BLOOMZ-176B TPS calculator

Open weights Hugging Face 176B parameters November 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

28.4 tok/s · 128 GB

Which GPUs can run BLOOMZ-176B?

Set the inputs, read the answer

A longer conversation needs more memory, which can push this model off smaller cards.

Hides cards that would only fit the model by compressing it below this point.

17 cards match

Calculating
Needs Quantisation Fit
28.4 tok/s

17–45 · low confidence

Radeon Instinct MI300 AMD 128 GB 6,550 GB/s Jan 2023 107.2 GB Q4_K_M Tight
28.0 tok/s

17–45 · low confidence

B200 NVIDIA 180 GB 8,000 GB/s Jan 2024 148.2 GB Q6_K Tight
27.2 tok/s

16–43 · low confidence

H200 NVL NVIDIA 141 GB 4,890 GB/s Nov 2024 107.2 GB Q4_K_M Tight
27.2 tok/s

16–43 · low confidence

H200 SXM 141 GB NVIDIA 141 GB 4,890 GB/s Nov 2024 107.2 GB Q4_K_M Tight
23.1 tok/s

14–37 · low confidence

Radeon Instinct MI300A AMD 128 GB 5,325 GB/s Dec 2023 107.2 GB Q4_K_M Tight
19.3 tok/s

12–31 · low confidence

B300 NVIDIA 288 GB 8,000 GB/s Sep 2025 189.1 GB Q8_0 Comfortable
15.4 tok/s

9–25 · low confidence

Radeon Instinct MI350X AMD 288 GB 8,190 GB/s Jan 2025 189.1 GB Q8_0 Comfortable
15.4 tok/s

9–25 · low confidence

Radeon Instinct MI355X AMD 288 GB 8,190 GB/s Jan 2025 189.1 GB Q8_0 Comfortable
14.5 tok/s

9–23 · low confidence

Radeon Instinct MI300X AMD 192 GB 5,325 GB/s Dec 2023 148.2 GB Q6_K Tight
14.5 tok/s

9–23 · low confidence

Radeon Instinct MI308X AMD 192 GB 5,325 GB/s Dec 2023 148.2 GB Q6_K Tight
14.2 tok/s

9–23 · low confidence

Radeon Instinct MI250 AMD 128 GB 3,280 GB/s Nov 2021 107.2 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 107.2 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 107.2 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 107.2 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 189.1 GB Q8_0 Comfortable
1.5 tok/s

1–2 · low confidence

GB10 NVIDIA 128 GB 273 GB/s Oct 2025 107.2 GB Q4_K_M Tight
1.5 tok/s

1–2 · low confidence

Jetson T5000 NVIDIA 128 GB 273 GB/s Aug 2025 107.2 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
Organisation type
Industry
Country
United States of America
Published
3 November 2022
Authors
Niklas Muennighoff, Thomas Wang, Lintang Sutawika, Adam Roberts, Stella Biderman, Teven Le Scao, M Saiful Bari, Sheng Shen, Zheng-Xin Yong, Hailey Schoelkopf, Xiangru Tang, Dragomir Radev, Alham Fikri Aji, Khalid Almubarak, Samuel Albanie, Zaid Alyafeai, Albert Webson, Edward Raff, Colin Raffel

What it does

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

Domain
Language
Task
Translation, Language modeling/generation
Base model
BLOOM-176B

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
176B

176B

Training data
20,000,000,000 tokens

per https://huggingface.co/datasets/bigscience/xP3, 94,941,936 KB or 94GB if approx 200M words per GB, that's ~20B words (rougher estimate because it's multilingual) https://docs.google.com/document/d/1G3vvQkn4x_W71MKg0GmHVtzfd9m0y3_Ofcoew0v902Q/edit#heading=h.ieihc08p8dn0

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.

