Llemma 34B TPS calculator

Open weights Princeton University,University of Toronto,Vector Institute,University of Cambridge,Carnegie Mellon University (CMU),University of Washington,EleutherAI 34B 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

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 Llemma 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 60–159 · low confidence	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	37.1 GB	Q8_0	Comfortable
99.7 tok/s 60–159 · low confidence	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	37.1 GB	Q8_0	Comfortable
79.6 tok/s 48–127 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	37.1 GB	Q8_0	Comfortable
79.6 tok/s 48–127 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	37.1 GB	Q8_0	Comfortable
63.6 tok/s 38–102 · low confidence	Radeon Instinct MI300 AMD	128 GB	6,550 GB/s	Jan 2023	37.1 GB	Q8_0	Comfortable
60.9 tok/s 37–97 · low confidence	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	37.1 GB	Q8_0	Comfortable
60.9 tok/s 37–97 · low confidence	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	37.1 GB	Q8_0	Comfortable
58.3 tok/s 35–93 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	37.1 GB	Q8_0	Comfortable
51.7 tok/s 31–83 · low confidence	Radeon Instinct MI300A AMD	128 GB	5,325 GB/s	Dec 2023	37.1 GB	Q8_0	Comfortable
51.7 tok/s 31–83 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	37.1 GB	Q8_0	Comfortable
51.7 tok/s 31–83 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	37.1 GB	Q8_0	Comfortable
49.1 tok/s 29–79 · low confidence	H100 NVL 94 GB NVIDIA	94 GB	3,940 GB/s	Mar 2023	37.1 GB	Q8_0	Comfortable
41.9 tok/s 25–67 · low confidence	H100 PCIe 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	37.1 GB	Q8_0	Comfortable
41.9 tok/s 25–67 · low confidence	H100 SXM5 80 GB NVIDIA	80 GB	3,360 GB/s	Oct 2022	37.1 GB	Q8_0	Comfortable
41.9 tok/s 25–67 · low confidence	H100 SXM5 94 GB NVIDIA	94 GB	3,360 GB/s	Mar 2023	37.1 GB	Q8_0	Comfortable
41.9 tok/s 25–67 · low confidence	H100 SXM5 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	37.1 GB	Q8_0	Comfortable
41.9 tok/s 25–67 · low confidence	H800 SXM5 NVIDIA	80 GB	3,360 GB/s	Mar 2023	37.1 GB	Q8_0	Comfortable
41.6 tok/s 25–67 · low confidence	DRIVE A100 PROD NVIDIA	32 GB	1,870 GB/s	May 2020	25.2 GB	Q5_K_M	Tight
41.6 tok/s 25–67 · low confidence	GRID A100A NVIDIA	32 GB	1,870 GB/s	May 2020	25.2 GB	Q5_K_M	Tight
39.8 tok/s 24–64 · low confidence	GeForce RTX 5090 NVIDIA	32 GB	1,790 GB/s	Jan 2025	25.2 GB	Q5_K_M	Tight
39.8 tok/s 24–64 · low confidence	GeForce RTX 5090 D NVIDIA	32 GB	1,790 GB/s	Jan 2025	25.2 GB	Q5_K_M	Tight
38.5 tok/s 23–62 · low confidence	GeForce RTX 5090 D V2 NVIDIA	24 GB	1,340 GB/s	Aug 2025	21.3 GB	Q4_K_M	Tight
35.1 tok/s 21–56 · low confidence	A30X NVIDIA	24 GB	1,220 GB/s	Apr 2021	21.3 GB	Q4_K_M	Tight
31.9 tok/s 19–51 · low confidence	Radeon Instinct MI250 AMD	128 GB	3,280 GB/s	Nov 2021	37.1 GB	Q8_0	Comfortable
31.9 tok/s 19–51 · low confidence	Radeon Instinct MI250X AMD	128 GB	3,280 GB/s	Nov 2021	37.1 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: Princeton University,University of Toronto,Vector Institute,University of Cambridge,Carnegie Mellon University (CMU),University of Washington,EleutherAI
Organisation type: Academia,Academia,Academia,Academia,Academia,Academia,Research collective
Country: United States of America, Canada, United Kingdom of Great Britain and Northern Ireland
Published: 16 October 2023
Authors: Zhangir Azerbayev, Hailey Schoelkopf, Keiran Paster, Marco Dos Santos, Stephen McAleer, Albert Q. Jiang, Jia Deng, Stella Biderman, Sean Welleck

