RWKV-4 World (7B) TPS calculator

Open weights RWKV Foundation 7.4B parameters June 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

589 cards that can run it

818 cards we hold specifications for

Smallest card that fits

Tesla K20c

5 GB · Q3_K_M · 27.3 tok/s

Fastest card

B200

458 tok/s · 180 GB

Which GPUs can run RWKV-4 World (7B)?

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

589 cards match

Calculating

					Needs	Quantisation	Fit
458 tok/s 275–733 · low confidence	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	8.6 GB	Q8_0	Comfortable
458 tok/s 275–733 · low confidence	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	8.6 GB	Q8_0	Comfortable
366 tok/s 220–586 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	8.6 GB	Q8_0	Comfortable
366 tok/s 220–586 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	8.6 GB	Q8_0	Comfortable
293 tok/s 176–468 · low confidence	Radeon Instinct MI300 AMD	128 GB	6,550 GB/s	Jan 2023	8.6 GB	Q8_0	Comfortable
280 tok/s 168–448 · low confidence	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	8.6 GB	Q8_0	Comfortable
280 tok/s 168–448 · low confidence	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	8.6 GB	Q8_0	Comfortable
268 tok/s 161–429 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	8.6 GB	Q8_0	Comfortable
238 tok/s 143–381 · low confidence	Radeon Instinct MI300A AMD	128 GB	5,325 GB/s	Dec 2023	8.6 GB	Q8_0	Comfortable
238 tok/s 143–381 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	8.6 GB	Q8_0	Comfortable
238 tok/s 143–381 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	8.6 GB	Q8_0	Comfortable
226 tok/s 135–361 · low confidence	H100 NVL 94 GB NVIDIA	94 GB	3,940 GB/s	Mar 2023	8.6 GB	Q8_0	Comfortable
192 tok/s 115–308 · low confidence	H100 PCIe 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	8.6 GB	Q8_0	Comfortable
192 tok/s 115–308 · low confidence	H100 SXM5 80 GB NVIDIA	80 GB	3,360 GB/s	Oct 2022	8.6 GB	Q8_0	Comfortable
192 tok/s 115–308 · low confidence	H100 SXM5 94 GB NVIDIA	94 GB	3,360 GB/s	Mar 2023	8.6 GB	Q8_0	Comfortable
192 tok/s 115–308 · low confidence	H100 SXM5 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	8.6 GB	Q8_0	Comfortable
192 tok/s 115–308 · low confidence	H800 SXM5 NVIDIA	80 GB	3,360 GB/s	Mar 2023	8.6 GB	Q8_0	Comfortable
147 tok/s 88–235 · low confidence	Radeon Instinct MI250 AMD	128 GB	3,280 GB/s	Nov 2021	8.6 GB	Q8_0	Comfortable
147 tok/s 88–235 · low confidence	Radeon Instinct MI250X AMD	128 GB	3,280 GB/s	Nov 2021	8.6 GB	Q8_0	Comfortable
124 tok/s 74–198 · low confidence	CMP 170HX 8 GB NVIDIA	8 GB	1,490 GB/s	Sep 2021	6.9 GB	Q6_K	Tight
122 tok/s 73–195 · low confidence	Data Center GPU Max 1550 Intel	128 GB	3,280 GB/s	Jan 2023	8.6 GB	Q8_0	Comfortable
120 tok/s 72–191 · low confidence	Data Center GPU Max Subsystem Intel	128 GB	3,210 GB/s	Jan 2023	8.6 GB	Q8_0	Comfortable
117 tok/s 70–187 · low confidence	A100 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Nov 2020	8.6 GB	Q8_0	Comfortable
117 tok/s 70–187 · low confidence	A100X NVIDIA	80 GB	2,040 GB/s	Jun 2021	8.6 GB	Q8_0	Comfortable
117 tok/s 70–187 · low confidence	A800 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Aug 2022	8.6 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: RWKV Foundation
Organisation type: Research collective
Country: Multinational
Published: 26 June 2023

What it does

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

Domain: Language
Task: Language modeling/generation, Chat

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: 7.4B
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: Open source

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: RWKV-4 World
Last updated: 11 February 2026

The extremes

The ten fastest GPUs that run RWKV-4 World (7B)

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 RWKV-4 World (7B)

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

Tesla K20c

Memory needed

4.3 GB

Fastest

458 tok/s

RWKV-4 World (7B) is small enough at 7.4B parameters that hardware is rarely the obstacle — 589 of the cards we track can run it, including cards several years old.

The entry point is the Tesla K20c: 5 GB of memory, Q3_K_M compression, roughly 27.3 tokens per second.

