Llama 2-13B TPS calculator

Open weights Meta AI 13B parameters July 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

295 cards that can run it

818 cards we hold specifications for

Smallest card that fits

GeForce GTX 1080 Ti

11 GB · Q3_K_M · 36.2 tok/s

Fastest card

B200

261 tok/s · 180 GB

Which GPUs can run Llama 2-13B?

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

295 cards match

Calculating

					Needs	Quantisation	Fit
261 tok/s 222–313	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	16.9 GB	Q8_0	Comfortable
261 tok/s 222–313	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	16.9 GB	Q8_0	Comfortable
208 tok/s 125–333 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	16.9 GB	Q8_0	Comfortable
208 tok/s 125–333 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	16.9 GB	Q8_0	Comfortable
166 tok/s 100–266 · low confidence	Radeon Instinct MI300 AMD	128 GB	6,550 GB/s	Jan 2023	16.9 GB	Q8_0	Comfortable
159 tok/s 135–191	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	16.9 GB	Q8_0	Comfortable
159 tok/s 135–191	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	16.9 GB	Q8_0	Comfortable
152 tok/s 91–244 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	16.9 GB	Q8_0	Comfortable
135 tok/s 81–217 · low confidence	Radeon Instinct MI300A AMD	128 GB	5,325 GB/s	Dec 2023	16.9 GB	Q8_0	Comfortable
135 tok/s 81–217 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	16.9 GB	Q8_0	Comfortable
135 tok/s 81–217 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	16.9 GB	Q8_0	Comfortable
128 tok/s 109–154	H100 NVL 94 GB NVIDIA	94 GB	3,940 GB/s	Mar 2023	16.9 GB	Q8_0	Comfortable
109 tok/s 93–131	H100 PCIe 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	16.9 GB	Q8_0	Comfortable
109 tok/s 93–131	H100 SXM5 80 GB NVIDIA	80 GB	3,360 GB/s	Oct 2022	16.9 GB	Q8_0	Comfortable
109 tok/s 93–131	H100 SXM5 94 GB NVIDIA	94 GB	3,360 GB/s	Mar 2023	16.9 GB	Q8_0	Comfortable
109 tok/s 93–131	H100 SXM5 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	16.9 GB	Q8_0	Comfortable
109 tok/s 93–131	H800 SXM5 NVIDIA	80 GB	3,360 GB/s	Mar 2023	16.9 GB	Q8_0	Comfortable
83.4 tok/s 50–133 · low confidence	Radeon Instinct MI250 AMD	128 GB	3,280 GB/s	Nov 2021	16.9 GB	Q8_0	Comfortable
83.4 tok/s 50–133 · low confidence	Radeon Instinct MI250X AMD	128 GB	3,280 GB/s	Nov 2021	16.9 GB	Q8_0	Comfortable
73.0 tok/s 62–88	GeForce RTX 3080 12 GB NVIDIA	12 GB	912 GB/s	Jan 2022	10.1 GB	IQ4_XS	Tight
73.0 tok/s 62–88	GeForce RTX 3080 Ti NVIDIA	12 GB	912 GB/s	May 2021	10.1 GB	IQ4_XS	Tight
69.5 tok/s 42–111 · low confidence	Data Center GPU Max 1550 Intel	128 GB	3,280 GB/s	Jan 2023	16.9 GB	Q8_0	Comfortable
68.0 tok/s 41–109 · low confidence	Data Center GPU Max Subsystem Intel	128 GB	3,210 GB/s	Jan 2023	16.9 GB	Q8_0	Comfortable
66.5 tok/s 56–80	A100 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Nov 2020	16.9 GB	Q8_0	Comfortable
66.5 tok/s 56–80	A100X NVIDIA	80 GB	2,040 GB/s	Jun 2021	16.9 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: Meta AI
Organisation type: Industry
Country: United States of America
Published: 18 July 2023
Authors: Hugo Touvron, Louis Martin, Kevin Stone, Peter Albert, Amjad Almahairi, Yasmine Babaei, Nikolay Bashlykov, Soumya Batra, Prajjwal Bhargava, Shruti Bhosale, Dan Bikel, Lukas Blecher, Cristian Canton Ferrer, Moya Chen, Guillem Cucurull, David Esiobu, Jude Fernandes, Jeremy Fu, Wenyin Fu, Brian Fuller, Cynthia Gao, Vedanuj Goswami, Naman Goyal, Anthony Hartshorn, Saghar Hosseini, Rui Hou, Hakan Inan,…

What it does

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

Domain: Language
Task: Language modeling
Approach: Supervised

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: 13B
Training data: 2,000,000,000,000 tokens
Epochs: 1
Batch size: 4,000,000

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: 1.6 × 10²³ 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 80 GB
Compute cost: $235,478
Data centre: Meta’s Research Super Cluster

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

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: Historical significance,Significant use,Highly cited
Record confidence: Confident
Citations: 16,911

Sources

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

Reference: Llama 2: Open Foundation and Fine-Tuned Chat Models
Last updated: 25 May 2026

The extremes

The ten fastest GPUs that run Llama 2-13B

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 2-13B

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

GeForce GTX 1080 Ti

Memory needed

9.4 GB

Fastest

261 tok/s

Llama 2-13B reaches a parameter count of 13B. That is small enough that hardware is rarely the obstacle, including on cards several years old. The number of cards we track that can run it: 295.

