Falcon-180B TPS calculator

Open weights Technology Innovation Institute 180B parameters September 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 · 13.9 tok/s

Fastest card

Radeon Instinct MI300

27.8 tok/s · 128 GB

Which GPUs can run Falcon-180B?

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
27.8 tok/s 17–44 · low confidence	Radeon Instinct MI300 AMD	128 GB	6,550 GB/s	Jan 2023	109.6 GB	Q4_K_M	Tight
27.4 tok/s 16–44 · low confidence	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	151.5 GB	Q6_K	Tight
26.6 tok/s 16–43 · low confidence	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	109.6 GB	Q4_K_M	Tight
26.6 tok/s 16–43 · low confidence	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	109.6 GB	Q4_K_M	Tight
22.6 tok/s 14–36 · low confidence	Radeon Instinct MI300A AMD	128 GB	5,325 GB/s	Dec 2023	109.6 GB	Q4_K_M	Tight
18.8 tok/s 11–30 · low confidence	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	193.4 GB	Q8_0	Comfortable
15.0 tok/s 9–24 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	193.4 GB	Q8_0	Comfortable
15.0 tok/s 9–24 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	193.4 GB	Q8_0	Comfortable
14.2 tok/s 9–23 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	151.5 GB	Q6_K	Tight
14.2 tok/s 9–23 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	151.5 GB	Q6_K	Tight
13.9 tok/s 8–22 · low confidence	Radeon Instinct MI250 AMD	128 GB	3,280 GB/s	Nov 2021	109.6 GB	Q4_K_M	Tight
13.9 tok/s 8–22 · low confidence	Radeon Instinct MI250X AMD	128 GB	3,280 GB/s	Nov 2021	109.6 GB	Q4_K_M	Tight
11.6 tok/s 7–19 · low confidence	Data Center GPU Max 1550 Intel	128 GB	3,280 GB/s	Jan 2023	109.6 GB	Q4_K_M	Tight
11.3 tok/s 7–18 · low confidence	Data Center GPU Max Subsystem Intel	128 GB	3,210 GB/s	Jan 2023	109.6 GB	Q4_K_M	Tight
11.0 tok/s 7–18 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	193.4 GB	Q8_0	Tight
1.5 tok/s 1–2 · low confidence	GB10 NVIDIA	128 GB	273 GB/s	Oct 2025	109.6 GB	Q4_K_M	Tight
1.5 tok/s 1–2 · low confidence	Jetson T5000 NVIDIA	128 GB	273 GB/s	Aug 2025	109.6 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: Technology Innovation Institute
Organisation type: Government
Country: United Arab Emirates
Published: 6 September 2023
Authors: Ebtesam Almazrouei, Hamza Alobeidli, Abdulaziz Alshamsi, Alessandro Cappelli, Ruxandra Cojocaru, Mérouane Debbah, Étienne Goffinet, Daniel Hesslow, Julien Launay, Quentin Malartic, Daniele Mazzotta, Badreddine Noune, Baptiste Pannier, Guilherme Penedo

What it does

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

Domain: Language
Task: Language modeling, Language modeling/generation, Question answering
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: 180B
Training data: 3,500,000,000,000 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: 3.8 × 10²⁴ FLOP
How it was established: Reported,Operation counting
Plausible range: 3.8 × 10²⁴ – 3.8 × 10²⁴ FLOP

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 40 GB
Chips used: 4,096
Chip-hours: 17,694,720
Wall-clock time: 4,320 hours (180 days)
Hardware utilisation: MFU 18.9%
Power draw: 3.3 MW
Compute cost: $10,743,501
Cloud vendor: Amazon Web Services

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.

Frontier model: Yes
Likely above 10²³ FLOP: Yes
Why it is tracked: Training cost
Record confidence: Confident
Citations: 691

Sources

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

Reference: The Falcon Series of Open Language Models
Last updated: 25 May 2026

The extremes

The ten fastest GPUs that run Falcon-180B

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 Falcon-180B

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 it takes to run this model

Minimum card

Radeon Instinct MI250

Memory needed

109.6 GB

Fastest

27.8 tok/s

Falcon-180B sits at 180B 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 13.9 tokens per second.