A B200 is the fastest we calculate for it: about 458 tokens per second, from 8,000 GB/s of memory bandwidth.

Background

RWKV-4 World (7B) was published by RWKV Foundation, in Multinational, in June 2023. The organisation is categorised as research collective.

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

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

The median result is around 24.8 tokens per second; 558 cards produce text faster than most people read it.

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.

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.

Step by step

How to choose a GPU for RWKV-4 World (7B)

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 RWKV-4 World (7B) — around 4.3 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

Set the context to what you will actually use. The cache grows with the conversation, and it is the usual reason RWKV-4 World (7B) stops fitting a card that seemed fine.
03

Decide how much compression you will accept

Compression is what makes RWKV-4 World (7B) fit smaller cards, at some cost in accuracy — Q3_K_M on the smallest card that fits. A minimum quality removes the ones that go too far.
04

Sort by speed

Sort by speed to see how cards rank for RWKV-4 World (7B). It will not match a gaming ordering — generation is bound by memory bandwidth, which is why the B200 tops it at 458 tok/s.
05

Look at the headroom, not just the fit

The fit column separates cards that just manage RWKV-4 World (7B) 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 RWKV-4 World (7B) alone — a card is usually bought for more than one model.

Answers

RWKV-4 World (7B) — common questions

How much VRAM does RWKV-4 World (7B) need?

About 4.3 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 RWKV-4 World (7B) on a 8 GB GPU?

Yes. A CMP 170HX 8 GB with 8 GB runs it at Q6_K, using about 6.9 GB and generating roughly 124 tokens per second — a tight fit.

Can I run RWKV-4 World (7B) on a 12 GB GPU?

Yes. A GeForce RTX 3080 Ti with 12 GB runs it at Q8_0, using about 8.6 GB and generating roughly 52.3 tokens per second — a comfortable fit.

Can I run RWKV-4 World (7B) on a 16 GB GPU?

Yes. A Tesla V100 SXM2 16 GB with 16 GB runs it at Q8_0, using about 8.6 GB and generating roughly 64.7 tokens per second — a comfortable fit.

Can I run RWKV-4 World (7B) on a 24 GB GPU?

Yes. A GeForce RTX 5090 D V2 with 24 GB runs it at Q8_0, using about 8.6 GB and generating roughly 76.8 tokens per second — a comfortable fit.

Is RWKV-4 World (7B) open source?

Its weights are published, so RWKV-4 World (7B) 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 RWKV-4 World (7B) have?

RWKV-4 World (7B) has 7.4B parameters. 7B Table 2 https://arxiv.org/pdf/2305.13048. 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 RWKV-4 World (7B)?

RWKV-4 World (7B) was published by RWKV Foundation, based in Multinational, categorised as research collective.

When was RWKV-4 World (7B) released?

RWKV-4 World (7B) was published in June 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 RWKV-4 World (7B) used for?

RWKV-4 World (7B) works in Language, and is recorded as handling language modeling/generation, Chat. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.

Where can I download RWKV-4 World (7B)?

The weights for RWKV-4 World (7B) are published, though we do not hold a repository link for it. This site calculates hardware requirements rather than hosting model files.

Can I run RWKV-4 World (7B) 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 RWKV-4 World (7B) is rarely worth using — the nearest miss we calculate is short by 1.6 GB. Every figure here assumes the whole model is on the card.

Would two GPUs run RWKV-4 World (7B) faster?

Two cards buy memory rather than speed. That matters for RWKV-4 World (7B) only if one card cannot hold it — 589 can, so a second adds little.

Why does the quantisation differ between cards for RWKV-4 World (7B)?

Each card is shown running the least-compressed copy it can hold, and RWKV-4 World (7B) appears at 4 different compression levels across the cards that fit it. Bigger cards get the more accurate version.

How accurate are these RWKV-4 World (7B) speed estimates?

These are estimates with real error bars. The fastest result here, 275–733 tok/s on the B200, could reasonably land anywhere in its published range depending on which runtime you use.

What GPU do I need to run RWKV-4 World (7B)?

The smallest card in our catalogue that holds RWKV-4 World (7B) is the Tesla K20c, with 5 GB of memory. It runs the model at Q3_K_M using about 4.3 GB, and produces roughly 27.3 tokens per second. 589 cards in total can run it.

How fast is RWKV-4 World (7B) on a GPU?

It depends on the card. The quickest we calculate is a B200 at about 458 tokens per second; the slowest that still runs it manages considerably less. Reading speed is around ten tokens per second, and 558 of the cards that can run RWKV-4 World (7B) clear that.

Source

Original publication

Record last updated 11 February 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