HiDream-I1 TPS calculator

Open weights HiDream 18B parameters April 2025

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

295 cards that can run it

818 cards we hold specifications for

Smallest card that fits

GeForce GTX 1080 Ti

11 GB · Q3_K_M · 26.1 tok/s

Fastest card

B200

188 tok/s · 180 GB

Which GPUs can run HiDream-I1?

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

295 cards match

Calculating

					Needs	Quantisation	Fit
188 tok/s 113–301 · low confidence	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	20.0 GB	Q8_0	Comfortable
188 tok/s 113–301 · low confidence	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	20.0 GB	Q8_0	Comfortable
150 tok/s 90–241 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	20.0 GB	Q8_0	Comfortable
150 tok/s 90–241 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	20.0 GB	Q8_0	Comfortable
120 tok/s 72–192 · low confidence	Radeon Instinct MI300 AMD	128 GB	6,550 GB/s	Jan 2023	20.0 GB	Q8_0	Comfortable
115 tok/s 69–184 · low confidence	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	20.0 GB	Q8_0	Comfortable
115 tok/s 69–184 · low confidence	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	20.0 GB	Q8_0	Comfortable
110 tok/s 66–176 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	20.0 GB	Q8_0	Comfortable
97.7 tok/s 59–156 · low confidence	Radeon Instinct MI300A AMD	128 GB	5,325 GB/s	Dec 2023	20.0 GB	Q8_0	Comfortable
97.7 tok/s 59–156 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	20.0 GB	Q8_0	Comfortable
97.7 tok/s 59–156 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	20.0 GB	Q8_0	Comfortable
92.7 tok/s 56–148 · low confidence	H100 NVL 94 GB NVIDIA	94 GB	3,940 GB/s	Mar 2023	20.0 GB	Q8_0	Comfortable
79.1 tok/s 47–126 · low confidence	H100 PCIe 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	20.0 GB	Q8_0	Comfortable
79.1 tok/s 47–126 · low confidence	H100 SXM5 80 GB NVIDIA	80 GB	3,360 GB/s	Oct 2022	20.0 GB	Q8_0	Comfortable
79.1 tok/s 47–126 · low confidence	H100 SXM5 94 GB NVIDIA	94 GB	3,360 GB/s	Mar 2023	20.0 GB	Q8_0	Comfortable
79.1 tok/s 47–126 · low confidence	H100 SXM5 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	20.0 GB	Q8_0	Comfortable
79.1 tok/s 47–126 · low confidence	H800 SXM5 NVIDIA	80 GB	3,360 GB/s	Mar 2023	20.0 GB	Q8_0	Comfortable
60.2 tok/s 36–96 · low confidence	Radeon Instinct MI250 AMD	128 GB	3,280 GB/s	Nov 2021	20.0 GB	Q8_0	Comfortable
60.2 tok/s 36–96 · low confidence	Radeon Instinct MI250X AMD	128 GB	3,280 GB/s	Nov 2021	20.0 GB	Q8_0	Comfortable
52.7 tok/s 32–84 · low confidence	GeForce RTX 3080 12 GB NVIDIA	12 GB	912 GB/s	Jan 2022	10.5 GB	IQ4_XS	Tight
52.7 tok/s 32–84 · low confidence	GeForce RTX 3080 Ti NVIDIA	12 GB	912 GB/s	May 2021	10.5 GB	IQ4_XS	Tight
50.2 tok/s 30–80 · low confidence	Data Center GPU Max 1550 Intel	128 GB	3,280 GB/s	Jan 2023	20.0 GB	Q8_0	Comfortable
49.1 tok/s 29–79 · low confidence	Data Center GPU Max Subsystem Intel	128 GB	3,210 GB/s	Jan 2023	20.0 GB	Q8_0	Comfortable
48.0 tok/s 29–77 · low confidence	A100 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Nov 2020	20.0 GB	Q8_0	Comfortable
48.0 tok/s 29–77 · low confidence	A100X NVIDIA	80 GB	2,040 GB/s	Jun 2021	20.0 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: HiDream
Organisation type: Industry
Country: China
Published: 25 April 2025

What it does

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

Domain: Image generation
Task: Image generation, Text-to-image

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: 18B
Training data: tokens

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: Unreleased
Hugging Face: HiDream-ai

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: HiDream-I1 is a new open-source image generative foundation model with 17B parameters that achieves state-of-the-art image generation quality within seconds.
Last updated: 28 November 2025

The extremes

The ten fastest GPUs that run HiDream-I1

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 HiDream-I1

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

GeForce GTX 1080 Ti

Memory needed

9.5 GB

Fastest

188 tok/s

HiDream-I1 is small enough at 18B parameters that hardware is rarely the obstacle — 295 of the cards we track can run it, including cards several years old.

