RedPajama-INCITE-7B-Base TPS calculator

Open weights Together 6.9B 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 · IQ4_XS · 26.7 tok/s

Fastest card

B200

491 tok/s · 180 GB

Which GPUs can run RedPajama-INCITE-7B-Base?

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
491 tok/s 295–786 · low confidence	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	8.1 GB	Q8_0	Comfortable
491 tok/s 295–786 · low confidence	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	8.1 GB	Q8_0	Comfortable
392 tok/s 235–627 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	8.1 GB	Q8_0	Comfortable
392 tok/s 235–627 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	8.1 GB	Q8_0	Comfortable
314 tok/s 188–502 · low confidence	Radeon Instinct MI300 AMD	128 GB	6,550 GB/s	Jan 2023	8.1 GB	Q8_0	Comfortable
300 tok/s 180–480 · low confidence	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	8.1 GB	Q8_0	Comfortable
300 tok/s 180–480 · low confidence	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	8.1 GB	Q8_0	Comfortable
287 tok/s 172–460 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	8.1 GB	Q8_0	Comfortable
255 tok/s 153–408 · low confidence	Radeon Instinct MI300A AMD	128 GB	5,325 GB/s	Dec 2023	8.1 GB	Q8_0	Comfortable
255 tok/s 153–408 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	8.1 GB	Q8_0	Comfortable
255 tok/s 153–408 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	8.1 GB	Q8_0	Comfortable
242 tok/s 145–387 · low confidence	H100 NVL 94 GB NVIDIA	94 GB	3,940 GB/s	Mar 2023	8.1 GB	Q8_0	Comfortable
206 tok/s 124–330 · low confidence	H100 PCIe 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	8.1 GB	Q8_0	Comfortable
206 tok/s 124–330 · low confidence	H100 SXM5 80 GB NVIDIA	80 GB	3,360 GB/s	Oct 2022	8.1 GB	Q8_0	Comfortable
206 tok/s 124–330 · low confidence	H100 SXM5 94 GB NVIDIA	94 GB	3,360 GB/s	Mar 2023	8.1 GB	Q8_0	Comfortable
206 tok/s 124–330 · low confidence	H100 SXM5 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	8.1 GB	Q8_0	Comfortable
206 tok/s 124–330 · low confidence	H800 SXM5 NVIDIA	80 GB	3,360 GB/s	Mar 2023	8.1 GB	Q8_0	Comfortable
157 tok/s 94–251 · low confidence	Radeon Instinct MI250 AMD	128 GB	3,280 GB/s	Nov 2021	8.1 GB	Q8_0	Comfortable
157 tok/s 94–251 · low confidence	Radeon Instinct MI250X AMD	128 GB	3,280 GB/s	Nov 2021	8.1 GB	Q8_0	Comfortable
133 tok/s 80–213 · low confidence	CMP 170HX 8 GB NVIDIA	8 GB	1,490 GB/s	Sep 2021	6.5 GB	Q6_K	Tight
131 tok/s 79–209 · low confidence	Data Center GPU Max 1550 Intel	128 GB	3,280 GB/s	Jan 2023	8.1 GB	Q8_0	Comfortable
128 tok/s 77–205 · low confidence	Data Center GPU Max Subsystem Intel	128 GB	3,210 GB/s	Jan 2023	8.1 GB	Q8_0	Comfortable
125 tok/s 75–200 · low confidence	A100 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Nov 2020	8.1 GB	Q8_0	Comfortable
125 tok/s 75–200 · low confidence	A100X NVIDIA	80 GB	2,040 GB/s	Jun 2021	8.1 GB	Q8_0	Comfortable
125 tok/s 75–200 · low confidence	A800 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Aug 2022	8.1 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: Together
Organisation type: Industry
Country: United States of America
Published: 6 June 2023

What it does

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

Domain: Language
Task: 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: 6.9B
Training data: 1,001,000,000,000 tokens
Epochs: 1
Batch size: 4,000,000

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: 4.1 × 10²² FLOP
How it was established: Operation counting

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 V100
Chips used: 3,072
Power draw: 1.8 MW

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

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.

Last updated: 28 November 2025

The extremes

The ten fastest GPUs that run RedPajama-INCITE-7B-Base

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 RedPajama-INCITE-7B-Base

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 you need to run it

Minimum card

Tesla K20c

Memory needed

4.5 GB

Fastest

491 tok/s

RedPajama-INCITE-7B-Base is small enough at 6.9B parameters that hardware is rarely the obstacle — 589 of the cards we track can run it, including cards several years old.

The least hardware that works is a Tesla K20c. Its 5 GB is enough at IQ4_XS compression, giving roughly 26.7 tokens per second.

A B200 is the fastest we calculate for it: about 491 tokens per second, from 8,000 GB/s of memory bandwidth.

What this model is

RedPajama-INCITE-7B-Base was published by Together, in United States of America, in June 2023. The organisation is categorised as industry.

It works in Language, and is recorded as doing chat.

