IDEFICS-9B TPS calculator

Open weights Hugging Face 9B parameters August 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

582 cards that can run it

818 cards we hold specifications for

Smallest card that fits

Quadro 6000

6 GB · Q3_K_M · 15.5 tok/s

Fastest card

B200

376 tok/s · 180 GB

Which GPUs can run IDEFICS-9B?

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

582 cards match

Calculating

					Needs	Quantisation	Fit
376 tok/s 226–602 · low confidence	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	10.3 GB	Q8_0	Comfortable
376 tok/s 226–602 · low confidence	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	10.3 GB	Q8_0	Comfortable
301 tok/s 180–481 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	10.3 GB	Q8_0	Comfortable
301 tok/s 180–481 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	10.3 GB	Q8_0	Comfortable
240 tok/s 144–385 · low confidence	Radeon Instinct MI300 AMD	128 GB	6,550 GB/s	Jan 2023	10.3 GB	Q8_0	Comfortable
230 tok/s 138–368 · low confidence	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	10.3 GB	Q8_0	Comfortable
230 tok/s 138–368 · low confidence	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	10.3 GB	Q8_0	Comfortable
220 tok/s 132–352 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	10.3 GB	Q8_0	Comfortable
195 tok/s 117–313 · low confidence	Radeon Instinct MI300A AMD	128 GB	5,325 GB/s	Dec 2023	10.3 GB	Q8_0	Comfortable
195 tok/s 117–313 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	10.3 GB	Q8_0	Comfortable
195 tok/s 117–313 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	10.3 GB	Q8_0	Comfortable
185 tok/s 111–297 · low confidence	H100 NVL 94 GB NVIDIA	94 GB	3,940 GB/s	Mar 2023	10.3 GB	Q8_0	Comfortable
158 tok/s 95–253 · low confidence	H100 PCIe 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	10.3 GB	Q8_0	Comfortable
158 tok/s 95–253 · low confidence	H100 SXM5 80 GB NVIDIA	80 GB	3,360 GB/s	Oct 2022	10.3 GB	Q8_0	Comfortable
158 tok/s 95–253 · low confidence	H100 SXM5 94 GB NVIDIA	94 GB	3,360 GB/s	Mar 2023	10.3 GB	Q8_0	Comfortable
158 tok/s 95–253 · low confidence	H100 SXM5 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	10.3 GB	Q8_0	Comfortable
158 tok/s 95–253 · low confidence	H800 SXM5 NVIDIA	80 GB	3,360 GB/s	Mar 2023	10.3 GB	Q8_0	Comfortable
125 tok/s 75–200 · low confidence	CMP 170HX 8 GB NVIDIA	8 GB	1,490 GB/s	Sep 2021	7.2 GB	Q5_K_M	Tight
120 tok/s 72–193 · low confidence	Radeon Instinct MI250 AMD	128 GB	3,280 GB/s	Nov 2021	10.3 GB	Q8_0	Comfortable
120 tok/s 72–193 · low confidence	Radeon Instinct MI250X AMD	128 GB	3,280 GB/s	Nov 2021	10.3 GB	Q8_0	Comfortable
107 tok/s 64–171 · low confidence	CMP 170HX 10 GB NVIDIA	10 GB	1,560 GB/s	Sep 2021	8.2 GB	Q6_K	Tight
100 tok/s 60–161 · low confidence	Data Center GPU Max 1550 Intel	128 GB	3,280 GB/s	Jan 2023	10.3 GB	Q8_0	Comfortable
98.2 tok/s 59–157 · low confidence	Data Center GPU Max Subsystem Intel	128 GB	3,210 GB/s	Jan 2023	10.3 GB	Q8_0	Comfortable
96.0 tok/s 58–154 · low confidence	A100 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Nov 2020	10.3 GB	Q8_0	Comfortable
96.0 tok/s 58–154 · low confidence	A100X NVIDIA	80 GB	2,040 GB/s	Jun 2021	10.3 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
Organisation type: Industry
Country: United States of America
Published: 22 August 2023
Authors: Hugo Laurencon, Daniel van Strien, Stas Bekman, Leo Tronchon, Lucile Saulnier, Thomas Wang, Siddharth Karamcheti, Amanpreet Singh, Giada Pistilli, Yacine Jernite, Victor Sanh

What it does

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

Domain: Multimodal, Language, Vision
Task: Language modeling, Image captioning, Visual question answering
Base model: CLIP ViT-H/14 - LAION-2B,LLaMA-7B
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: 9B
Training data: 262,000,000,000 tokens

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.

How it was established: Operation counting,Hardware
Fine-tuning compute: 1.5 × 10²² 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
Chips used: 128
Wall-clock time: 350 hours (14.6 days)
Power draw: 101.8 kW
Cloud vendor: AWS

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 (non-commercial)
Hugging Face: HuggingFaceM4

How it is classified

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

Record confidence: Confident

Sources

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

Reference: Introducing IDEFICS: An Open Reproduction of State-of-the-Art Visual Language Model
Last updated: 28 November 2025

The extremes

The ten fastest GPUs that run IDEFICS-9B

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 IDEFICS-9B

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

Quadro 6000

Memory needed

5.1 GB

Fastest

376 tok/s

IDEFICS-9B is small enough at 9B parameters that hardware is rarely the obstacle — 582 of the cards we track can run it, including cards several years old.

