minChatGPT TPS calculator

Open weights Stanford University 1.6B parameters March 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

818 cards that can run it

818 cards we hold specifications for

Smallest card that fits

Tesla C1080

4 GB · Q8_0 · 22.5 tok/s

Fastest card

B200

2,067 tok/s · 180 GB

Which GPUs can run minChatGPT?

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

818 cards match

Calculating

					Needs	Quantisation	Fit
2,067 tok/s 1,240–3,308 · low confidence	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	2.5 GB	Q8_0	Comfortable
2,067 tok/s 1,240–3,308 · low confidence	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	2.5 GB	Q8_0	Comfortable
1,651 tok/s 990–2,641 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	2.5 GB	Q8_0	Comfortable
1,651 tok/s 990–2,641 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	2.5 GB	Q8_0	Comfortable
1,320 tok/s 792–2,112 · low confidence	Radeon Instinct MI300 AMD	128 GB	6,550 GB/s	Jan 2023	2.5 GB	Q8_0	Comfortable
1,264 tok/s 758–2,022 · low confidence	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	2.5 GB	Q8_0	Comfortable
1,264 tok/s 758–2,022 · low confidence	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	2.5 GB	Q8_0	Comfortable
1,209 tok/s 726–1,935 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	2.5 GB	Q8_0	Comfortable
1,073 tok/s 644–1,717 · low confidence	Radeon Instinct MI300A AMD	128 GB	5,325 GB/s	Dec 2023	2.5 GB	Q8_0	Comfortable
1,073 tok/s 644–1,717 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	2.5 GB	Q8_0	Comfortable
1,073 tok/s 644–1,717 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	2.5 GB	Q8_0	Comfortable
1,018 tok/s 611–1,629 · low confidence	H100 NVL 94 GB NVIDIA	94 GB	3,940 GB/s	Mar 2023	2.5 GB	Q8_0	Comfortable
868 tok/s 521–1,389 · low confidence	H100 PCIe 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	2.5 GB	Q8_0	Comfortable
868 tok/s 521–1,389 · low confidence	H100 SXM5 80 GB NVIDIA	80 GB	3,360 GB/s	Oct 2022	2.5 GB	Q8_0	Comfortable
868 tok/s 521–1,389 · low confidence	H100 SXM5 94 GB NVIDIA	94 GB	3,360 GB/s	Mar 2023	2.5 GB	Q8_0	Comfortable
868 tok/s 521–1,389 · low confidence	H100 SXM5 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	2.5 GB	Q8_0	Comfortable
868 tok/s 521–1,389 · low confidence	H800 SXM5 NVIDIA	80 GB	3,360 GB/s	Mar 2023	2.5 GB	Q8_0	Comfortable
661 tok/s 397–1,058 · low confidence	Radeon Instinct MI250 AMD	128 GB	3,280 GB/s	Nov 2021	2.5 GB	Q8_0	Comfortable
661 tok/s 397–1,058 · low confidence	Radeon Instinct MI250X AMD	128 GB	3,280 GB/s	Nov 2021	2.5 GB	Q8_0	Comfortable
551 tok/s 331–881 · low confidence	Data Center GPU Max 1550 Intel	128 GB	3,280 GB/s	Jan 2023	2.5 GB	Q8_0	Comfortable
539 tok/s 324–863 · low confidence	Data Center GPU Max Subsystem Intel	128 GB	3,210 GB/s	Jan 2023	2.5 GB	Q8_0	Comfortable
527 tok/s 316–843 · low confidence	A100 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Nov 2020	2.5 GB	Q8_0	Comfortable
527 tok/s 316–843 · low confidence	A100X NVIDIA	80 GB	2,040 GB/s	Jun 2021	2.5 GB	Q8_0	Comfortable
527 tok/s 316–843 · low confidence	A800 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Aug 2022	2.5 GB	Q8_0	Comfortable
527 tok/s 316–843 · low confidence	H100 CNX NVIDIA	80 GB	2,040 GB/s	Mar 2023	2.5 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: Stanford University
Organisation type: Academia
Country: United States of America
Published: 24 March 2023
Authors: Yanjia Li

What it does

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

Domain: Language
Task: Chat
Base model: GPT-2 (1.5B)

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: 1.6B
Training data: 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.

Fine-tuning compute: 1.6 × 10¹⁵ 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)

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.

Reference: Minimum Generative Pre-trained Transformer with Human Feedback
Last updated: 28 November 2025

The extremes

The ten fastest GPUs that run minChatGPT

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 minChatGPT

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 C1080

Memory needed

2.5 GB

Fastest

2,067 tok/s

minChatGPT is small enough at 1.6B parameters that hardware is rarely the obstacle — 818 of the cards we track can run it, including cards several years old.

