BLOOM-176B TPS calculator

Open weights Hugging Face,BigScience 176.2B 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

17 cards that can run it

818 cards we hold specifications for

Smallest card that fits

Radeon Instinct MI250

128 GB · Q4_K_M · 14.2 tok/s

Fastest card

Radeon Instinct MI300

28.3 tok/s · 128 GB

Which GPUs can run BLOOM-176B?

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

17 cards match

Calculating

					Needs	Quantisation	Fit
28.3 tok/s 17–45 · low confidence	Radeon Instinct MI300 AMD	128 GB	6,550 GB/s	Jan 2023	107.3 GB	Q4_K_M	Tight
27.9 tok/s 17–45 · low confidence	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	148.4 GB	Q6_K	Tight
27.1 tok/s 16–43 · low confidence	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	107.3 GB	Q4_K_M	Tight
27.1 tok/s 16–43 · low confidence	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	107.3 GB	Q4_K_M	Tight
23.0 tok/s 14–37 · low confidence	Radeon Instinct MI300A AMD	128 GB	5,325 GB/s	Dec 2023	107.3 GB	Q4_K_M	Tight
19.2 tok/s 12–31 · low confidence	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	189.4 GB	Q8_0	Comfortable
15.4 tok/s 9–25 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	189.4 GB	Q8_0	Comfortable
15.4 tok/s 9–25 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	189.4 GB	Q8_0	Comfortable
14.5 tok/s 9–23 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	148.4 GB	Q6_K	Tight
14.5 tok/s 9–23 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	148.4 GB	Q6_K	Tight
14.2 tok/s 9–23 · low confidence	Radeon Instinct MI250 AMD	128 GB	3,280 GB/s	Nov 2021	107.3 GB	Q4_K_M	Tight
14.2 tok/s 9–23 · low confidence	Radeon Instinct MI250X AMD	128 GB	3,280 GB/s	Nov 2021	107.3 GB	Q4_K_M	Tight
11.8 tok/s 7–19 · low confidence	Data Center GPU Max 1550 Intel	128 GB	3,280 GB/s	Jan 2023	107.3 GB	Q4_K_M	Tight
11.6 tok/s 7–19 · low confidence	Data Center GPU Max Subsystem Intel	128 GB	3,210 GB/s	Jan 2023	107.3 GB	Q4_K_M	Tight
11.3 tok/s 7–18 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	189.4 GB	Q8_0	Comfortable
1.5 tok/s 1–2 · low confidence	GB10 NVIDIA	128 GB	273 GB/s	Oct 2025	107.3 GB	Q4_K_M	Tight
1.5 tok/s 1–2 · low confidence	Jetson T5000 NVIDIA	128 GB	273 GB/s	Aug 2025	107.3 GB	Q4_K_M	Tight

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: 11 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, Translation, Code generation
Approach: Self-supervised learning
Numerical format: BF16

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: 176.2B
Training data: 379,000,000,000 tokens
Epochs: 1
Batch size: 4,194,304

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: 3.7 × 10²³ FLOP
How it was established: 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 SXM4 80 GB
Chips used: 384
Chip-hours: 1,078,272
Wall-clock time: 2,808 hours (117 days)
Hardware utilisation: HFU 50.0%
Power draw: 308.0 kW
Compute cost: $995,819

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.

Foundation model: Yes
Likely above 10²³ FLOP: Yes
Why it is tracked: Historical significance,Highly cited
Record confidence: Confident
Citations: 2,917

Sources

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

Reference: BLOOM: A 176B-Parameter Open-Access Multilingual Language Model
Last updated: 25 May 2026

The extremes

The ten fastest GPUs that run BLOOM-176B

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-176B

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

Radeon Instinct MI250

Memory needed

107.3 GB

Fastest

28.3 tok/s

BLOOM-176B reaches a parameter count of 176.2B. That puts it above consumer hardware, into the range where a card is bought for this purpose rather than repurposed for it. The number of cards we track that can hold it: 17.

