BLOOM-1.7B TPS calculator

Open weights Hugging Face,BigScience 1.7B 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

818 cards that can run it

818 cards we hold specifications for

Smallest card that fits

Tesla C1080

4 GB · Q8_0 · 21.7 tok/s

Fastest card

B200

1,993 tok/s · 180 GB

Which GPUs can run BLOOM-1.7B?

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

818 cards match

Calculating

					Needs	Quantisation	Fit
1,993 tok/s 1,196–3,189 · low confidence	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	2.5 GB	Q8_0	Comfortable
1,993 tok/s 1,196–3,189 · low confidence	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	2.5 GB	Q8_0	Comfortable
1,592 tok/s 955–2,546 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	2.5 GB	Q8_0	Comfortable
1,592 tok/s 955–2,546 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	2.5 GB	Q8_0	Comfortable
1,273 tok/s 764–2,037 · low confidence	Radeon Instinct MI300 AMD	128 GB	6,550 GB/s	Jan 2023	2.5 GB	Q8_0	Comfortable
1,218 tok/s 731–1,949 · low confidence	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	2.5 GB	Q8_0	Comfortable
1,218 tok/s 731–1,949 · low confidence	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	2.5 GB	Q8_0	Comfortable
1,166 tok/s 700–1,866 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	2.5 GB	Q8_0	Comfortable
1,035 tok/s 621–1,656 · low confidence	Radeon Instinct MI300A AMD	128 GB	5,325 GB/s	Dec 2023	2.5 GB	Q8_0	Comfortable
1,035 tok/s 621–1,656 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	2.5 GB	Q8_0	Comfortable
1,035 tok/s 621–1,656 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	2.5 GB	Q8_0	Comfortable
982 tok/s 589–1,571 · low confidence	H100 NVL 94 GB NVIDIA	94 GB	3,940 GB/s	Mar 2023	2.5 GB	Q8_0	Comfortable
837 tok/s 502–1,339 · low confidence	H100 PCIe 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	2.5 GB	Q8_0	Comfortable
837 tok/s 502–1,339 · low confidence	H100 SXM5 80 GB NVIDIA	80 GB	3,360 GB/s	Oct 2022	2.5 GB	Q8_0	Comfortable
837 tok/s 502–1,339 · low confidence	H100 SXM5 94 GB NVIDIA	94 GB	3,360 GB/s	Mar 2023	2.5 GB	Q8_0	Comfortable
837 tok/s 502–1,339 · low confidence	H100 SXM5 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	2.5 GB	Q8_0	Comfortable
837 tok/s 502–1,339 · low confidence	H800 SXM5 NVIDIA	80 GB	3,360 GB/s	Mar 2023	2.5 GB	Q8_0	Comfortable
637 tok/s 382–1,020 · low confidence	Radeon Instinct MI250 AMD	128 GB	3,280 GB/s	Nov 2021	2.5 GB	Q8_0	Comfortable
637 tok/s 382–1,020 · low confidence	Radeon Instinct MI250X AMD	128 GB	3,280 GB/s	Nov 2021	2.5 GB	Q8_0	Comfortable
531 tok/s 319–850 · low confidence	Data Center GPU Max 1550 Intel	128 GB	3,280 GB/s	Jan 2023	2.5 GB	Q8_0	Comfortable
520 tok/s 312–832 · low confidence	Data Center GPU Max Subsystem Intel	128 GB	3,210 GB/s	Jan 2023	2.5 GB	Q8_0	Comfortable
508 tok/s 305–813 · low confidence	A100 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Nov 2020	2.5 GB	Q8_0	Comfortable
508 tok/s 305–813 · low confidence	A100X NVIDIA	80 GB	2,040 GB/s	Jun 2021	2.5 GB	Q8_0	Comfortable
508 tok/s 305–813 · low confidence	A800 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Aug 2022	2.5 GB	Q8_0	Comfortable
508 tok/s 305–813 · low confidence	H100 CNX NVIDIA	80 GB	2,040 GB/s	Mar 2023	2.5 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: 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

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: 1.7B
Training data: 354,000,000,000 tokens
Epochs: 1

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

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-1.7B

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-1.7B

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 BLOOM-1.7B

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

Hardware requirements in practice

Minimum card

Tesla C1080

Memory needed

2.5 GB

Fastest

1,993 tok/s

BLOOM-1.7B is small enough at 1.7B 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 21.7 tokens per second.

