TinyLlama-1.1B (1T token checkpoint) TPS calculator

Open weights Singapore University of Technology & Design 1.1B parameters October 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 of 818 cards that can run it

Smallest card that fits

Tesla C1080

4 GB · Q8_0 · 33.5 tok/s

Fastest card

B200

3,080 tok/s · 180 GB

Which GPUs can run TinyLlama-1.1B (1T token checkpoint)?

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
3,080 tok/s 1,848–4,928 · low confidence	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	1.9 GB	Q8_0	Comfortable
3,080 tok/s 1,848–4,928 · low confidence	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	1.9 GB	Q8_0	Comfortable
2,460 tok/s 1,476–3,935 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	1.9 GB	Q8_0	Comfortable
2,460 tok/s 1,476–3,935 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	1.9 GB	Q8_0	Comfortable
1,967 tok/s 1,180–3,147 · low confidence	Radeon Instinct MI300 AMD	128 GB	6,550 GB/s	Jan 2023	1.9 GB	Q8_0	Comfortable
1,883 tok/s 1,130–3,012 · low confidence	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	1.9 GB	Q8_0	Comfortable
1,883 tok/s 1,130–3,012 · low confidence	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	1.9 GB	Q8_0	Comfortable
1,802 tok/s 1,081–2,883 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	1.9 GB	Q8_0	Comfortable
1,599 tok/s 960–2,559 · low confidence	Radeon Instinct MI300A AMD	128 GB	5,325 GB/s	Dec 2023	1.9 GB	Q8_0	Comfortable
1,599 tok/s 960–2,559 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	1.9 GB	Q8_0	Comfortable
1,599 tok/s 960–2,559 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	1.9 GB	Q8_0	Comfortable
1,517 tok/s 910–2,427 · low confidence	H100 NVL 94 GB NVIDIA	94 GB	3,940 GB/s	Mar 2023	1.9 GB	Q8_0	Comfortable
1,294 tok/s 776–2,070 · low confidence	H100 PCIe 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	1.9 GB	Q8_0	Comfortable
1,294 tok/s 776–2,070 · low confidence	H100 SXM5 80 GB NVIDIA	80 GB	3,360 GB/s	Oct 2022	1.9 GB	Q8_0	Comfortable
1,294 tok/s 776–2,070 · low confidence	H100 SXM5 94 GB NVIDIA	94 GB	3,360 GB/s	Mar 2023	1.9 GB	Q8_0	Comfortable
1,294 tok/s 776–2,070 · low confidence	H100 SXM5 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	1.9 GB	Q8_0	Comfortable
1,294 tok/s 776–2,070 · low confidence	H800 SXM5 NVIDIA	80 GB	3,360 GB/s	Mar 2023	1.9 GB	Q8_0	Comfortable
985 tok/s 591–1,576 · low confidence	Radeon Instinct MI250 AMD	128 GB	3,280 GB/s	Nov 2021	1.9 GB	Q8_0	Comfortable
985 tok/s 591–1,576 · low confidence	Radeon Instinct MI250X AMD	128 GB	3,280 GB/s	Nov 2021	1.9 GB	Q8_0	Comfortable
821 tok/s 493–1,313 · low confidence	Data Center GPU Max 1550 Intel	128 GB	3,280 GB/s	Jan 2023	1.9 GB	Q8_0	Comfortable
803 tok/s 482–1,285 · low confidence	Data Center GPU Max Subsystem Intel	128 GB	3,210 GB/s	Jan 2023	1.9 GB	Q8_0	Comfortable
785 tok/s 471–1,257 · low confidence	A100 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Nov 2020	1.9 GB	Q8_0	Comfortable
785 tok/s 471–1,257 · low confidence	A100X NVIDIA	80 GB	2,040 GB/s	Jun 2021	1.9 GB	Q8_0	Comfortable
785 tok/s 471–1,257 · low confidence	A800 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Aug 2022	1.9 GB	Q8_0	Comfortable
785 tok/s 471–1,257 · low confidence	H100 CNX NVIDIA	80 GB	2,040 GB/s	Mar 2023	1.9 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: Singapore University of Technology & Design
Organisation type: Academia
Country: Singapore
Published: 1 October 2023
Authors: Peiyuan Zhang, Guangtao Zeng, Tianduo Wang, Wei Lu