The entry point is Radeon Instinct MI250, with a memory capacity of 128 GB, running it at a compression of Q4_K_M and producing around 14.2 tokens per second.

The fastest we calculate for it is Radeon Instinct MI300, generating roughly 28.3 tokens per second on the strength of a memory bandwidth of 6,550 GB/s.

About this model

BLOOM-176B 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, Translation, Code generation.

Because its weights were released, nothing about running it depends on a provider staying available — it is yours once downloaded.

How fast it runs, and why

Half the cards that hold it manage more than 14.5 tokens per second. Exceeding reading speed outright: 15 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.

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

Producing it required arithmetic totalling around 3.7 × 10²³ FLOP, on hardware recorded as NVIDIA A100 SXM4 80 GB. That figure measures what producing the model cost, and has no bearing on how fast it answers.

The training set ran to roughly 379,000,000,000 tokens of text.

The reason it appears in this catalogue at all: historical significance,Highly cited.

Step by step

How to choose a GPU for BLOOM-176B

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

Start from what it actually needs, which is the requirement of BLOOM-176B, needing around 107.3 GB at a compression of Q4_K_M. No amount of processing power compensates for a card that cannot hold it.
02

Match the context to your actual use

Set the context to what you will actually use. The cache grows with the conversation, and it is the usual reason a card that seemed fine stops fitting BLOOM-176B.
03

Choose how far you will compress it

Compression is what makes a model fit smaller cards, at some cost in accuracy, reaching a compression of Q4_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

Sort by speed

Ranking by tokens per second follows memory bandwidth rather than core counts, for BLOOM-176B. It will not match a gaming ordering, because generation is bound by memory bandwidth. The card topping the list is Radeon Instinct MI300, at 28.3 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-176B. 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

See what else that card runs

Each card page repeats this sweep for every model we hold, answering what else the hardware is good for beyond BLOOM-176B.

Answers

BLOOM-176B — common questions

BLOOM-176B— how accurate are these speed estimates?

These are estimates with real error bars, and any of them could reasonably land anywhere in its published range depending on which runtime you use. The fastest result here: 17–45 tok/s on Radeon Instinct MI300. The same model and card vary by thirty to fifty per cent depending on the inference software and its version.

BLOOM-176B— what GPU do I need to run it?

The smallest card in our catalogue that holds it is Radeon Instinct MI250, with a memory capacity of 128 GB. It runs the model at a compression of Q4_K_M using about 107.3 GB, and produces roughly 14.2 tokens per second. The number of cards able to run it in total: 17.

BLOOM-176B— how fast is it on a GPU?

It depends on the card. The quickest we calculate is Radeon Instinct MI300, at about 28.3 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: 15.

BLOOM-176B— how much VRAM does it need?

It needs about 107.3 GB at a compression of Q4_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-176B— 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-176B— how many parameters does it have?

It has a parameter count of 176.2B. See "Technical Specifications" on Hugging Face: https://huggingface.co/bigscience/bloom. 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-176B— who created it?

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

BLOOM-176B— 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-176B— what is it used for?

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

BLOOM-176B— where can I download it?

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

BLOOM-176B— how much compute was used to train it?

Training consumed around 3.7 × 10²³ FLOP, on hardware recorded as NVIDIA A100 SXM4 80 GB. 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-176B— can I run it if it does not fit in my GPU?

Only by offloading, which is usually a false economy: the part held in system memory drags the whole thing down. The nearest miss we calculate falls short by 20.9 GB. Every figure here assumes the whole model is resident on the card.

BLOOM-176B— would two GPUs run it faster?

Capacity adds across cards; throughput does not. The number of cards already holding it on their own: 17. So a second card is rarely the answer here.

BLOOM-176B— why does the quantisation differ between cards?

A larger card holds a more accurate copy. The number of compression levels used across the cards that run it: 3. Bigger cards get the more accurate version, and the quality floor above pins the comparison to one level.

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