Multi-Token Prediction 7B TPS calculator

Open weights Facebook AI Research 6.7B parameters April 2024

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 · 27.4 tok/s

Fastest card

B200

506 tok/s · 180 GB

Which GPUs can run Multi-Token Prediction 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
506 tok/s 303–809 · low confidence	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	7.9 GB	Q8_0	Comfortable
506 tok/s 303–809 · low confidence	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	7.9 GB	Q8_0	Comfortable
404 tok/s 242–646 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	7.9 GB	Q8_0	Comfortable
404 tok/s 242–646 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	7.9 GB	Q8_0	Comfortable
323 tok/s 194–517 · low confidence	Radeon Instinct MI300 AMD	128 GB	6,550 GB/s	Jan 2023	7.9 GB	Q8_0	Comfortable
309 tok/s 185–495 · low confidence	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	7.9 GB	Q8_0	Comfortable
309 tok/s 185–495 · low confidence	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	7.9 GB	Q8_0	Comfortable
296 tok/s 178–473 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	7.9 GB	Q8_0	Comfortable
263 tok/s 158–420 · low confidence	Radeon Instinct MI300A AMD	128 GB	5,325 GB/s	Dec 2023	7.9 GB	Q8_0	Comfortable
263 tok/s 158–420 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	7.9 GB	Q8_0	Comfortable
263 tok/s 158–420 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	7.9 GB	Q8_0	Comfortable
249 tok/s 149–399 · low confidence	H100 NVL 94 GB NVIDIA	94 GB	3,940 GB/s	Mar 2023	7.9 GB	Q8_0	Comfortable
212 tok/s 127–340 · low confidence	H100 PCIe 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	7.9 GB	Q8_0	Comfortable
212 tok/s 127–340 · low confidence	H100 SXM5 80 GB NVIDIA	80 GB	3,360 GB/s	Oct 2022	7.9 GB	Q8_0	Comfortable
212 tok/s 127–340 · low confidence	H100 SXM5 94 GB NVIDIA	94 GB	3,360 GB/s	Mar 2023	7.9 GB	Q8_0	Comfortable
212 tok/s 127–340 · low confidence	H100 SXM5 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	7.9 GB	Q8_0	Comfortable
212 tok/s 127–340 · low confidence	H800 SXM5 NVIDIA	80 GB	3,360 GB/s	Mar 2023	7.9 GB	Q8_0	Comfortable
162 tok/s 97–259 · low confidence	Radeon Instinct MI250 AMD	128 GB	3,280 GB/s	Nov 2021	7.9 GB	Q8_0	Comfortable
162 tok/s 97–259 · low confidence	Radeon Instinct MI250X AMD	128 GB	3,280 GB/s	Nov 2021	7.9 GB	Q8_0	Comfortable
137 tok/s 82–219 · low confidence	CMP 170HX 8 GB NVIDIA	8 GB	1,490 GB/s	Sep 2021	6.3 GB	Q6_K	Tight
135 tok/s 81–216 · low confidence	Data Center GPU Max 1550 Intel	128 GB	3,280 GB/s	Jan 2023	7.9 GB	Q8_0	Comfortable
132 tok/s 79–211 · low confidence	Data Center GPU Max Subsystem Intel	128 GB	3,210 GB/s	Jan 2023	7.9 GB	Q8_0	Comfortable
129 tok/s 77–206 · low confidence	A100 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Nov 2020	7.9 GB	Q8_0	Comfortable
129 tok/s 77–206 · low confidence	A100X NVIDIA	80 GB	2,040 GB/s	Jun 2021	7.9 GB	Q8_0	Comfortable
129 tok/s 77–206 · low confidence	A800 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Aug 2022	7.9 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: Facebook AI Research
Organisation type: Industry
Country: United States of America, France
Published: 30 April 2024
Authors: Fabian Gloeckle, Badr Youbi Idrissi, Baptiste Rozière, David Lopez-Paz, Gabriel Synnaeve

What it does

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

Domain: Language
Task: Code generation

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: 6.7B
Training data: tokens
Epochs: 4

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 × 10²³ FLOP
How it was established: Hardware

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 80 GB,NVIDIA H100 SXM5 80GB

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)
Training code: Unreleased

How it is classified

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

Likely above 10²³ FLOP: Yes
Record confidence: Likely

Sources

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

Reference: Better & Faster Large Language Models via Multi-token Prediction
Last updated: 28 November 2025

The extremes

The ten fastest GPUs that run Multi-Token Prediction 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 Multi-Token Prediction 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

4.4 GB

Fastest

506 tok/s

Multi-Token Prediction 7B is small enough at 6.7B 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, IQ4_XS compression, roughly 27.4 tokens per second.

