Llama 4 Maverick TPS calculator

Open weights Meta AI 400B 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

6 cards that can run it

818 cards we hold specifications for

Smallest card that fits

Radeon Instinct MI300X

192 GB · Q3_K_M · 65.9 tok/s

Fastest card

B300

109 tok/s · 288 GB

Which GPUs can run Llama 4 Maverick?

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

6 cards match

Calculating

					Needs	Quantisation	Fit
109 tok/s 65–174 · low confidence	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	214.8 GB	Q4_K_M	Comfortable
86.8 tok/s 52–139 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	214.8 GB	Q4_K_M	Comfortable
86.8 tok/s 52–139 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	214.8 GB	Q4_K_M	Comfortable
65.9 tok/s 40–105 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	168.2 GB	Q3_K_M	Tight
65.9 tok/s 40–105 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	168.2 GB	Q3_K_M	Tight
63.6 tok/s 38–102 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	214.8 GB	Q4_K_M	Tight

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: Meta AI
Organisation type: Industry
Country: United States of America
Published: 5 April 2025

What it does

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

Domain: Multimodal, Language, Vision
Task: Chat, Code generation, Visual question answering, Language modeling/generation, Question answering

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: 400B
Training data: 30,000,000,000,000 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.

Training compute: 2.2 × 10²⁴ FLOP

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 (restricted use)
Training code: Unreleased
Hugging Face: meta-llama

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
Why it is tracked: Discretionary
Record confidence: Likely

Sources

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

Reference: The Llama 4 herd: The beginning of a new era of natively multimodal AI innovation
Last updated: 28 November 2025

The extremes

The ten fastest GPUs that run Llama 4 Maverick

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 Llama 4 Maverick

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

Radeon Instinct MI300X

Memory needed

168.2 GB

Fastest

109 tok/s

Llama 4 Maverick reaches a parameter count of 400B. That is beyond what any single graphics card holds. Running it means either splitting it across several cards or renting hardware built for the job, and every card able to hold it alone is a datacentre part. The number that can: 6.

The entry point is Radeon Instinct MI300X, with a memory capacity of 192 GB, running it at a compression of Q3_K_M and producing around 65.9 tokens per second.

The fastest we calculate for it is B300, generating roughly 109 tokens per second on the strength of a memory bandwidth of 8,000 GB/s.

What this model is

Llama 4 Maverick was published by Meta AI, in the country recorded as United States of America, during April 2025. The publishing organisation is categorised as industry.

It works in the domain of Multimodal, Language, Vision, and is recorded as performing the task of chat, Code generation, Visual question answering, Language modeling/generation, Question answering.

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

What decides the speed

The median result is around 76.3 tokens per second. Producing text faster than most people read it: 6 of them.

Mixture-of-experts routing is why the speeds here look high for the parameter count. Only a fraction is read per token, but the whole thing has to be loaded.

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

Producing it required arithmetic totalling around 2.2 × 10²⁴ FLOP. That figure measures what producing the model cost, and has no bearing on how fast it answers.

It was trained on a corpus of about 30,000,000,000,000 tokens of text.

Its inclusion criterion: discretionary.

Step by step

How to choose a GPU for Llama 4 Maverick

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 able to hold Llama 4 Maverick, needing around 168.2 GB at a compression of Q3_K_M. That figure, not the headline performance of a card, is what decides whether it runs.
02

Match the context to your actual use

Set the context to what you will actually use. The cache grows with the conversation, and it is the usual reason a card that seemed fine stops fitting Llama 4 Maverick.
03

Decide how much compression you will accept

The quantisation column varies by card, because a bigger card holds a more accurate copy, reaching a compression of Q3_K_M on the smallest card that fits. Setting a minimum quality drops the cards that only manage it by squeezing further than you would want, and holds the comparison at one level.
04

Rank by throughput rather than spec sheet

Ranking by tokens per second follows memory bandwidth rather than core counts, for Llama 4 Maverick. It will not match a gaming ordering, because generation is bound by memory bandwidth. The card topping the list is B300, at 109 tok/s.
05

Read the fit column last

A tight fit runs, but leaves nothing spare for a longer conversation, in the case of Llama 4 Maverick. Comfortable means you can grow the context later. That difference matters more than a few tokens per second, so buy for comfortable if you expect to.
06

See what else that card runs

Each card page repeats this sweep for every model we hold, answering what else the hardware is good for beyond Llama 4 Maverick.

Answers

Llama 4 Maverick — common questions

Llama 4 Maverick— how much compute was used to train it?

Training consumed around 2.2 × 10²⁴ FLOP. 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.

Llama 4 Maverick— can I run it 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 model is rarely worth using. The nearest miss we calculate falls short by 52.8 GB. Every figure here assumes the whole model is resident on the card.

Llama 4 Maverick— would two GPUs run it faster?

Capacity adds across cards; throughput does not. The number of cards already holding it on their own: 6. So a second card is rarely the answer here.

Llama 4 Maverick— why does the quantisation differ between cards?

A larger card holds a more accurate copy. The number of compression levels used across the cards that run it: 2. Bigger cards get the more accurate version, and the quality floor above pins the comparison to one level.

Llama 4 Maverick— how accurate are these speed estimates?

They are calculated from specifications rather than measured, and each carries a range. One example: 65–174 tok/s on B300. The same model and card vary by thirty to fifty per cent depending on the inference software and its version.

Llama 4 Maverick— what GPU do I need to run it?

The smallest card in our catalogue that holds it is Radeon Instinct MI300X, with a memory capacity of 192 GB. It runs the model at a compression of Q3_K_M using about 168.2 GB, and produces roughly 65.9 tokens per second. The number of cards able to run it in total: 6.

Llama 4 Maverick— how fast is it on a GPU?

It depends on the card. The quickest we calculate is B300, at about 109 tokens per second; the slowest that still runs it manages considerably less. Reading speed is around ten tokens per second, and the number of cards clearing that: 6.

Llama 4 Maverick— how much VRAM does it need?

It needs about 168.2 GB at a compression of Q3_K_M, 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.

Llama 4 Maverick— is it open source?

Its weights are published, so it 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.

Llama 4 Maverick— how many parameters does it have?

It has a parameter count of 400B. "Llama 4 Maverick models have 17B active parameters and 400B total parameters." https://ai.meta.com/blog/llama-4-multimodal-intelligence/. 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.

Llama 4 Maverick— who created it?

It was published by Meta AI, based in United States of America, an organisation categorised as industry.

Llama 4 Maverick— when was it released?

It was published in April 2025.

Llama 4 Maverick— what is it used for?

It works in the domain of Multimodal, Language, Vision, and is recorded as handling the task of chat, Code generation, Visual question answering, Language modeling/generation, Question answering. A model can carry several of each, so these are the areas it was built for rather than a limit on what it will attempt.

Llama 4 Maverick— where can I download it?

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

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