around 4.1 GB at Q3_K_M. Capacity is the gate — a card either holds it or it does not.
02

Decide how long your conversations run

Set the context to what you will actually use. The cache grows with the conversation, and it is the usual reason Pharia-1-LLM-7B stops fitting a card that seemed fine.
03

Set a quality floor

The quantisation column varies by card, because a bigger card holds a more accurate copy of Pharia-1-LLM-7B — Q3_K_M on the smallest card that fits. Set a floor to hold the comparison at one level.
04

Sort by speed

The speed ordering for Pharia-1-LLM-7B is effectively an ordering by memory bandwidth, which is why the B200 tops it at 481 tok/s.
05

Read the fit column last

Tight means Pharia-1-LLM-7B 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

Every card name links to its own page, which runs the same calculation across the whole model catalogue. Worth a look before buying for Pharia-1-LLM-7B alone — a card is usually bought for more than one model.

Answers

Pharia-1-LLM-7B — common questions

Can I run Pharia-1-LLM-7B on a 24 GB GPU?

Yes. A GeForce RTX 5090 D V2 with 24 GB runs it at Q8_0, using about 8.2 GB and generating roughly 80.6 tokens per second — a comfortable fit.

Is Pharia-1-LLM-7B open source?

Its weights are published, so Pharia-1-LLM-7B 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 Pharia-1-LLM-7B have?

Pharia-1-LLM-7B has 7B 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 Pharia-1-LLM-7B?

Pharia-1-LLM-7B was published by Aleph Alpha, based in Germany, categorised as industry.

When was Pharia-1-LLM-7B released?

Pharia-1-LLM-7B was published in August 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 Pharia-1-LLM-7B used for?

Pharia-1-LLM-7B works in Language, and is recorded as handling language modeling/generation, Translation, Question answering. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.

Where can I download Pharia-1-LLM-7B?

Its weights are published under the Aleph-Alpha 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 Pharia-1-LLM-7B?

Around 4.4 × 10²³ FLOP, on NVIDIA A100 SXM4 80 GB,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 Pharia-1-LLM-7B if it does not fit in my GPU?

It can be split between the card and system memory, but Pharia-1-LLM-7B generates painfully slowly that way — the nearest miss we calculate is short by 1.4 GB. Nothing on this page assumes offloading.

Would two GPUs run Pharia-1-LLM-7B faster?

Capacity adds across cards; throughput does not. Since 589 of the cards we track already hold Pharia-1-LLM-7B on their own, a second card is rarely the answer here.

Why does the quantisation differ between cards for Pharia-1-LLM-7B?

A larger card holds a more accurate copy. Across the cards that run Pharia-1-LLM-7B, 4 compression levels are used; the floor control above pins it to one.

How accurate are these Pharia-1-LLM-7B 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 289–770 tok/s on the B200 rather than a single number.

What GPU do I need to run Pharia-1-LLM-7B?

The smallest card in our catalogue that holds Pharia-1-LLM-7B is the Tesla K20c, with 5 GB of memory. It runs the model at Q3_K_M using about 4.1 GB, and produces roughly 28.7 tokens per second. 589 cards in total can run it.

How fast is Pharia-1-LLM-7B on a GPU?

It depends on the card. The quickest we calculate is a B200 at about 481 tokens per second; the slowest that still runs it manages considerably less. Reading speed is around ten tokens per second, and 559 of the cards that can run Pharia-1-LLM-7B clear that.

How much VRAM does Pharia-1-LLM-7B need?

About 4.1 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 Pharia-1-LLM-7B on a 8 GB GPU?

Yes. A CMP 170HX 8 GB with 8 GB runs it at Q6_K, using about 6.6 GB and generating roughly 130 tokens per second — a tight fit.

Can I run Pharia-1-LLM-7B on a 12 GB GPU?

Yes. A GeForce RTX 3080 Ti with 12 GB runs it at Q8_0, using about 8.2 GB and generating roughly 54.9 tokens per second — a comfortable fit.

Can I run Pharia-1-LLM-7B on a 16 GB GPU?

Yes. A Tesla V100 SXM2 16 GB with 16 GB runs it at Q8_0, using about 8.2 GB and generating roughly 68.0 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