The entry point is the GeForce GTX 1080 Ti: 11 GB of memory, Q3_K_M compression, roughly 26.1 tokens per second.

A B200 is the fastest we calculate for it: about 188 tokens per second, from 8,000 GB/s of memory bandwidth.

What this model is

HiDream-I1 was published by HiDream, in China, in April 2025. industry is the category the publisher falls under.

It works in Image generation, and is recorded as doing image generation, Text-to-image.

The weights are published, so it can be downloaded and run on your own hardware indefinitely, offline, with no account attached. It is published under the HiDream-ai organisation on Hugging Face.

What decides the speed

Half the cards that hold it manage more than 19.4 tokens per second, and 248 exceed reading speed outright.

Every weight participates in every token here, so bandwidth is the whole story: the ranking below is effectively a ranking of memory throughput.

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.

Step by step

How to choose a GPU for HiDream-I1

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

Every card here has been checked against HiDream-I1 — around 9.5 GB at Q3_K_M. Capacity is the gate — a card either holds it or it does not.
02

Set the context length you will work at

The conversation occupies memory too, and grows as it goes. Set the slider to the length you expect: at long context HiDream-I1 can slip off a card that handles short questions easily.
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 HiDream-I1 by squeezing it further than you would want.
04

Compare tokens per second, not specifications

Ranking by tokens per second for HiDream-I1 follows memory bandwidth, not core counts, which is why the B200 tops it at 188 tok/s.
05

Check the fit verdict before buying

Tight means HiDream-I1 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 HiDream-I1.

Answers

HiDream-I1 — common questions

Can I run HiDream-I1 on a 12 GB GPU?

Yes. A GeForce RTX 3080 Ti with 12 GB runs it at IQ4_XS, using about 10.5 GB and generating roughly 52.7 tokens per second — a tight fit.

Can I run HiDream-I1 on a 16 GB GPU?

Yes. A Tesla V100 SXM2 16 GB with 16 GB runs it at Q5_K_M, using about 13.7 GB and generating roughly 47.5 tokens per second — a tight fit.

Can I run HiDream-I1 on a 24 GB GPU?

Yes. A GeForce RTX 5090 D V2 with 24 GB runs it at Q8_0, using about 20.0 GB and generating roughly 31.5 tokens per second — a tight fit.

Is HiDream-I1 open source?

Its weights are published, so HiDream-I1 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 HiDream-I1 have?

HiDream-I1 has 18B parameters. 18B. 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 HiDream-I1?

HiDream-I1 was published by HiDream, based in China, categorised as industry.

When was HiDream-I1 released?

HiDream-I1 was published in April 2025.

What is HiDream-I1 used for?

HiDream-I1 works in Image generation, and is recorded as handling image generation, Text-to-image. These are the areas it was designed around; they describe intent rather than a hard boundary.

Where can I download HiDream-I1?

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

Can I run HiDream-I1 if it does not fit in my GPU?

Partly. Layers that do not fit sit in system memory and run at a fraction of the speed, so a mostly-offloaded HiDream-I1 is rarely worth using — the nearest miss we calculate is short by 2.6 GB. Every figure here assumes the whole model is on the card.

Would two GPUs run HiDream-I1 faster?

A second card roughly doubles the memory available but not the generation rate. With 295 cards already able to run HiDream-I1 alone, the case for pairing is weak.

Why does the quantisation differ between cards for HiDream-I1?

Each card is shown running the least-compressed copy it can hold, and HiDream-I1 appears at 5 different compression levels across the cards that fit it. Bigger cards get the more accurate version.

How accurate are these HiDream-I1 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 113–301 tok/s on the B200 rather than a single number.

What GPU do I need to run HiDream-I1?

The smallest card in our catalogue that holds HiDream-I1 is the GeForce GTX 1080 Ti, with 11 GB of memory. It runs the model at Q3_K_M using about 9.5 GB, and produces roughly 26.1 tokens per second. 295 cards in total can run it.

How fast is HiDream-I1 on a GPU?

It depends on the card. The quickest we calculate is a B200 at about 188 tokens per second; the slowest that still runs it manages considerably less. Reading speed is around ten tokens per second, and 248 of the cards that can run HiDream-I1 clear that.

How much VRAM does HiDream-I1 need?

About 9.5 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.

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