Fine-tuning compute
1.4 × 10²² FLOP

"We use publicly available pretrained BLOOM models ranging from 560 million to 176 billion parameters. BLOOM models are large decoder-only language models pretrained for around 350 billion tokens with an architecture similar to GPT-3 (Brown et al., 2020). We finetune the models for an additional 13 billion tokens with loss only being computed on target tokens." 13B * 176B * 6

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
Open source

Apache 2.0 train/eval code: https://github.com/bigscience-workshop/xmtf?tab=readme-ov-file#train-models weights: https://huggingface.co/bigscience/bloomz

How it is classified

Labels the source dataset applies when tracking notable models, and how confident it is in the entry.

Record confidence
Likely
Citations
242

Sources

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

Reference
Crosslingual Generalization through Multitask Finetuning
Last updated
28 November 2025

The extremes

The ten fastest GPUs that run BLOOMZ-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.

  1. 01 Radeon Instinct MI300 128 GB · 6,550 GB/s · Q4_K_M 28.4 tok/s
  2. 02 B200 180 GB · 8,000 GB/s · Q6_K 28.0 tok/s
  3. 03 H200 NVL 141 GB · 4,890 GB/s · Q4_K_M 27.2 tok/s
  4. 04 H200 SXM 141 GB 141 GB · 4,890 GB/s · Q4_K_M 27.2 tok/s
  5. 05 Radeon Instinct MI300A 128 GB · 5,325 GB/s · Q4_K_M 23.1 tok/s
  6. 06 B300 288 GB · 8,000 GB/s · Q8_0 19.3 tok/s
  7. 07 Radeon Instinct MI350X 288 GB · 8,190 GB/s · Q8_0 15.4 tok/s
  8. 08 Radeon Instinct MI355X 288 GB · 8,190 GB/s · Q8_0 15.4 tok/s
  9. 09 Radeon Instinct MI300X 192 GB · 5,325 GB/s · Q6_K 14.5 tok/s
  10. 10 Radeon Instinct MI308X 192 GB · 5,325 GB/s · Q6_K 14.5 tok/s

The smallest GPUs that still run BLOOMZ-176B

The cheapest route in, by memory capacity. A tight fit runs the model but leaves nothing spare for a longer conversation.

  1. 01 GB10 128 GB · needs 107.2 GB · Q4_K_M · tight 1.5 tok/s
  2. 02 Jetson T5000 128 GB · needs 107.2 GB · Q4_K_M · tight 1.5 tok/s
  3. 03 Radeon Instinct MI300A 128 GB · needs 107.2 GB · Q4_K_M · tight 23.1 tok/s
  4. 04 Data Center GPU Max 1550 128 GB · needs 107.2 GB · Q4_K_M · tight 11.8 tok/s
  5. 05 Data Center GPU Max Subsystem 128 GB · needs 107.2 GB · Q4_K_M · tight 11.6 tok/s
  6. 06 Radeon Instinct MI300 128 GB · needs 107.2 GB · Q4_K_M · tight 28.4 tok/s
  7. 07 Radeon Instinct MI250 128 GB · needs 107.2 GB · Q4_K_M · tight 14.2 tok/s
  8. 08 Radeon Instinct MI250X 128 GB · needs 107.2 GB · Q4_K_M · tight 14.2 tok/s
  9. 09 H200 NVL 141 GB · needs 107.2 GB · Q4_K_M · tight 27.2 tok/s
  10. 10 H200 SXM 141 GB 141 GB · needs 107.2 GB · Q4_K_M · tight 27.2 tok/s

What the numbers mean

What it takes to run this model

Minimum card

Radeon Instinct MI250

Memory needed

107.2 GB

Fastest

28.4 tok/s

BLOOMZ-176B sits at 176B parameters, which puts it above consumer hardware and into the range where a card is bought for this purpose rather than repurposed for it. 17 of the cards we track can hold it.

The smallest card that holds it is the Radeon Instinct MI250 with 128 GB, running it at Q4_K_M and producing around 14.2 tokens per second.

