Llama 2-7B TPS calculator

Open weights Meta AI 7B 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

509 cards that can run it

818 cards we hold specifications for

Smallest card that fits

Xeon Phi 5110P

8 GB · Q4_K_M · 29.1 tok/s

Fastest card

B200

484 tok/s · 180 GB

Which GPUs can run Llama 2-7B?

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

509 cards match

Calculating

					Needs	Quantisation	Fit
484 tok/s 411–581	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	9.8 GB	Q8_0	Comfortable
484 tok/s 411–581	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	9.8 GB	Q8_0	Comfortable
387 tok/s 232–618 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	9.8 GB	Q8_0	Comfortable
387 tok/s 232–618 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	9.8 GB	Q8_0	Comfortable
309 tok/s 185–495 · low confidence	Radeon Instinct MI300 AMD	128 GB	6,550 GB/s	Jan 2023	9.8 GB	Q8_0	Comfortable
296 tok/s 251–355	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	9.8 GB	Q8_0	Comfortable
296 tok/s 251–355	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	9.8 GB	Q8_0	Comfortable
283 tok/s 170–453 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	9.8 GB	Q8_0	Comfortable
251 tok/s 151–402 · low confidence	Radeon Instinct MI300A AMD	128 GB	5,325 GB/s	Dec 2023	9.8 GB	Q8_0	Comfortable
251 tok/s 151–402 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	9.8 GB	Q8_0	Comfortable
251 tok/s 151–402 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	9.8 GB	Q8_0	Comfortable
238 tok/s 203–286	H100 NVL 94 GB NVIDIA	94 GB	3,940 GB/s	Mar 2023	9.8 GB	Q8_0	Comfortable
208 tok/s 177–250	CMP 170HX 8 GB NVIDIA	8 GB	1,490 GB/s	Sep 2021	6.5 GB	Q4_K_M	Tight
203 tok/s 173–244	H100 PCIe 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	9.8 GB	Q8_0	Comfortable
203 tok/s 173–244	H100 SXM5 80 GB NVIDIA	80 GB	3,360 GB/s	Oct 2022	9.8 GB	Q8_0	Comfortable
203 tok/s 173–244	H100 SXM5 94 GB NVIDIA	94 GB	3,360 GB/s	Mar 2023	9.8 GB	Q8_0	Comfortable
203 tok/s 173–244	H100 SXM5 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	9.8 GB	Q8_0	Comfortable
203 tok/s 173–244	H800 SXM5 NVIDIA	80 GB	3,360 GB/s	Mar 2023	9.8 GB	Q8_0	Comfortable
155 tok/s 93–248 · low confidence	Radeon Instinct MI250 AMD	128 GB	3,280 GB/s	Nov 2021	9.8 GB	Q8_0	Comfortable
155 tok/s 93–248 · low confidence	Radeon Instinct MI250X AMD	128 GB	3,280 GB/s	Nov 2021	9.8 GB	Q8_0	Comfortable
137 tok/s 117–165	CMP 170HX 10 GB NVIDIA	10 GB	1,560 GB/s	Sep 2021	8.1 GB	Q6_K	Tight
129 tok/s 77–206 · low confidence	Data Center GPU Max 1550 Intel	128 GB	3,280 GB/s	Jan 2023	9.8 GB	Q8_0	Comfortable
126 tok/s 76–202 · low confidence	Data Center GPU Max Subsystem Intel	128 GB	3,210 GB/s	Jan 2023	9.8 GB	Q8_0	Comfortable
123 tok/s 105–148	A100 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Nov 2020	9.8 GB	Q8_0	Comfortable
123 tok/s 105–148	A100X NVIDIA	80 GB	2,040 GB/s	Jun 2021	9.8 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: 7B
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: 8.4 × 10²² 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
Chip-hours: 184,320
Compute cost: $114,259
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.

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 2-7B

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 2-7B

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

The hardware side

Minimum card

Xeon Phi 5110P

Memory needed

6.5 GB

Fastest

484 tok/s

Llama 2-7B is small enough at 7B parameters that hardware is rarely the obstacle — 509 of the cards we track can run it, including cards several years old.

At the low end, a Xeon Phi 5110P handles it — 8 GB, at Q4_K_M, for about 29.1 tokens per second.

The quickest result comes from a B200 at around 484 tokens per second — its 8,000 GB/s of bandwidth is what buys that.

