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 of 818 cards that can run it

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

A longer conversation needs more memory, which can push this model off smaller cards.

Hides cards that would only fit the model by compressing it below this point.

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

"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

Training data
6,200,000,000,000 tokens

(Speculative confidence, see compute notes)

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

"On these benchmarks, Grok-1 displayed strong results, surpassing all other models in its compute class, including ChatGPT-3.5 and Inflection-1. It is only surpassed by models that were trained with a significantly larger amount of training data and compute resources like GPT-4" Per table, Grok-1 is surpassed by Palm 2, Claude 2, GPT-4, so it required less compute than these three models. Palm 2 was trained on 7e24 FLOP. GPT-3.5 is ~2.6e24. Inflection-1's compute is not public/known by us but …

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

apache 2.0 https://github.com/xai-org/grok-1

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

"On these benchmarks, Grok-1 displayed strong results, surpassing all other models in its compute class, including ChatGPT-3.5 and Inflection-1"

Record confidence
Likely

Sources

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

Reference
Announcing Grok
Last updated
18 December 2025

What the numbers mean

What it takes to run this model

Minimum card

B200

Memory needed

154.1 GB

Fastest

29.1 tok/s

At 314B parameters, Grok-1 is beyond what any single graphics card holds. Running it means either splitting it across several cards or renting hardware built for the job — 7 of the cards we track can hold it on their own, and all of them are datacentre parts.

The smallest card that holds it is the B200 with 180 GB, running it at Q3_K_M and producing around 29.1 tokens per second.

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

About this model

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

It works in Language, and is recorded as doing 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; 7 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.

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 describes the cost of creating it and has no bearing on how quickly it generates text.

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

Its inclusion criterion is 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.

  1. 01

    Check what it needs before anything else

    Look at what Grok-1 actually needs — around 154.1 GB at Q3_K_M. No amount of processing power compensates for a card that cannot hold it.

  2. 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 Grok-1 stops fitting a card that seemed fine.

  3. 03

    Choose how far you will compress it

    Compression is what makes Grok-1 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.

  4. 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 — generation is bound by memory bandwidth, which is why the B200 tops it at 29.1 tok/s.

  5. 05

    Look at the headroom, not just the fit

    A tight fit runs Grok-1 but leaves nothing spare for a longer conversation; comfortable has headroom. If you expect to grow the context, buy for comfortable.

  6. 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 Grok-1 alone — a card is usually bought for more than one model.

Answers

Grok-1 — common questions

01

Why does the quantisation differ between cards for Grok-1?

Because capacity varies, so does how hard Grok-1 has to be squeezed — 3 distinct levels appear in the table above. Set a minimum quality to compare at one.

02

How accurate are these Grok-1 speed estimates?

They are calculated from specifications rather than measured, and each carries a range — 17–47 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.

03

What GPU do I need to run Grok-1?

The smallest card in our catalogue that holds Grok-1 is the B200, with 180 GB of memory. It runs the model at Q3_K_M using about 154.1 GB, and produces roughly 29.1 tokens per second. 7 cards in total can run it.

04

How fast is Grok-1 on a GPU?

It depends on the card. The quickest we calculate is a 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 7 of the cards that can run Grok-1 clear that.

05

How much VRAM does Grok-1 need?

About 154.1 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.

06

Is Grok-1 open source?

Its weights are published, so Grok-1 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.

07

How many parameters does Grok-1 have?

Grok-1 has 314B parameters. "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.

08

Who created Grok-1?

Grok-1 was published by xAI, based in United States of America, categorised as industry.

09

When was Grok-1 released?

Grok-1 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.

10

What is Grok-1 used for?

Grok-1 works in Language, and is recorded as handling language modeling, Chat. These are the areas it was designed around; they describe intent rather than a hard boundary.

11

Where can I download Grok-1?

The weights for Grok-1 are published, though we do not hold a repository link for it. This site calculates hardware requirements rather than hosting model files.

12

How much compute was used to train Grok-1?

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.

13

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

It can be split between the card and system memory, but Grok-1 generates painfully slowly that way — the nearest miss we calculate is short by 63.8 GB. Nothing on this page assumes offloading.

14

Would two GPUs run Grok-1 faster?

Two cards buy memory rather than speed. That matters for Grok-1 only if one card cannot hold it — 7 can, so a second adds little.

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.