What it does

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

Domain: Language
Task: Chat, Language modeling/generation, Translation, Question answering
Approach: Self-supervised learning

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: 1.1B
Training data: 1,000,000,000,000 tokens
Batch size: 2,000,000

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: 7.2 × 10²¹ FLOP
How it was established: Hardware,Operation counting

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 40 GB
Chips used: 16
Chip-hours: 11,520
Wall-clock time: 720 hours (30 days)
Hardware utilisation: MFU 56.0%
Power draw: 12.7 kW

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: Open source

How it is classified

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

Record confidence: Confident
Citations: 722

Sources

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

Reference: TinyLlama: An Open-Source Small Language Model
Last updated: 25 May 2026

The extremes

The ten fastest GPUs for TinyLlama-1.1B (1T token checkpoint)

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 TinyLlama-1.1B (1T token checkpoint)

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

Tesla C1080

Memory needed

1.9 GB

Fastest

3,080 tok/s

TinyLlama-1.1B (1T token checkpoint) is small enough at 1.1B parameters that hardware is rarely the obstacle — 818 of the cards we track can run it, including cards several years old.

The smallest card that holds it is the Tesla C1080 with 4 GB, running it at Q8_0 and producing around 33.5 tokens per second.

At the other end, a B200 generates roughly 3,080 tokens per second on it, on the strength of 8,000 GB/s of memory bandwidth.

About this model

TinyLlama-1.1B (1T token checkpoint) was published by Singapore University of Technology & Design, in Singapore, in October 2023. It comes out of academia.

It works in Language, and is recorded as doing chat, Language modeling/generation, Translation, Question answering.

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

Half the cards that hold it manage more than 86.5 tokens per second, and 799 exceed reading speed outright.

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.

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.

How it was trained

Producing it required around 7.2 × 10²¹ FLOP of arithmetic, on NVIDIA A100 SXM4 40 GB, which is a statement about the training budget rather than about inference.

Around 1,000,000,000,000 tokens went into training it.

Step by step

How to choose a GPU for TinyLlama-1.1B (1T token checkpoint)

The table above has already assessed every card we hold specifications for against this model. Getting to your answer takes six steps.

01

Start from the memory column

Look at what TinyLlama-1.1B (1T token checkpoint) actually needs — around 1.9 GB at Q8_0. No amount of processing power compensates for a card that cannot hold it.
02

Set the context length you will work at

The conversation occupies memory too, and grows as it goes. Set the slider to the length you expect: at long context TinyLlama-1.1B (1T token checkpoint) can slip off a card that handles short questions easily.
03

Set a quality floor

The quantisation column varies by card, because a bigger card holds a more accurate copy of TinyLlama-1.1B (1T token checkpoint) — Q8_0 on the smallest card that fits. Set a floor to hold the comparison at one level.
04

Sort by speed

Ranking by tokens per second for TinyLlama-1.1B (1T token checkpoint) follows memory bandwidth, not core counts, which is why the B200 tops it at 3,080 tok/s.
05

Check the fit verdict before buying

The fit column separates cards that just manage TinyLlama-1.1B (1T token checkpoint) from those with room to spare. Buy for the second if the context might grow.
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 TinyLlama-1.1B (1T token checkpoint) alone — a card is usually bought for more than one model.

Answers

TinyLlama-1.1B (1T token checkpoint) — common questions

Why does the quantisation differ between cards for TinyLlama-1.1B (1T token checkpoint)?

