BLOOM-7.1B TPS calculator

Open weights Hugging Face,BigScience 7.1B parameters July 2022

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 · 28.6 tok/s

Fastest card

B200

479 tok/s · 180 GB

Which GPUs can run BLOOM-7.1B?

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
479 tok/s 288–767 · low confidence	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	8.3 GB	Q8_0	Comfortable
479 tok/s 288–767 · low confidence	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	8.3 GB	Q8_0	Comfortable
383 tok/s 230–612 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	8.3 GB	Q8_0	Comfortable
383 tok/s 230–612 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	8.3 GB	Q8_0	Comfortable
306 tok/s 184–490 · low confidence	Radeon Instinct MI300 AMD	128 GB	6,550 GB/s	Jan 2023	8.3 GB	Q8_0	Comfortable
293 tok/s 176–469 · low confidence	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	8.3 GB	Q8_0	Comfortable
293 tok/s 176–469 · low confidence	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	8.3 GB	Q8_0	Comfortable
280 tok/s 168–449 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	8.3 GB	Q8_0	Comfortable
249 tok/s 149–398 · low confidence	Radeon Instinct MI300A AMD	128 GB	5,325 GB/s	Dec 2023	8.3 GB	Q8_0	Comfortable
249 tok/s 149–398 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	8.3 GB	Q8_0	Comfortable
249 tok/s 149–398 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	8.3 GB	Q8_0	Comfortable
236 tok/s 142–378 · low confidence	H100 NVL 94 GB NVIDIA	94 GB	3,940 GB/s	Mar 2023	8.3 GB	Q8_0	Comfortable
201 tok/s 121–322 · low confidence	H100 PCIe 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	8.3 GB	Q8_0	Comfortable
201 tok/s 121–322 · low confidence	H100 SXM5 80 GB NVIDIA	80 GB	3,360 GB/s	Oct 2022	8.3 GB	Q8_0	Comfortable
201 tok/s 121–322 · low confidence	H100 SXM5 94 GB NVIDIA	94 GB	3,360 GB/s	Mar 2023	8.3 GB	Q8_0	Comfortable
201 tok/s 121–322 · low confidence	H100 SXM5 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	8.3 GB	Q8_0	Comfortable
201 tok/s 121–322 · low confidence	H800 SXM5 NVIDIA	80 GB	3,360 GB/s	Mar 2023	8.3 GB	Q8_0	Comfortable
153 tok/s 92–245 · low confidence	Radeon Instinct MI250 AMD	128 GB	3,280 GB/s	Nov 2021	8.3 GB	Q8_0	Comfortable
153 tok/s 92–245 · low confidence	Radeon Instinct MI250X AMD	128 GB	3,280 GB/s	Nov 2021	8.3 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 77–204 · low confidence	Data Center GPU Max 1550 Intel	128 GB	3,280 GB/s	Jan 2023	8.3 GB	Q8_0	Comfortable
125 tok/s 75–200 · low confidence	Data Center GPU Max Subsystem Intel	128 GB	3,210 GB/s	Jan 2023	8.3 GB	Q8_0	Comfortable
122 tok/s 73–196 · low confidence	A100 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Nov 2020	8.3 GB	Q8_0	Comfortable
122 tok/s 73–196 · low confidence	A100X NVIDIA	80 GB	2,040 GB/s	Jun 2021	8.3 GB	Q8_0	Comfortable
122 tok/s 73–196 · low confidence	A800 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Aug 2022	8.3 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: Hugging Face,BigScience
Organisation type: Industry,Research collective
Country: United States of America, France
Published: 5 July 2022
Authors: Margaret Mitchell, Giada Pistilli, Yacine Jernite, Ezinwanne Ozoani, Marissa Gerchick, Nazneen Rajani, Sasha Luccioni, Irene Solaiman, Maraim Masoud, Somaieh Nikpoor, Carlos Muñoz Ferrandis, Stas Bekman, Christopher Akiki, Danish Contractor, David Lansky, Angelina McMillan-Major, Tristan Thrush, Suzana Ilić, Gérard Dupont, Shayne Longpre, Manan Dey, Stella Biderman, Douwe Kiela, Emi Baylor, Teven …

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

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: 7.1B
Training data: 354,000,000,000 tokens
Epochs: 1

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: 1.5 × 10²² FLOP
How it was established: Operation counting

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 (restricted use)
Training code: Unreleased
Hugging Face: bigscience

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: 2,917
Benchmark data: BLOOM-7.1B

Sources

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

Reference: BigScience Language Open-science Open-access Multilingual (BLOOM) Language Model
Last updated: 25 May 2026

The extremes

The ten fastest GPUs that run BLOOM-7.1B

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 BLOOM-7.1B

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

4.2 GB

Fastest

479 tok/s

BLOOM-7.1B reaches a parameter count of 7.1B. That is small enough that hardware is rarely the obstacle, including on cards several years old. The number of cards we track that can run it: 589.

The least hardware that works is Tesla K20c, with a memory capacity of 5 GB, running it at a compression of Q3_K_M and producing around 28.6 tokens per second.

The quickest result comes from B200, generating roughly 479 tokens per second on the strength of a memory bandwidth of 8,000 GB/s.

Background

BLOOM-7.1B was published by Hugging Face,BigScience, in the country recorded as United States of America, during July 2022. The publishing organisation is categorised as industry,Research collective.