Because its weights were released, nothing about running it depends on a provider staying available — it is yours once downloaded.

What decides the speed

Half the cards that hold it manage more than 26.5 tokens per second, and 562 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.

Without the attention layout on record, the memory column is an approximation. It is close enough to choose hardware by, and least reliable at long context.

Training and provenance

Training it took roughly 4.1 × 10²² FLOP of computation, on NVIDIA V100 — a measure of what producing the model cost, not of how fast it answers.

Around 1,001,000,000,000 tokens went into training it.

Step by step

How to choose a GPU for RedPajama-INCITE-7B-Base

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 RedPajama-INCITE-7B-Base — around 4.5 GB at IQ4_XS. Capacity is the gate — a card either holds it or it does not.
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 RedPajama-INCITE-7B-Base stops fitting a card that seemed fine.
03

Set a quality floor

Each card runs the least-compressed copy it can hold — IQ4_XS on the smallest card that fits. Setting a floor drops the cards that only manage RedPajama-INCITE-7B-Base by squeezing it further than you would want.
04

Sort by speed

The speed ordering for RedPajama-INCITE-7B-Base is effectively an ordering by memory bandwidth, which is why the B200 tops it at 491 tok/s.
05

Look at the headroom, not just the fit

The fit column separates cards that just manage RedPajama-INCITE-7B-Base from those with room to spare. Buy for the second if the context might grow.
06

Open the card you have settled on

Each card page repeats this sweep for every model we hold. It answers what else the hardware is good for, beyond RedPajama-INCITE-7B-Base.

Answers

RedPajama-INCITE-7B-Base — common questions

How many parameters does RedPajama-INCITE-7B-Base have?

RedPajama-INCITE-7B-Base has 6.9B parameters. 6.9b. 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 RedPajama-INCITE-7B-Base?

RedPajama-INCITE-7B-Base was published by Together, based in United States of America, categorised as industry.

When was RedPajama-INCITE-7B-Base released?

RedPajama-INCITE-7B-Base 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 RedPajama-INCITE-7B-Base used for?

RedPajama-INCITE-7B-Base works in Language, and is recorded as handling chat. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.

Where can I download RedPajama-INCITE-7B-Base?

The weights for RedPajama-INCITE-7B-Base are published, though we do not hold a repository link for it. This site calculates hardware requirements rather than hosting model files.

How much compute was used to train RedPajama-INCITE-7B-Base?

Around 4.1 × 10²² FLOP, on NVIDIA V100. 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 RedPajama-INCITE-7B-Base 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 RedPajama-INCITE-7B-Base is rarely worth using — the nearest miss we calculate is short by 1.3 GB. Every figure here assumes the whole model is on the card.

Would two GPUs run RedPajama-INCITE-7B-Base faster?

Two cards buy memory rather than speed. That matters for RedPajama-INCITE-7B-Base only if one card cannot hold it — 589 can, so a second adds little.

Why does the quantisation differ between cards for RedPajama-INCITE-7B-Base?

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

How accurate are these RedPajama-INCITE-7B-Base speed estimates?

They are calculated from specifications rather than measured, and each carries a range — 295–786 tok/s on the B200, 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 RedPajama-INCITE-7B-Base?

The smallest card in our catalogue that holds RedPajama-INCITE-7B-Base is the Tesla K20c, with 5 GB of memory. It runs the model at IQ4_XS using about 4.5 GB, and produces roughly 26.7 tokens per second. 589 cards in total can run it.

How fast is RedPajama-INCITE-7B-Base on a GPU?

It depends on the card. The quickest we calculate is a B200 at about 491 tokens per second; the slowest that still runs it manages considerably less. Reading speed is around ten tokens per second, and 562 of the cards that can run RedPajama-INCITE-7B-Base clear that.

How much VRAM does RedPajama-INCITE-7B-Base need?

About 4.5 GB at IQ4_XS 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 RedPajama-INCITE-7B-Base on a 8 GB GPU?

Yes. A CMP 170HX 8 GB with 8 GB runs it at Q6_K, using about 6.5 GB and generating roughly 133 tokens per second — a tight fit.

Can I run RedPajama-INCITE-7B-Base on a 12 GB GPU?

Yes. A GeForce RTX 3080 Ti with 12 GB runs it at Q8_0, using about 8.1 GB and generating roughly 56.0 tokens per second — a comfortable fit.

Can I run RedPajama-INCITE-7B-Base on a 16 GB GPU?

Yes. A Tesla V100 SXM2 16 GB with 16 GB runs it at Q8_0, using about 8.1 GB and generating roughly 69.4 tokens per second — a comfortable fit.

Can I run RedPajama-INCITE-7B-Base on a 24 GB GPU?

Yes. A GeForce RTX 5090 D V2 with 24 GB runs it at Q8_0, using about 8.1 GB and generating roughly 82.3 tokens per second — a comfortable fit.

Is RedPajama-INCITE-7B-Base open source?

Its weights are published, so RedPajama-INCITE-7B-Base 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.

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