BLUUMI TPS calculator

Open weights University of Turku,Hugging Face 176B parameters November 2023

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 BLUUMI?

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
28.4 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: University of Turku,Hugging Face
Organisation type: Academia,Industry
Country: Finland, United States of America
Published: 3 November 2023
Authors: Risto Luukkonen, Ville Komulainen, Jouni Luoma, Anni Eskelinen, Jenna Kanerva, Hanna-Mari Kupari, Filip Ginter, Veronika Laippala, Niklas Muennighoff, Aleksandra Piktus, Thomas Wang, Nouamane Tazi, Teven Le Scao, Thomas Wolf, Osma Suominen, Samuli Sairanen, Mikko Merioksa, Jyrki Heinonen, Aija Vahtola, Samuel Antao, Sampo Pyysalo

What it does

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

Domain: Language
Task: Language modeling
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
Training data: 38,000,000,000 tokens
Epochs: 8
Batch size: 4,194,304

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: AMD Radeon Instinct MI250X
Data centre: LUMI Supercomputer

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: TurkuNLP

How it is classified

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

Foundation model: Yes
Why it is tracked: SOTA improvement
Record confidence: Likely
Citations: 70

Sources

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

Reference: FinGPT: Large Generative Models for a Small Language
Last updated: 25 May 2026

The extremes

The ten fastest GPUs that run BLUUMI

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 BLUUMI

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

The hardware side

Minimum card

Radeon Instinct MI250

Memory needed

107.2 GB

Fastest

28.4 tok/s

BLUUMI 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.

At the low end, a Radeon Instinct MI250 handles it — 128 GB, at Q4_K_M, for about 14.2 tokens per second.

The quickest result comes from a Radeon Instinct MI300 at around 28.4 tokens per second — its 6,550 GB/s of bandwidth is what buys that.

About this model

BLUUMI was published by University of Turku,Hugging Face, in Finland, in November 2023. academia,Industry is the category the publisher falls under.

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

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

The weights being open is what puts this page in the calculator rather than only in the catalogue: it is a model you can actually hold. It is published under the TurkuNLP organisation on Hugging Face.

How fast it runs, and why

Across every card that can run it, the middle of the range is about 14.5 tokens per second, and 15 of them clear the ten tokens per second that roughly matches reading speed.

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.

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.

What went into building it

It was trained on about 38,000,000,000 tokens of text.

The reason it appears in this catalogue at all is sOTA improvement.

Step by step

How to choose a GPU for BLUUMI

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 that can hold BLUUMI — around 107.2 GB at Q4_K_M. That figure, not the card's headline performance, is what decides whether it runs.
02

Set the context length you will work at

Longer conversations cost memory on top of what the weights need. Move the slider to your real working length before trusting any row for BLUUMI.
03

Decide how much compression you will accept

Compression is what makes BLUUMI 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.
04

Rank by throughput rather than spec sheet

Ranking by tokens per second for BLUUMI follows memory bandwidth, not core counts, which is why the Radeon Instinct MI300 tops it at 28.4 tok/s.
05

Look at the headroom, not just the fit

The fit column separates cards that just manage BLUUMI from those with room to spare. Buy for the second if the context might grow.
06

Check the card from the other side

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

Answers

BLUUMI — common questions

Can I run BLUUMI if it does not fit in my GPU?

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

Would two GPUs run BLUUMI faster?

Capacity adds across cards; throughput does not. Since 17 of the cards we track already hold BLUUMI on their own, a second card is rarely the answer here.

Why does the quantisation differ between cards for BLUUMI?

A larger card holds a more accurate copy. Across the cards that run BLUUMI, 3 compression levels are used; the floor control above pins it to one.

How accurate are these BLUUMI 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.

What GPU do I need to run BLUUMI?

The smallest card in our catalogue that holds BLUUMI 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.

How fast is BLUUMI 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 BLUUMI clear that.

How much VRAM does BLUUMI 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.

Is BLUUMI open source?

Its weights are published, so BLUUMI 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 BLUUMI have?

BLUUMI has 176B parameters. 176 billion. 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 BLUUMI?

BLUUMI was published by University of Turku,Hugging Face, based in Finland, categorised as academia,Industry.

When was BLUUMI released?

BLUUMI was published in November 2023. 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 BLUUMI used for?

BLUUMI works in Language, and is recorded as handling language modeling. 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 BLUUMI?

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

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