It works in the domain of Language, and is recorded as performing the task of language modeling/generation, Translation.

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. On Hugging Face it is published under the organisation bigscience.

Reading the throughput figures

Half the cards that hold it manage more than 25.9 tokens per second. Exceeding reading speed outright: 559 of them.

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.

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

Producing it required arithmetic totalling around 1.5 × 10²² FLOP. That figure measures what producing the model cost, and has no bearing on how fast it answers.

It was trained on a corpus of about 354,000,000,000 tokens of text.

Step by step

How to choose a GPU for BLOOM-7.1B

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

The table lists every card able to hold BLOOM-7.1B, needing around 4.2 GB at a compression of Q3_K_M. No amount of processing power compensates for a card that cannot hold it.
02

Match the context to your actual use

The conversation occupies memory too, and grows as it goes. Set the slider to the length you expect, because at long context a card that handles short questions easily can be dropped by BLOOM-7.1B.
03

Decide how much compression you will accept

Each card runs the least-compressed copy it can hold, reaching a compression of Q3_K_M on the smallest card that fits. Setting a minimum quality drops the cards that only manage it by squeezing further than you would want, and holds the comparison at one level.
04

Compare tokens per second, not specifications

The speed ordering is effectively an ordering by memory bandwidth, for BLOOM-7.1B. It will not match a gaming ordering, because generation is bound by memory bandwidth. The card topping the list is B200, at 479 tok/s.
05

Look at the headroom, not just the fit

A tight fit runs, but leaves nothing spare for a longer conversation, in the case of BLOOM-7.1B. Comfortable means you can grow the context later. That difference matters more than a few tokens per second, so buy for comfortable if you expect to.
06

Open the card you have settled on

Every card name links to its own page, which runs the same calculation across the whole model catalogue. A card is usually bought for more than one model, so it is worth a look before buying for BLOOM-7.1B.

Answers

BLOOM-7.1B — common questions

BLOOM-7.1B— when was it released?

It was published in July 2022. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.

BLOOM-7.1B— what is it used for?

It works in the domain of Language, and is recorded as handling the task of language modeling/generation, Translation. These are the areas it was designed around; they describe intent rather than a hard boundary.

BLOOM-7.1B— where can I download it?

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

BLOOM-7.1B— how much compute was used to train it?

Training consumed around 1.5 × 10²² FLOP. 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.

BLOOM-7.1B— can I run it if it does not fit in my GPU?

It can be split between the card and system memory, but it generates painfully slowly that way. The nearest miss we calculate falls short by 1.4 GB. Every figure here assumes the whole model is resident on the card.

BLOOM-7.1B— would two GPUs run it faster?

Capacity adds across cards; throughput does not. The number of cards already holding it on their own: 589. So a second card is rarely the answer here.

BLOOM-7.1B— why does the quantisation differ between cards?

Each card is shown running the least-compressed copy it can hold. The number of distinct compression levels across the cards that fit it: 4. Bigger cards get the more accurate version, and the quality floor above pins the comparison to one level.

BLOOM-7.1B— how accurate are these speed estimates?

They are calculated from specifications rather than measured, and each carries a range. One example: 288–767 tok/s on B200. The same model and card vary by thirty to fifty per cent depending on the inference software and its version.

BLOOM-7.1B— what GPU do I need to run it?

The smallest card in our catalogue that holds it is Tesla K20c, with a memory capacity of 5 GB. It runs the model at a compression of Q3_K_M using about 4.2 GB, and produces roughly 28.6 tokens per second. The number of cards able to run it in total: 589.

BLOOM-7.1B— how fast is it on a GPU?

It depends on the card. The quickest we calculate is B200, at about 479 tokens per second; the slowest that still runs it manages considerably less. Reading speed is around ten tokens per second, and the number of cards clearing that: 559.

BLOOM-7.1B— how much VRAM does it need?

It needs about 4.2 GB at a compression of Q3_K_M, 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.

BLOOM-7.1B— can I run it on a GPU holding 8 GB?

Yes. The card CMP 170HX 8 GB, holding 8 GB, runs it at a compression of Q6_K, using about 6.6 GB and generating roughly 130 tokens per second. The fit is tight.

BLOOM-7.1B— can I run it on a GPU holding 12 GB?

Yes. The card GeForce RTX 3080 Ti, holding 12 GB, runs it at a compression of Q8_0, using about 8.3 GB and generating roughly 54.7 tokens per second. The fit is comfortable.

BLOOM-7.1B— can I run it on a GPU holding 16 GB?

Yes. The card Tesla V100 SXM2 16 GB, holding 16 GB, runs it at a compression of Q8_0, using about 8.3 GB and generating roughly 67.7 tokens per second. The fit is comfortable.

BLOOM-7.1B— can I run it on a GPU holding 24 GB?

Yes. The card GeForce RTX 5090 D V2, holding 24 GB, runs it at a compression of Q8_0, using about 8.3 GB and generating roughly 80.3 tokens per second. The fit is comfortable.

BLOOM-7.1B— is it open source?

Its weights are published, so it 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.

BLOOM-7.1B— how many parameters does it have?

It has a parameter count of 7.1B. 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.

BLOOM-7.1B— who created it?

It was published by Hugging Face,BigScience, based in United States of America, an organisation categorised as industry,Research collective.

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