Code Llama-34B TPS calculator

Open weights Meta AI 34B 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

132 cards that can run it

818 cards we hold specifications for

Smallest card that fits

RTX A4500

20 GB · Q3_K_M · 21.5 tok/s

Fastest card

B200

99.7 tok/s · 180 GB

Which GPUs can run Code Llama-34B?

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

132 cards match

Calculating

					Needs	Quantisation	Fit
99.7 tok/s 85–120	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	36.5 GB	Q8_0	Comfortable
99.7 tok/s 85–120	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	36.5 GB	Q8_0	Comfortable
79.6 tok/s 48–127 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	36.5 GB	Q8_0	Comfortable
79.6 tok/s 48–127 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	36.5 GB	Q8_0	Comfortable
63.6 tok/s 38–102 · low confidence	Radeon Instinct MI300 AMD	128 GB	6,550 GB/s	Jan 2023	36.5 GB	Q8_0	Comfortable
60.9 tok/s 52–73	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	36.5 GB	Q8_0	Comfortable
60.9 tok/s 52–73	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	36.5 GB	Q8_0	Comfortable
58.3 tok/s 35–93 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	36.5 GB	Q8_0	Comfortable
51.7 tok/s 31–83 · low confidence	Radeon Instinct MI300A AMD	128 GB	5,325 GB/s	Dec 2023	36.5 GB	Q8_0	Comfortable
51.7 tok/s 31–83 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	36.5 GB	Q8_0	Comfortable
51.7 tok/s 31–83 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	36.5 GB	Q8_0	Comfortable
49.1 tok/s 42–59	H100 NVL 94 GB NVIDIA	94 GB	3,940 GB/s	Mar 2023	36.5 GB	Q8_0	Comfortable
41.9 tok/s 36–50	H100 PCIe 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	36.5 GB	Q8_0	Comfortable
41.9 tok/s 36–50	H100 SXM5 80 GB NVIDIA	80 GB	3,360 GB/s	Oct 2022	36.5 GB	Q8_0	Comfortable
41.9 tok/s 36–50	H100 SXM5 94 GB NVIDIA	94 GB	3,360 GB/s	Mar 2023	36.5 GB	Q8_0	Comfortable
41.9 tok/s 36–50	H100 SXM5 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	36.5 GB	Q8_0	Comfortable
41.9 tok/s 36–50	H800 SXM5 NVIDIA	80 GB	3,360 GB/s	Mar 2023	36.5 GB	Q8_0	Comfortable
38.5 tok/s 33–46	GeForce RTX 5090 D V2 NVIDIA	24 GB	1,340 GB/s	Aug 2025	20.6 GB	Q4_K_M	Tight
35.1 tok/s 30–42	A30X NVIDIA	24 GB	1,220 GB/s	Apr 2021	20.6 GB	Q4_K_M	Tight
33.9 tok/s 29–41	DRIVE A100 PROD NVIDIA	32 GB	1,870 GB/s	May 2020	28.6 GB	Q6_K	Tight
33.9 tok/s 29–41	GRID A100A NVIDIA	32 GB	1,870 GB/s	May 2020	28.6 GB	Q6_K	Tight
32.4 tok/s 28–39	GeForce RTX 5090 NVIDIA	32 GB	1,790 GB/s	Jan 2025	28.6 GB	Q6_K	Tight
32.4 tok/s 28–39	GeForce RTX 5090 D NVIDIA	32 GB	1,790 GB/s	Jan 2025	28.6 GB	Q6_K	Tight
31.9 tok/s 19–51 · low confidence	Radeon Instinct MI250 AMD	128 GB	3,280 GB/s	Nov 2021	36.5 GB	Q8_0	Comfortable
31.9 tok/s 19–51 · low confidence	Radeon Instinct MI250X AMD	128 GB	3,280 GB/s	Nov 2021	36.5 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: 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 2-34B

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: 34B
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: 5.3 × 10²³ FLOP
How it was established: Operation counting
Fine-tuning compute: 1.2 × 10²³ 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-34B

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-34B

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

RTX A4500

Memory needed

16.7 GB

Fastest

99.7 tok/s

Code Llama-34B reaches a parameter count of 34B. That lands in the range a serious desktop card can handle once the weights are compressed. The number of cards we track that can run it: 132.