What this model is

Llama 2-7B was published by Meta AI, in United States of America, in July 2023. industry is the category the publisher falls under.

It works in Language, and is recorded as doing language modeling.

Because its weights were released, nothing about running it depends on a provider staying available — it is yours once downloaded.

What decides the speed

Half the cards that hold it manage more than 30.4 tokens per second, and 482 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.

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

What went into building it

Producing it required around 8.4 × 10²² FLOP of arithmetic, on NVIDIA A100 SXM4 80 GB, which is a statement about the training budget rather than about inference.

Around 2,000,000,000,000 tokens went into training it.

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 2-7B

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 2-7B — around 6.5 GB at Q4_K_M. Capacity is the gate — a card either holds it or it does not.
02

Decide how long your conversations run

Longer conversations cost memory on top of what the weights need. Move the slider to your real working length before trusting any row for Llama 2-7B.
03

Choose how far you will compress it

The quantisation column varies by card, because a bigger card holds a more accurate copy of Llama 2-7B — Q4_K_M 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 Llama 2-7B follows memory bandwidth, not core counts, which is why the B200 tops it at 484 tok/s.
05

Check the fit verdict before buying

Tight means Llama 2-7B loads and works, with no room to raise the context later. Comfortable means you can. The difference matters more than a few tokens per second.
06

Open the card you have settled on

Each card page repeats this sweep for every model we hold. It answers what else the hardware is good for, beyond Llama 2-7B.

Answers

Llama 2-7B — common questions

When was Llama 2-7B released?

Llama 2-7B 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.

What is Llama 2-7B used for?

Llama 2-7B works in Language, and is recorded as handling language modeling. These are the areas it was designed around; they describe intent rather than a hard boundary.

Where can I download Llama 2-7B?

The weights for Llama 2-7B 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 Llama 2-7B?

Around 8.4 × 10²² FLOP, on 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.

Can I run Llama 2-7B if it does not fit in my GPU?

It can be split between the card and system memory, but Llama 2-7B generates painfully slowly that way — the nearest miss we calculate is short by 1.1 GB. Nothing on this page assumes offloading.

Would two GPUs run Llama 2-7B faster?

Capacity adds across cards; throughput does not. Since 509 of the cards we track already hold Llama 2-7B on their own, a second card is rarely the answer here.

Why does the quantisation differ between cards for Llama 2-7B?

Because capacity varies, so does how hard Llama 2-7B has to be squeezed — 3 distinct levels appear in the table above. Set a minimum quality to compare at one.

How accurate are these Llama 2-7B 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 411–581 tok/s on the B200 rather than a single number.

What GPU do I need to run Llama 2-7B?

The smallest card in our catalogue that holds Llama 2-7B is the Xeon Phi 5110P, with 8 GB of memory. It runs the model at Q4_K_M using about 6.5 GB, and produces roughly 29.1 tokens per second. 509 cards in total can run it.

How fast is Llama 2-7B on a GPU?

It depends on the card. The quickest we calculate is a B200 at about 484 tokens per second; the slowest that still runs it manages considerably less. Reading speed is around ten tokens per second, and 482 of the cards that can run Llama 2-7B clear that.

How much VRAM does Llama 2-7B need?

About 6.5 GB at Q4_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.

Can I run Llama 2-7B on a 8 GB GPU?

Yes. A CMP 170HX 8 GB with 8 GB runs it at Q4_K_M, using about 6.5 GB and generating roughly 208 tokens per second — a tight fit.

Can I run Llama 2-7B on a 12 GB GPU?

Yes. A GeForce RTX 3080 Ti with 12 GB runs it at Q8_0, using about 9.8 GB and generating roughly 55.2 tokens per second — a tight fit.

Can I run Llama 2-7B on a 16 GB GPU?

Yes. A Tesla V100 SXM2 16 GB with 16 GB runs it at Q8_0, using about 9.8 GB and generating roughly 68.4 tokens per second — a comfortable fit.

Can I run Llama 2-7B on a 24 GB GPU?

Yes. A GeForce RTX 5090 D V2 with 24 GB runs it at Q8_0, using about 9.8 GB and generating roughly 81.1 tokens per second — a comfortable fit.

Is Llama 2-7B open source?

Its weights are published, so Llama 2-7B 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 Llama 2-7B have?

Llama 2-7B has 7B parameters. 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.

Who created Llama 2-7B?

Llama 2-7B was published by Meta AI, based in United States of America, categorised as industry.

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