Grok-1 TPS calculator

Open weights xAI 314B parameters November 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

7 cards that can run it

818 cards we hold specifications for

Smallest card that fits

B200

180 GB · Q3_K_M · 29.1 tok/s

Fastest card

B200

29.1 tok/s · 180 GB

Which GPUs can run Grok-1?

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

7 cards match

Calculating

					Needs	Quantisation	Fit
29.1 tok/s 17–47 · low confidence	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	154.1 GB	Q3_K_M	Tight
19.3 tok/s 12–31 · low confidence	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	227.2 GB	Q5_K_M	Tight
15.4 tok/s 9–25 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	227.2 GB	Q5_K_M	Tight
15.4 tok/s 9–25 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	227.2 GB	Q5_K_M	Tight
13.8 tok/s 8–22 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	172.4 GB	IQ4_XS	Tight
13.8 tok/s 8–22 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	172.4 GB	IQ4_XS	Tight
11.3 tok/s 7–18 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	227.2 GB	Q5_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: xAI
Organisation type: Industry
Country: United States of America
Published: 4 November 2023

What it does

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

Domain: Language
Task: Language modeling, 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: 314B
Training data: 6,200,000,000,000 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: 2.9 × 10²⁴ FLOP
How it was established: Benchmarks
Plausible range: 2 × 10²⁴ – 7 × 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 (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.

Foundation model: Yes
Likely above 10²³ FLOP: Yes
Why it is tracked: Training cost
Record confidence: Likely

Sources

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

Reference: Announcing Grok
Last updated: 18 December 2025

The extremes

The ten fastest GPUs that run Grok-1

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 Grok-1

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 it takes to run this model

Minimum card

B200

Memory needed

154.1 GB

Fastest

29.1 tok/s

Grok-1 reaches a parameter count of 314B. 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: 7.

The smallest card that holds it is B200, with a memory capacity of 180 GB, running it at a compression of Q3_K_M and producing around 29.1 tokens per second.

At the other end sits B200, generating roughly 29.1 tokens per second on the strength of a memory bandwidth of 8,000 GB/s.

About this model

Grok-1 was published by xAI, in the country recorded as United States of America, during November 2023. The category the publisher falls under is industry.

It works in the domain of Language, and is recorded as performing the task of language modeling, 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.

How fast it runs, and why

The median result is around 15.4 tokens per second. Producing text faster than most people read it: 7 of them.

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.

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.

What went into building it

The training run consumed about 2.9 × 10²⁴ FLOP. That figure measures what producing the model cost, and has no bearing on how fast it answers.

The training set ran to roughly 6,200,000,000,000 tokens of text.

Its inclusion criterion: training cost.

Step by step

How to choose a GPU for Grok-1

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

Start from what it actually needs, which is the requirement of Grok-1, needing around 154.1 GB at a compression of Q3_K_M. No amount of processing power compensates for a card that cannot hold it.
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 Grok-1.
03

Choose how far you will compress it

Compression is what makes a model fit smaller cards, at some cost in accuracy, 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

Compare tokens per second, not specifications

Sort by speed to see how cards rank for Grok-1. It will not match a gaming ordering, because generation is bound by memory bandwidth. The card topping the list is B200, at 29.1 tok/s.
05

Look at the headroom, not just the fit

A tight fit runs, but leaves nothing spare for a longer conversation, in the case of Grok-1. 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

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. A card is usually bought for more than one model, so it is worth a look before buying for Grok-1.

Answers

Grok-1 — common questions

Grok-1— why does the quantisation differ between cards?

Because capacity varies, so does how hard it has to be squeezed. The number of distinct levels in the table above: 3. Bigger cards get the more accurate version, and the quality floor above pins the comparison to one level.

Grok-1— how accurate are these speed estimates?

They are calculated from specifications rather than measured, and each carries a range. One example: 17–47 tok/s on B200. The same model and card vary by thirty to fifty per cent depending on the inference software and its version.

Grok-1— what GPU do I need to run it?

The smallest card in our catalogue that holds it is B200, with a memory capacity of 180 GB. It runs the model at a compression of Q3_K_M using about 154.1 GB, and produces roughly 29.1 tokens per second. The number of cards able to run it in total: 7.

Grok-1— how fast is it on a GPU?

It depends on the card. The quickest we calculate is B200, at about 29.1 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: 7.

Grok-1— how much VRAM does it need?

It needs about 154.1 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.

Grok-1— 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.

Grok-1— how many parameters does it have?

It has a parameter count of 314B. "314B parameter Mixture-of-Experts model with 25% of the weights active on a given token". So effectively 78B parameters Mixture of 8 experts: https://github.com/xai-org/grok-1. 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.

Grok-1— who created it?

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

Grok-1— when was it released?

It was published in November 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.

Grok-1— what is it used for?

It works in the domain of Language, and is recorded as handling the task of language modeling, Chat. These are the areas it was designed around; they describe intent rather than a hard boundary.

Grok-1— where can I download it?

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

Grok-1— how much compute was used to train it?

Training consumed around 2.9 × 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.

Grok-1— can I run it if it does not fit in my GPU?

It can be split between the card and system memory, but it generates painfully slowly that way. The nearest miss we calculate falls short by 63.8 GB. Every figure here assumes the whole model is resident on the card.

Grok-1— would two GPUs run it faster?

Two cards buy memory rather than speed, which matters only if one card cannot hold it. The number that can: 7. So a second card is rarely the answer here.

Source

Original publication

Record last updated 18 December 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