Code Llama-7B TPS calculator

Open weights Meta AI 7B parameters August 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

306 cards that can run it

818 cards we hold specifications for

Smallest card that fits

P102-101

10 GB · Q4_K_M · 38.0 tok/s

Fastest card

B200

484 tok/s · 180 GB

Which GPUs can run Code Llama-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

306 cards match

Calculating

					Needs	Quantisation	Fit
484 tok/s 411–581	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	11.8 GB	Q8_0	Comfortable
484 tok/s 411–581	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	11.8 GB	Q8_0	Comfortable
387 tok/s 232–618 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	11.8 GB	Q8_0	Comfortable
387 tok/s 232–618 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	11.8 GB	Q8_0	Comfortable
309 tok/s 185–495 · low confidence	Radeon Instinct MI300 AMD	128 GB	6,550 GB/s	Jan 2023	11.8 GB	Q8_0	Comfortable
296 tok/s 251–355	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	11.8 GB	Q8_0	Comfortable
296 tok/s 251–355	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	11.8 GB	Q8_0	Comfortable
283 tok/s 170–453 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	11.8 GB	Q8_0	Comfortable
251 tok/s 151–402 · low confidence	Radeon Instinct MI300A AMD	128 GB	5,325 GB/s	Dec 2023	11.8 GB	Q8_0	Comfortable
251 tok/s 151–402 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	11.8 GB	Q8_0	Comfortable
251 tok/s 151–402 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	11.8 GB	Q8_0	Comfortable
238 tok/s 203–286	H100 NVL 94 GB NVIDIA	94 GB	3,940 GB/s	Mar 2023	11.8 GB	Q8_0	Comfortable
218 tok/s 185–261	CMP 170HX 10 GB NVIDIA	10 GB	1,560 GB/s	Sep 2021	8.5 GB	Q4_K_M	Tight
203 tok/s 173–244	H100 PCIe 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	11.8 GB	Q8_0	Comfortable
203 tok/s 173–244	H100 SXM5 80 GB NVIDIA	80 GB	3,360 GB/s	Oct 2022	11.8 GB	Q8_0	Comfortable
203 tok/s 173–244	H100 SXM5 94 GB NVIDIA	94 GB	3,360 GB/s	Mar 2023	11.8 GB	Q8_0	Comfortable
203 tok/s 173–244	H100 SXM5 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	11.8 GB	Q8_0	Comfortable
203 tok/s 173–244	H800 SXM5 NVIDIA	80 GB	3,360 GB/s	Mar 2023	11.8 GB	Q8_0	Comfortable
155 tok/s 93–248 · low confidence	Radeon Instinct MI250 AMD	128 GB	3,280 GB/s	Nov 2021	11.8 GB	Q8_0	Comfortable
155 tok/s 93–248 · low confidence	Radeon Instinct MI250X AMD	128 GB	3,280 GB/s	Nov 2021	11.8 GB	Q8_0	Comfortable
129 tok/s 77–206 · low confidence	Data Center GPU Max 1550 Intel	128 GB	3,280 GB/s	Jan 2023	11.8 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	11.8 GB	Q8_0	Comfortable
123 tok/s 105–148	A100 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Nov 2020	11.8 GB	Q8_0	Comfortable
123 tok/s 105–148	A100X NVIDIA	80 GB	2,040 GB/s	Jun 2021	11.8 GB	Q8_0	Comfortable
123 tok/s 105–148	A800 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Aug 2022	11.8 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: 14 August 2023
Authors: Baptiste Rozière, Jonas Gehring, Fabian Gloeckle, Sten Sootla, Itai Gat, Ellen Tan, Yossef (Yossi) Adi, Jingyu Liu, Tal Remez, Jérémy Rapin, Artyom Kozhevnikov, Ivan Evtimov, Joanna Bitton, Manish Bhatt, Cristian Canton Ferrer, Aaron Grattafiori, Wenhan Xiong, Alexandre Defossez, Jade Copet, Faisal Azhar, Hugo Touvron, Gabriel Synnaeve, Louis Martin, Nicolas Usunier, Thomas Scialom

What it does

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

Domain: Language
Task: Code generation
Base model: Llama 2-7B

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: 600,000,000,000 tokens
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: 1.1 × 10²³ FLOP
How it was established: Operation counting
Fine-tuning compute: 2.5 × 10²² FLOP

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

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
Record confidence: Confident
Citations: 3,163

Sources

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

Reference: Code Llama: Open Foundation Models for Code
Last updated: 25 May 2026

The extremes

The ten fastest GPUs that run Code Llama-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 Code Llama-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

P102-101

Memory needed

8.5 GB

Fastest

484 tok/s

Code Llama-7B is small enough at 7B parameters that hardware is rarely the obstacle — 306 of the cards we track can run it, including cards several years old.