The least hardware that works is a Tesla C1080. Its 4 GB is enough at Q8_0 compression, giving roughly 22.5 tokens per second.

A B200 is the fastest we calculate for it: about 2,067 tokens per second, from 8,000 GB/s of memory bandwidth.

About this model

minChatGPT was published by Stanford University, in United States of America, in March 2023. academia is the category the publisher falls under.

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

Its starting point was GPT-2 (1.5B) — most models at this scale are adapted from an existing base rather than built from nothing.

The weights being open is what puts this page in the calculator rather than only in the catalogue: it is a model you can actually hold.

How fast it runs, and why

Across every card that can run it, the middle of the range is about 58.1 tokens per second, and 794 of them clear the ten tokens per second that roughly matches reading speed.

Being dense, it reads all of itself per token, which is why the ordering by speed below follows the ordering by memory bandwidth so closely.

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.

Step by step

How to choose a GPU for minChatGPT

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

Look at what minChatGPT actually needs — around 2.5 GB at Q8_0. No amount of processing power compensates for a card that cannot hold it.
02

Decide how long your conversations run

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

Set a quality floor

Each card runs the least-compressed copy it can hold — Q8_0 on the smallest card that fits. Setting a floor drops the cards that only manage minChatGPT by squeezing it further than you would want.
04

Rank by throughput rather than spec sheet

Ranking by tokens per second for minChatGPT follows memory bandwidth, not core counts, which is why the B200 tops it at 2,067 tok/s.
05

Look at the headroom, not just the fit

A tight fit runs minChatGPT 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 minChatGPT is settled.

Answers

minChatGPT — common questions

Can I run minChatGPT on a 8 GB GPU?

Yes. A CMP 170HX 8 GB with 8 GB runs it at Q8_0, using about 2.5 GB and generating roughly 385 tokens per second — a comfortable fit.

Can I run minChatGPT on a 12 GB GPU?

Yes. A GeForce RTX 3080 Ti with 12 GB runs it at Q8_0, using about 2.5 GB and generating roughly 236 tokens per second — a comfortable fit.

Can I run minChatGPT on a 16 GB GPU?

Yes. A Tesla V100 SXM2 16 GB with 16 GB runs it at Q8_0, using about 2.5 GB and generating roughly 292 tokens per second — a comfortable fit.

Can I run minChatGPT on a 24 GB GPU?

Yes. A GeForce RTX 5090 D V2 with 24 GB runs it at Q8_0, using about 2.5 GB and generating roughly 346 tokens per second — a comfortable fit.

Is minChatGPT open source?

Its weights are published, so minChatGPT 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 minChatGPT have?

minChatGPT has 1.6B parameters. “We used two different models, GPT-2 Medium and GPT-2 XL for our supervised fine-tuning to verify our trainer is implemented correctly… We fine-tuned the model for about 100K step with a batch size 2 and learning rate of 1e-4 with an Adam optimizer. It’s equivalent of about 3 epochs of our training dataset” (https://github.com/ethanyanjiali/minChatGPT/blob/main/report.pdf, page 4). GPT-2 XL has 1.639B parameters (https://github.com/ethanyanjiali/minChatGPT/blob/main/report.pdf, page 5). 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 minChatGPT?

minChatGPT was published by Stanford University, based in United States of America, categorised as academia.

When was minChatGPT released?

minChatGPT was published in March 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 minChatGPT used for?

minChatGPT 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 minChatGPT?

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

Can I run minChatGPT if it does not fit in my GPU?

It can be split between the card and system memory, but minChatGPT generates painfully slowly that way. Nothing on this page assumes offloading.

Would two GPUs run minChatGPT faster?

Two cards buy memory rather than speed. That matters for minChatGPT only if one card cannot hold it — 818 can, so a second adds little.

Why does the quantisation differ between cards for minChatGPT?

Each card is shown running the least-compressed copy it can hold, and minChatGPT appears at 1 different compression levels across the cards that fit it. Bigger cards get the more accurate version.

How accurate are these minChatGPT speed estimates?

They are calculated from specifications rather than measured, and each carries a range — 1,240–3,308 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 minChatGPT?

The smallest card in our catalogue that holds minChatGPT is the Tesla C1080, with 4 GB of memory. It runs the model at Q8_0 using about 2.5 GB, and produces roughly 22.5 tokens per second. 818 cards in total can run it.

How fast is minChatGPT on a GPU?

It depends on the card. The quickest we calculate is a B200 at about 2,067 tokens per second; the slowest that still runs it manages considerably less. Reading speed is around ten tokens per second, and 794 of the cards that can run minChatGPT clear that.

How much VRAM does minChatGPT need?

About 2.5 GB at Q8_0 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