At the other end, a Radeon Instinct MI300 generates roughly 27.8 tokens per second on it, on the strength of 6,550 GB/s of memory bandwidth.

Where it came from

Falcon-180B was published by Technology Innovation Institute, in United Arab Emirates, in September 2023. It comes out of government.

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

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.

Understanding the speeds

Half the cards that hold it manage more than 14.2 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.

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.

How it was trained

Training it took roughly 3.8 × 10²⁴ FLOP of computation, on NVIDIA A100 SXM4 40 GB — a measure of what producing the model cost, not of how fast it answers.

The training set ran to roughly 3,500,000,000,000 tokens.

The reason it appears in this catalogue at all is training cost.

Step by step

How to choose a GPU for Falcon-180B

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

01

Start from the memory column

Every card here has been checked against Falcon-180B — around 109.6 GB at Q4_K_M. Capacity is the gate — a card either holds it or it does not.
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: at long context Falcon-180B 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 — Q4_K_M on the smallest card that fits. Setting a floor drops the cards that only manage Falcon-180B by squeezing it further than you would want.
04

Rank by throughput rather than spec sheet

Sort by speed to see how cards rank for Falcon-180B. It will not match a gaming ordering — generation is bound by memory bandwidth, which is why the Radeon Instinct MI300 tops it at 27.8 tok/s.
05

Check the fit verdict before buying

Tight means Falcon-180B 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.
06

Check the card from the other side

Each card page repeats this sweep for every model we hold. It answers what else the hardware is good for, beyond Falcon-180B.

Answers

Falcon-180B — common questions

How much compute was used to train Falcon-180B?

Around 3.8 × 10²⁴ FLOP, on NVIDIA A100 SXM4 40 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.

Can I run Falcon-180B if it does not fit in my GPU?

Only by offloading, which is usually a false economy: the part in system memory drags the whole thing down — the nearest miss we calculate is short by 23.2 GB. Our figures for Falcon-180B assume it is fully resident.

Would two GPUs run Falcon-180B faster?

Two cards buy memory rather than speed. That matters for Falcon-180B only if one card cannot hold it — 17 can, so a second adds little.

Why does the quantisation differ between cards for Falcon-180B?

Because capacity varies, so does how hard Falcon-180B has to be squeezed — 3 distinct levels appear in the table above. Set a minimum quality to compare at one.

How accurate are these Falcon-180B speed estimates?

They are calculated from specifications rather than measured, and each carries a range — 17–44 tok/s on the Radeon Instinct MI300, for instance. The same model and card vary by thirty to fifty per cent depending on the inference software and its version.

What GPU do I need to run Falcon-180B?

The smallest card in our catalogue that holds Falcon-180B is the Radeon Instinct MI250, with 128 GB of memory. It runs the model at Q4_K_M using about 109.6 GB, and produces roughly 13.9 tokens per second. 17 cards in total can run it.

How fast is Falcon-180B on a GPU?

It depends on the card. The quickest we calculate is a Radeon Instinct MI300 at about 27.8 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 Falcon-180B clear that.

How much VRAM does Falcon-180B need?

About 109.6 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 Falcon-180B open source?

Its weights are published, so Falcon-180B 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 Falcon-180B have?

Falcon-180B has 180B parameters. "Falcon 180B is a super-powerful language model with 180 billion 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 Falcon-180B?

Falcon-180B was published by Technology Innovation Institute, based in United Arab Emirates, categorised as government.

When was Falcon-180B released?

Falcon-180B was published in September 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 Falcon-180B used for?

Falcon-180B works in Language, and is recorded as handling language modeling, Language modeling/generation, Question answering. These are the areas it was designed around; they describe intent rather than a hard boundary.

Where can I download Falcon-180B?

The weights for Falcon-180B are published, though we do not hold a repository link for it. This site calculates hardware requirements rather than hosting model files.

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