At the low end, a P102-101 handles it — 10 GB, at Q4_K_M, for about 38.0 tokens per second.

At the other end, a B200 generates roughly 484 tokens per second on it, on the strength of 8,000 GB/s of memory bandwidth.

Background

Code Llama-7B was published by Meta AI, in United States of America, in August 2023. The organisation is categorised as industry.

It works in Language, and is recorded as doing code generation.

It builds on Llama 2-7B, which is why it shares that model's general shape and size.

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

Reading the throughput figures

Across every card that can run it, the middle of the range is about 35.4 tokens per second, and 289 of them clear the ten tokens per second that roughly matches reading speed.

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 attention layout is on file, so the memory figures are computed exactly rather than approximated.

How it was trained

Producing it required around 1.1 × 10²³ FLOP of arithmetic, on NVIDIA A100 SXM4 80 GB, which is a statement about the training budget rather than about inference.

Around 600,000,000,000 tokens went into training it.

Step by step

How to choose a GPU for Code Llama-7B

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

The table lists every card that can hold Code Llama-7B — around 8.5 GB at Q4_K_M. That figure, not the card's headline performance, is what decides whether it runs.
02

Decide how long your conversations run

The conversation occupies memory too, and grows as it goes. Set the slider to the length you expect: at long context Code Llama-7B can slip off a card that handles short questions easily.
03

Set a quality floor

Each card runs the least-compressed copy it can hold — Q4_K_M on the smallest card that fits. Setting a floor drops the cards that only manage Code Llama-7B by squeezing it further than you would want.
04

Rank by throughput rather than spec sheet

The speed ordering for Code Llama-7B is effectively an ordering by memory bandwidth, which is why the B200 tops it at 484 tok/s.
05

Check the fit verdict before buying

Tight means Code Llama-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

Check the card from the other side

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

Answers

Code Llama-7B — common questions

How many parameters does Code Llama-7B have?

Code Llama-7B has 7B parameters. 7B. 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 Code Llama-7B?

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

When was Code Llama-7B released?

Code Llama-7B was published in August 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 Code Llama-7B used for?

Code Llama-7B works in Language, and is recorded as handling code generation. A model can carry several of each, so these are the areas it was built for rather than a limit on what it will attempt.

Where can I download Code Llama-7B?

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

Around 1.1 × 10²³ 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 Code Llama-7B if it does not fit in my GPU?

Only by offloading, which is usually a false economy: the part in system memory drags the whole thing down — the nearest miss we calculate is short by 1.3 GB. Our figures for Code Llama-7B assume it is fully resident.

Would two GPUs run Code Llama-7B faster?

Two cards buy memory rather than speed. That matters for Code Llama-7B only if one card cannot hold it — 306 can, so a second adds little.

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

Each card is shown running the least-compressed copy it can hold, and Code Llama-7B appears at 4 different compression levels across the cards that fit it. Bigger cards get the more accurate version.

How accurate are these Code Llama-7B speed estimates?

These are estimates with real error bars. The fastest result here, 411–581 tok/s on the B200, could reasonably land anywhere in its published range depending on which runtime you use.

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

The smallest card in our catalogue that holds Code Llama-7B is the P102-101, with 10 GB of memory. It runs the model at Q4_K_M using about 8.5 GB, and produces roughly 38.0 tokens per second. 306 cards in total can run it.

How fast is Code Llama-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 289 of the cards that can run Code Llama-7B clear that.

How much VRAM does Code Llama-7B need?

About 8.5 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 Code Llama-7B on a 12 GB GPU?

Yes. A GeForce RTX 3080 Ti with 12 GB runs it at Q6_K, using about 10.1 GB and generating roughly 80.2 tokens per second — a tight fit.

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

Yes. A Tesla V100 SXM2 16 GB with 16 GB runs it at Q8_0, using about 11.8 GB and generating roughly 68.4 tokens per second — a comfortable fit.

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

Yes. A GeForce RTX 5090 D V2 with 24 GB runs it at Q8_0, using about 11.8 GB and generating roughly 81.1 tokens per second — a comfortable fit.

Is Code Llama-7B open source?

Its weights are published, so Code Llama-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.

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