Each card is shown running the least-compressed copy it can hold, and TinyLlama-1.1B (1T token checkpoint) appears at 1 different compression levels across the cards that fit it. Bigger cards get the more accurate version.

How accurate are these TinyLlama-1.1B (1T token checkpoint) speed estimates?

Every figure is derived from memory bandwidth and model size, not benchmarked. That is why each is published as a range such as 1,848–4,928 tok/s on the B200 rather than a single number.

What GPU do I need to run TinyLlama-1.1B (1T token checkpoint)?

The smallest card in our catalogue that holds TinyLlama-1.1B (1T token checkpoint) is the Tesla C1080, with 4 GB of memory. It runs the model at Q8_0 using about 1.9 GB, and produces roughly 33.5 tokens per second. 818 cards in total can run it.

How fast is TinyLlama-1.1B (1T token checkpoint) on a GPU?

It depends on the card. The quickest we calculate is a B200 at about 3,080 tokens per second; the slowest that still runs it manages considerably less. Reading speed is around ten tokens per second, and 799 of the cards that can run TinyLlama-1.1B (1T token checkpoint) clear that.

How much VRAM does TinyLlama-1.1B (1T token checkpoint) need?

About 1.9 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.

Can I run TinyLlama-1.1B (1T token checkpoint) on a 8 GB GPU?

Yes. A CMP 170HX 8 GB with 8 GB runs it at Q8_0, using about 1.9 GB and generating roughly 574 tokens per second — a comfortable fit.

Can I run TinyLlama-1.1B (1T token checkpoint) on a 12 GB GPU?

Yes. A GeForce RTX 3080 Ti with 12 GB runs it at Q8_0, using about 1.9 GB and generating roughly 351 tokens per second — a comfortable fit.

Can I run TinyLlama-1.1B (1T token checkpoint) on a 16 GB GPU?

Yes. A Tesla V100 SXM2 16 GB with 16 GB runs it at Q8_0, using about 1.9 GB and generating roughly 435 tokens per second — a comfortable fit.

Can I run TinyLlama-1.1B (1T token checkpoint) on a 24 GB GPU?

Yes. A GeForce RTX 5090 D V2 with 24 GB runs it at Q8_0, using about 1.9 GB and generating roughly 516 tokens per second — a comfortable fit.

Is TinyLlama-1.1B (1T token checkpoint) open source?

Its weights are published, so TinyLlama-1.1B (1T token checkpoint) 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 TinyLlama-1.1B (1T token checkpoint) have?

TinyLlama-1.1B (1T token checkpoint) has 1.1B parameters. 1.1B. 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 TinyLlama-1.1B (1T token checkpoint)?

TinyLlama-1.1B (1T token checkpoint) was published by Singapore University of Technology & Design, based in Singapore, categorised as academia.

When was TinyLlama-1.1B (1T token checkpoint) released?

TinyLlama-1.1B (1T token checkpoint) was published in October 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 TinyLlama-1.1B (1T token checkpoint) used for?

TinyLlama-1.1B (1T token checkpoint) works in Language, and is recorded as handling chat, Language modeling/generation, Translation, Question answering. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.

Where can I download TinyLlama-1.1B (1T token checkpoint)?

The weights for TinyLlama-1.1B (1T token checkpoint) 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 TinyLlama-1.1B (1T token checkpoint)?

Around 7.2 × 10²¹ FLOP, on NVIDIA A100 SXM4 40 GB. 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 TinyLlama-1.1B (1T token checkpoint) 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 TinyLlama-1.1B (1T token checkpoint) is rarely worth using. Every figure here assumes the whole model is on the card.

Would two GPUs run TinyLlama-1.1B (1T token checkpoint) faster?

Two cards buy memory rather than speed. That matters for TinyLlama-1.1B (1T token checkpoint) only if one card cannot hold it — 818 can, so a second adds little.

Source

Original publication

Record last updated 25 May 2026

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