A Radeon Instinct MI300 is the fastest we calculate for it: about 28.4 tokens per second, from 6,550 GB/s of memory bandwidth.

Background

BLOOMZ-176B was published by Hugging Face, in United States of America, in November 2022. It comes out of industry.

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

It is derived from BLOOM-176B rather than trained from scratch, which is the usual way a specialised model is produced.

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.

Reading the throughput figures

Half the cards that hold it manage more than 14.5 tokens per second, and 15 exceed reading speed outright.

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

It was trained on about 20,000,000,000 tokens of text.

Step by step

How to choose a GPU for BLOOMZ-176B

The table above has already assessed every card we hold specifications for against this model. Getting to your answer takes six steps.

  1. 01

    Read the memory figure first

    The table lists every card that can hold BLOOMZ-176B — around 107.2 GB at Q4_K_M. That figure, not the card's headline performance, is what decides whether it runs.

  2. 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 BLOOMZ-176B stops fitting a card that seemed fine.

  3. 03

    Decide how much compression you will accept

    Compression is what makes BLOOMZ-176B fit smaller cards, at some cost in accuracy — Q4_K_M on the smallest card that fits. A minimum quality removes the ones that go too far.

  4. 04

    Compare tokens per second, not specifications

    The speed ordering for BLOOMZ-176B is effectively an ordering by memory bandwidth, which is why the Radeon Instinct MI300 tops it at 28.4 tok/s.

  5. 05

    Look at the headroom, not just the fit

    Tight means BLOOMZ-176B 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.

  6. 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 BLOOMZ-176B is settled.

Answers

BLOOMZ-176B — common questions

01

Is BLOOMZ-176B open source?

Its weights are published, so BLOOMZ-176B 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.

02

How many parameters does BLOOMZ-176B have?

BLOOMZ-176B has 176B parameters. 176B. 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.

03

Who created BLOOMZ-176B?

BLOOMZ-176B was published by Hugging Face, based in United States of America, categorised as industry.

04

When was BLOOMZ-176B released?

BLOOMZ-176B was published in November 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.

05

What is BLOOMZ-176B used for?

BLOOMZ-176B works in Language, and is recorded as handling translation, Language modeling/generation. These are the areas it was designed around; they describe intent rather than a hard boundary.

06

Where can I download BLOOMZ-176B?

The weights for BLOOMZ-176B are published, though we do not hold a repository link for it. This site calculates hardware requirements rather than hosting model files.

07

Can I run BLOOMZ-176B if it does not fit in my GPU?

It can be split between the card and system memory, but BLOOMZ-176B generates painfully slowly that way — the nearest miss we calculate is short by 20.8 GB. Nothing on this page assumes offloading.

08

Would two GPUs run BLOOMZ-176B faster?

A second card roughly doubles the memory available but not the generation rate. With 17 cards already able to run BLOOMZ-176B alone, the case for pairing is weak.

09

Why does the quantisation differ between cards for BLOOMZ-176B?

Because capacity varies, so does how hard BLOOMZ-176B has to be squeezed — 3 distinct levels appear in the table above. Set a minimum quality to compare at one.

10

How accurate are these BLOOMZ-176B 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 17–45 tok/s on the Radeon Instinct MI300 rather than a single number.

11

What GPU do I need to run BLOOMZ-176B?

The smallest card in our catalogue that holds BLOOMZ-176B is the Radeon Instinct MI250, with 128 GB of memory. It runs the model at Q4_K_M using about 107.2 GB, and produces roughly 14.2 tokens per second. 17 cards in total can run it.

12

How fast is BLOOMZ-176B on a GPU?

It depends on the card. The quickest we calculate is a Radeon Instinct MI300 at about 28.4 tokens per second; the slowest that still runs it manages considerably less. Reading speed is around ten tokens per second, and 15 of the cards that can run BLOOMZ-176B clear that.

13

How much VRAM does BLOOMZ-176B need?

About 107.2 GB at Q4_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.

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