At the other end, a B200 generates roughly 506 tokens per second on it, on the strength of 8,000 GB/s of memory bandwidth.

About this model

Multi-Token Prediction 7B was published by Facebook AI Research, in United States of America, in April 2024. The organisation is categorised as industry.

It works in Language, and is recorded as doing code generation.

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

How fast it runs, and why

The median result is around 27.3 tokens per second; 562 cards produce text faster than most people read it.

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.

Training and provenance

Training it took roughly 3.8 × 10²³ FLOP of computation, on NVIDIA A100 SXM4 80 GB,NVIDIA H100 SXM5 80GB — a measure of what producing the model cost, not of how fast it answers.

Step by step

How to choose a GPU for Multi-Token Prediction 7B

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 Multi-Token Prediction 7B — around 4.4 GB at IQ4_XS. That figure, not the card's headline performance, is what decides whether it runs.
02

Decide how long your conversations run

The conversation occupies memory too, and grows as it goes. Set the slider to the length you expect: at long context Multi-Token Prediction 7B can slip off a card that handles short questions easily.
03

Choose how far you will compress it

The quantisation column varies by card, because a bigger card holds a more accurate copy of Multi-Token Prediction 7B — IQ4_XS on the smallest card that fits. Set a floor to hold the comparison at one level.
04

Rank by throughput rather than spec sheet

Sort by speed to see how cards rank for Multi-Token Prediction 7B. It will not match a gaming ordering — generation is bound by memory bandwidth, which is why the B200 tops it at 506 tok/s.
05

Read the fit column last

A tight fit runs Multi-Token Prediction 7B 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 Multi-Token Prediction 7B is settled.

Answers

Multi-Token Prediction 7B — common questions

Can I run Multi-Token Prediction 7B on a 8 GB GPU?

Yes. A CMP 170HX 8 GB with 8 GB runs it at Q6_K, using about 6.3 GB and generating roughly 137 tokens per second — a tight fit.

Can I run Multi-Token Prediction 7B on a 12 GB GPU?

Yes. A GeForce RTX 3080 Ti with 12 GB runs it at Q8_0, using about 7.9 GB and generating roughly 57.7 tokens per second — a comfortable fit.

Can I run Multi-Token Prediction 7B on a 16 GB GPU?

Yes. A Tesla V100 SXM2 16 GB with 16 GB runs it at Q8_0, using about 7.9 GB and generating roughly 71.4 tokens per second — a comfortable fit.

Can I run Multi-Token Prediction 7B on a 24 GB GPU?

Yes. A GeForce RTX 5090 D V2 with 24 GB runs it at Q8_0, using about 7.9 GB and generating roughly 84.7 tokens per second — a comfortable fit.

Is Multi-Token Prediction 7B open source?

Its weights are published, so Multi-Token Prediction 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 Multi-Token Prediction 7B have?

Multi-Token Prediction 7B has 6.7B parameters. 6.7B (“7B”). 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 Multi-Token Prediction 7B?

Multi-Token Prediction 7B was published by Facebook AI Research, based in United States of America, categorised as industry.

When was Multi-Token Prediction 7B released?

Multi-Token Prediction 7B was published in April 2024. 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 Multi-Token Prediction 7B used for?

Multi-Token Prediction 7B works in Language, and is recorded as handling code generation. These are the areas it was designed around; they describe intent rather than a hard boundary.

Where can I download Multi-Token Prediction 7B?

The weights for Multi-Token Prediction 7B 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 Multi-Token Prediction 7B?

Around 3.8 × 10²³ FLOP, on NVIDIA A100 SXM4 80 GB,NVIDIA H100 SXM5 80GB. 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 Multi-Token Prediction 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 Multi-Token Prediction 7B is rarely worth using — the nearest miss we calculate is short by 1.2 GB. Every figure here assumes the whole model is on the card.

Would two GPUs run Multi-Token Prediction 7B faster?

A second card roughly doubles the memory available but not the generation rate. With 589 cards already able to run Multi-Token Prediction 7B alone, the case for pairing is weak.

Why does the quantisation differ between cards for Multi-Token Prediction 7B?

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

How accurate are these Multi-Token Prediction 7B speed estimates?

These are estimates with real error bars. The fastest result here, 303–809 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 Multi-Token Prediction 7B?

The smallest card in our catalogue that holds Multi-Token Prediction 7B is the Tesla K20c, with 5 GB of memory. It runs the model at IQ4_XS using about 4.4 GB, and produces roughly 27.4 tokens per second. 589 cards in total can run it.

How fast is Multi-Token Prediction 7B on a GPU?

It depends on the card. The quickest we calculate is a B200 at about 506 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 Multi-Token Prediction 7B clear that.

How much VRAM does Multi-Token Prediction 7B need?

About 4.4 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.

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