At the low end, a Quadro 6000 handles it — 6 GB, at Q3_K_M, for about 15.5 tokens per second.

A B200 is the fastest we calculate for it: about 376 tokens per second, from 8,000 GB/s of memory bandwidth.

About this model

IDEFICS-9B was published by Hugging Face, in United States of America, in August 2023. It comes out of industry.

It works in Multimodal, Language, Vision, and is recorded as doing language modeling, Image captioning, Visual question answering.

It is derived from CLIP ViT-H/14 - LAION-2B,LLaMA-7B rather than trained from scratch, which is the usual way a specialised model is produced.

Because its weights were released, nothing about running it depends on a provider staying available — it is yours once downloaded. It is published under the HuggingFaceM4 organisation on Hugging Face.

How fast it runs, and why

Half the cards that hold it manage more than 21.1 tokens per second, and 541 exceed reading speed outright.

Being dense, it reads all of itself per token, which is why the ordering by speed below follows the ordering by memory bandwidth so closely.

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.

Training and provenance

It was trained on about 262,000,000,000 tokens of text.

Step by step

How to choose a GPU for IDEFICS-9B

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

The table lists every card that can hold IDEFICS-9B — around 5.1 GB at Q3_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 IDEFICS-9B.
03

Set a quality floor

Each card runs the least-compressed copy it can hold — Q3_K_M on the smallest card that fits. Setting a floor drops the cards that only manage IDEFICS-9B 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 IDEFICS-9B. It will not match a gaming ordering — generation is bound by memory bandwidth, which is why the B200 tops it at 376 tok/s.
05

Read the fit column last

A tight fit runs IDEFICS-9B but leaves nothing spare for a longer conversation; comfortable has headroom. If you expect to grow the context, buy for comfortable.
06

See what else that card runs

Following a card through to its own page shows every other model it can hold, which is the question that follows once IDEFICS-9B is settled.

Answers

IDEFICS-9B — common questions

How much VRAM does IDEFICS-9B need?

About 5.1 GB at Q3_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.

Can I run IDEFICS-9B on a 8 GB GPU?

Yes. A CMP 170HX 8 GB with 8 GB runs it at Q5_K_M, using about 7.2 GB and generating roughly 125 tokens per second — a tight fit.

Can I run IDEFICS-9B on a 12 GB GPU?

Yes. A GeForce RTX 3080 Ti with 12 GB runs it at Q8_0, using about 10.3 GB and generating roughly 42.9 tokens per second — a tight fit.

Can I run IDEFICS-9B on a 16 GB GPU?

Yes. A Tesla V100 SXM2 16 GB with 16 GB runs it at Q8_0, using about 10.3 GB and generating roughly 53.2 tokens per second — a comfortable fit.

Can I run IDEFICS-9B on a 24 GB GPU?

Yes. A GeForce RTX 5090 D V2 with 24 GB runs it at Q8_0, using about 10.3 GB and generating roughly 63.1 tokens per second — a comfortable fit.

Is IDEFICS-9B open source?

Its weights are published, so IDEFICS-9B 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 IDEFICS-9B have?

IDEFICS-9B has 9B parameters. 9B. 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 IDEFICS-9B?

IDEFICS-9B was published by Hugging Face, based in United States of America, categorised as industry.

When was IDEFICS-9B released?

IDEFICS-9B was published in August 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 IDEFICS-9B used for?

IDEFICS-9B works in Multimodal, Language, Vision, and is recorded as handling language modeling, Image captioning, Visual question answering. These are the areas it was designed around; they describe intent rather than a hard boundary.

Where can I download IDEFICS-9B?

Its weights are published under the HuggingFaceM4 organisation on Hugging Face. We do not host model files — this site calculates what hardware is needed to run them.

Can I run IDEFICS-9B if it does not fit in my GPU?

It can be split between the card and system memory, but IDEFICS-9B generates painfully slowly that way — the nearest miss we calculate is short by 1.6 GB. Nothing on this page assumes offloading.

Would two GPUs run IDEFICS-9B faster?

Capacity adds across cards; throughput does not. Since 582 of the cards we track already hold IDEFICS-9B on their own, a second card is rarely the answer here.

Why does the quantisation differ between cards for IDEFICS-9B?

Because capacity varies, so does how hard IDEFICS-9B has to be squeezed — 4 distinct levels appear in the table above. Set a minimum quality to compare at one.

How accurate are these IDEFICS-9B 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 226–602 tok/s on the B200 rather than a single number.

What GPU do I need to run IDEFICS-9B?

The smallest card in our catalogue that holds IDEFICS-9B is the Quadro 6000, with 6 GB of memory. It runs the model at Q3_K_M using about 5.1 GB, and produces roughly 15.5 tokens per second. 582 cards in total can run it.

How fast is IDEFICS-9B on a GPU?

It depends on the card. The quickest we calculate is a B200 at about 376 tokens per second; the slowest that still runs it manages considerably less. Reading speed is around ten tokens per second, and 541 of the cards that can run IDEFICS-9B clear that.

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