The least hardware that works is GeForce GTX 1080 Ti, with a memory capacity of 11 GB, running it at a compression of Q3_K_M and producing around 36.2 tokens per second.

The fastest we calculate for it is B200, generating roughly 261 tokens per second on the strength of a memory bandwidth of 8,000 GB/s.

Background

Llama 2-13B was published by Meta AI, in the country recorded as United States of America, during July 2023. It comes out of an organisation categorised as industry.

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

The weights are published, so it can be downloaded and run on your own hardware indefinitely, offline, with no account attached.

Reading the throughput figures

Half the cards that hold it manage more than 24.2 tokens per second. Clearing the ten tokens per second that roughly matches reading speed: 258 of them.

Every weight participates in every token here, so bandwidth is the whole story: the ranking below is effectively a ranking of memory throughput.

Because the architecture is recorded, the memory column is derived rather than estimated.

How it was trained

The training run consumed about 1.6 × 10²³ FLOP, on hardware recorded as NVIDIA A100 SXM4 80 GB. 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 2,000,000,000,000 tokens of text.

It is tracked in the underlying dataset for one reason in particular: historical significance,Significant use,Highly cited.

Step by step

How to choose a GPU for Llama 2-13B

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

Every card here has been checked against Llama 2-13B, needing around 9.4 GB at a compression of Q3_K_M. 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 a card that seemed fine stops fitting Llama 2-13B.
03

Decide how much compression you will accept

Each card runs the least-compressed copy it can hold, 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 2-13B. It will not match a gaming ordering, because generation is bound by memory bandwidth. The card topping the list is B200, at 261 tok/s.
05

Read the fit column last

The fit column separates cards that just manage it from those with room to spare, in the case of Llama 2-13B. 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

Following a card through to its own page shows every other model it can hold, which is the question that follows once you have settled on Llama 2-13B.

Answers

Llama 2-13B — common questions

Llama 2-13B— who created it?

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

Llama 2-13B— when was it released?

It was published in July 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.

Llama 2-13B— what is it used for?

It works in the domain of Language, and is recorded as handling the task of language modeling. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.

Llama 2-13B— 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.

Llama 2-13B— how much compute was used to train it?

Training consumed around 1.6 × 10²³ FLOP, on hardware recorded as NVIDIA A100 SXM4 80 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.

Llama 2-13B— 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 1.9 GB. Every figure here assumes the whole model is resident on the card.

Llama 2-13B— would two GPUs run it faster?

Capacity adds across cards; throughput does not. The number of cards already holding it on their own: 295. So a second card is rarely the answer here.

Llama 2-13B— why does the quantisation differ between cards?

Each card is shown running the least-compressed copy it can hold. The number of distinct compression levels across the cards that fit it: 4. Bigger cards get the more accurate version, and the quality floor above pins the comparison to one level.

Llama 2-13B— how accurate are these speed estimates?

These are estimates with real error bars, and any of them could reasonably land anywhere in its published range depending on which runtime you use. The fastest result here: 222–313 tok/s on B200. The same model and card vary by thirty to fifty per cent depending on the inference software and its version.

Llama 2-13B— what GPU do I need to run it?

The smallest card in our catalogue that holds it is GeForce GTX 1080 Ti, with a memory capacity of 11 GB. It runs the model at a compression of Q3_K_M using about 9.4 GB, and produces roughly 36.2 tokens per second. The number of cards able to run it in total: 295.

Llama 2-13B— how fast is it on a GPU?

It depends on the card. The quickest we calculate is B200, at about 261 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: 258.

Llama 2-13B— how much VRAM does it need?

It needs about 9.4 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 2-13B— can I run it on a GPU holding 12 GB?

Yes. The card GeForce RTX 3080 Ti, holding 12 GB, runs it at a compression of IQ4_XS, using about 10.1 GB and generating roughly 73.0 tokens per second. The fit is tight.

Llama 2-13B— can I run it on a GPU holding 16 GB?

Yes. The card Tesla V100 SXM2 16 GB, holding 16 GB, runs it at a compression of Q6_K, using about 13.9 GB and generating roughly 53.5 tokens per second. The fit is tight.

Llama 2-13B— can I run it on a GPU holding 24 GB?

Yes. The card GeForce RTX 5090 D V2, holding 24 GB, runs it at a compression of Q8_0, using about 16.9 GB and generating roughly 43.7 tokens per second. The fit is comfortable.

Llama 2-13B— 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 2-13B— how many parameters does it have?

It has a parameter count of 13B. Llama has been released in 7B, 13B, and 70B variants. 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.

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