The quickest result comes from a B200 at around 1,993 tokens per second — its 8,000 GB/s of bandwidth is what buys that.

Background

BLOOM-1.7B was published by Hugging Face,BigScience, in United States of America, in July 2022. industry,Research collective is the category the publisher falls under.

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

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 56.0 tokens per second; 792 cards produce text faster than most people read it.

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

Without the attention layout on record, the memory column is an approximation. It is close enough to choose hardware by, and least reliable at long context.

What went into building it

The training set ran to roughly 354,000,000,000 tokens.

Step by step

How to choose a GPU for BLOOM-1.7B

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

Look at what BLOOM-1.7B actually needs — around 2.5 GB at Q8_0. No amount of processing power compensates for a card that cannot hold it.
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 BLOOM-1.7B 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 BLOOM-1.7B by squeezing it further than you would want.
04

Rank by throughput rather than spec sheet

Ranking by tokens per second for BLOOM-1.7B follows memory bandwidth, not core counts, which is why the B200 tops it at 1,993 tok/s.
05

Check the fit verdict before buying

The fit column separates cards that just manage BLOOM-1.7B 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 BLOOM-1.7B is settled.

Answers

BLOOM-1.7B — common questions

How much VRAM does BLOOM-1.7B need?

About 2.5 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 BLOOM-1.7B on a 8 GB GPU?

Yes. A CMP 170HX 8 GB with 8 GB runs it at Q8_0, using about 2.5 GB and generating roughly 371 tokens per second — a comfortable fit.

Can I run BLOOM-1.7B on a 12 GB GPU?

Yes. A GeForce RTX 3080 Ti with 12 GB runs it at Q8_0, using about 2.5 GB and generating roughly 227 tokens per second — a comfortable fit.

Can I run BLOOM-1.7B on a 16 GB GPU?

Yes. A Tesla V100 SXM2 16 GB with 16 GB runs it at Q8_0, using about 2.5 GB and generating roughly 282 tokens per second — a comfortable fit.

Can I run BLOOM-1.7B on a 24 GB GPU?

Yes. A GeForce RTX 5090 D V2 with 24 GB runs it at Q8_0, using about 2.5 GB and generating roughly 334 tokens per second — a comfortable fit.

Is BLOOM-1.7B open source?

Its weights are published, so BLOOM-1.7B 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 BLOOM-1.7B have?

BLOOM-1.7B has 1.7B 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 BLOOM-1.7B?

BLOOM-1.7B was published by Hugging Face,BigScience, based in United States of America, categorised as industry,Research collective.

When was BLOOM-1.7B released?

BLOOM-1.7B 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.

What is BLOOM-1.7B used for?

BLOOM-1.7B works in Language, and is recorded as handling language modeling/generation. 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 BLOOM-1.7B?

The weights for BLOOM-1.7B are published, though we do not hold a repository link for it. This site calculates hardware requirements rather than hosting model files.

Can I run BLOOM-1.7B if it does not fit in my GPU?

It can be split between the card and system memory, but BLOOM-1.7B generates painfully slowly that way. Nothing on this page assumes offloading.

Would two GPUs run BLOOM-1.7B faster?

Capacity adds across cards; throughput does not. Since 818 of the cards we track already hold BLOOM-1.7B on their own, a second card is rarely the answer here.

Why does the quantisation differ between cards for BLOOM-1.7B?

Because capacity varies, so does how hard BLOOM-1.7B has to be squeezed — 1 distinct levels appear in the table above. Set a minimum quality to compare at one.

How accurate are these BLOOM-1.7B speed estimates?

These are estimates with real error bars. The fastest result here, 1,196–3,189 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 BLOOM-1.7B?

The smallest card in our catalogue that holds BLOOM-1.7B is the Tesla C1080, with 4 GB of memory. It runs the model at Q8_0 using about 2.5 GB, and produces roughly 21.7 tokens per second. 818 cards in total can run it.

How fast is BLOOM-1.7B on a GPU?

It depends on the card. The quickest we calculate is a B200 at about 1,993 tokens per second; the slowest that still runs it manages considerably less. Reading speed is around ten tokens per second, and 792 of the cards that can run BLOOM-1.7B clear that.

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