The smallest card that holds it is RTX A4500, with a memory capacity of 20 GB, running it at a compression of Q3_K_M and producing around 21.5 tokens per second.

Top of the range is B200, generating roughly 99.7 tokens per second on the strength of a memory bandwidth of 8,000 GB/s.

What this model is

Code Llama-34B was published by Meta AI, in the country recorded as United States of America, during August 2023. The category the publisher falls under is industry.

It works in the domain of Language, and is recorded as performing the task of code generation.

Its starting point was an existing base model, Llama 2-34B. Most models at this scale are adapted from an existing base rather than built from nothing.

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

What decides the speed

Half the cards that hold it manage more than 19.7 tokens per second. Exceeding reading speed outright: 100 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.

What went into building it

Training it took a computation budget of roughly 5.3 × 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.

Training consumed a corpus of around 600,000,000,000 tokens of text.

Step by step

How to choose a GPU for Code Llama-34B

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

Every card here has been checked against Code Llama-34B, needing around 16.7 GB at a compression of Q3_K_M. No amount of processing power compensates for a card that cannot hold it.
02

Match the context to your actual use

Longer conversations cost memory on top of what the weights need. Move the slider to your real working length before trusting any row for Code Llama-34B.
03

Set a quality floor

The quantisation column varies by card, because a bigger card holds a more accurate copy, 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

Sort by speed

Sort by speed to see how cards rank for Code Llama-34B. It will not match a gaming ordering, because generation is bound by memory bandwidth. The card topping the list is B200, at 99.7 tok/s.
05

Look at the headroom, not just the fit

The fit column separates cards that just manage it from those with room to spare, in the case of Code Llama-34B. 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

Open the card you have settled on

Each card page repeats this sweep for every model we hold, answering what else the hardware is good for beyond Code Llama-34B.

Answers

Code Llama-34B — common questions

Code Llama-34B— how much VRAM does it need?

It needs about 16.7 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.

Code Llama-34B— 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 Q4_K_M, using about 20.6 GB and generating roughly 38.5 tokens per second. The fit is tight.

Code Llama-34B— 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.

Code Llama-34B— how many parameters does it have?

It has a parameter count of 34B. 34B. 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.

Code Llama-34B— who created it?

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

Code Llama-34B— when was it released?

It 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.

Code Llama-34B— what is it used for?

It works in the domain of Language, and is recorded as handling the task of code generation. These are the areas it was designed around; they describe intent rather than a hard boundary.

Code Llama-34B— 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.

Code Llama-34B— how much compute was used to train it?

Training consumed around 5.3 × 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.

Code Llama-34B— can I run it if it does not fit in my GPU?

Only by offloading, which is usually a false economy: the part held in system memory drags the whole thing down. The nearest miss we calculate falls short by 6.2 GB. Every figure here assumes the whole model is resident on the card.

Code Llama-34B— would two GPUs run it faster?

A second card roughly doubles the memory available but not the generation rate. The number already able to run it alone: 132. So a second card is rarely the answer here.

Code Llama-34B— why does the quantisation differ between cards?

Because capacity varies, so does how hard it has to be squeezed. The number of distinct levels in the table above: 5. Bigger cards get the more accurate version, and the quality floor above pins the comparison to one level.

Code Llama-34B— 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: 85–120 tok/s on B200. The same model and card vary by thirty to fifty per cent depending on the inference software and its version.

Code Llama-34B— what GPU do I need to run it?

The smallest card in our catalogue that holds it is RTX A4500, with a memory capacity of 20 GB. It runs the model at a compression of Q3_K_M using about 16.7 GB, and produces roughly 21.5 tokens per second. The number of cards able to run it in total: 132.

Code Llama-34B— how fast is it on a GPU?

It depends on the card. The quickest we calculate is B200, at about 99.7 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: 100.

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