What it does

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

Domain: Mathematics, Language
Task: Mathematical reasoning, Language modeling/generation, Question answering, Code generation
Base model: Code Llama-34B
Numerical format: BF16

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: 55,000,000,000 tokens
Epochs: 0.9
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: 5.4 × 10²³ FLOP
How it was established: Operation counting,Hardware
Fine-tuning compute: 1.3 × 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 40 GB
Chips used: 256
Chip-hours: 47,000
Power draw: 203.3 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 (restricted use)
Training code: Unreleased
Hugging Face: EleutherAI

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: 440

Sources

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

Reference: Llemma: An Open Language Model For Mathematics
Last updated: 25 May 2026

The extremes

The ten fastest GPUs that run Llemma 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 Llemma 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 you need to run it

Minimum card

RTX A4500

Memory needed

17.3 GB

Fastest

99.7 tok/s

With 34B parameters, Llemma 34B lands in the range a serious desktop card can handle once the weights are compressed. 132 of the cards we track can run it.

The least hardware that works is a RTX A4500. Its 20 GB is enough at Q3_K_M compression, giving roughly 21.5 tokens per second.

Top of the range is the B200, at roughly 99.7 tokens per second thanks to 8,000 GB/s of bandwidth.

About this model

Llemma 34B was published by Princeton University,University of Toronto,Vector Institute,University of Cambridge,Carnegie Mellon University (CMU),University of Washington,EleutherAI, in United States of America, in October 2023. academia,Academia,Academia,Academia,Academia,Academia,Research collective is the category the publisher falls under.

It works in Mathematics, Language, and is recorded as doing mathematical reasoning, Language modeling/generation, Question answering, Code generation.

Its starting point was Code Llama-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. It is published under the EleutherAI organisation on Hugging Face.

How fast it runs, and why

Across every card that can run it, the middle of the range is about 21.2 tokens per second, and 103 of them clear the ten tokens per second that roughly matches reading speed.

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.

Without the attention layout on record, the memory column is an approximation. It is close enough to choose hardware by, and least reliable at long context.

How it was trained

Training it took roughly 5.4 × 10²³ FLOP of computation, on NVIDIA A100 SXM4 40 GB — a measure of what producing the model cost, not of how fast it answers.

It was trained on about 55,000,000,000 tokens of text.

Step by step

How to choose a GPU for Llemma 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

Look at what Llemma 34B actually needs — around 17.3 GB at Q3_K_M. No amount of processing power compensates for a card that cannot hold it.
02

Set the context length you will work at

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

Set a quality floor

Each card runs the least-compressed copy it can hold — Q3_K_M on the smallest card that fits. Setting a floor drops the cards that only manage Llemma 34B by squeezing it further than you would want.
04

Compare tokens per second, not specifications

Sort by speed to see how cards rank for Llemma 34B. It will not match a gaming ordering — generation is bound by memory bandwidth, which is why the B200 tops it at 99.7 tok/s.
05

Check the fit verdict before buying

Tight means Llemma 34B 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

Every card name links to its own page, which runs the same calculation across the whole model catalogue. Worth a look before buying for Llemma 34B alone — a card is usually bought for more than one model.

Answers

Llemma 34B — common questions

Can I run Llemma 34B on a 24 GB GPU?

Yes. A GeForce RTX 5090 D V2 with 24 GB runs it at Q4_K_M, using about 21.3 GB and generating roughly 38.5 tokens per second — a tight fit.

Is Llemma 34B open source?

Its weights are published, so Llemma 34B 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 Llemma 34B have?

Llemma 34B has 34B parameters. https://arxiv.org/abs/2310.10631. 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 Llemma 34B?

Llemma 34B was published by Princeton University,University of Toronto,Vector Institute,University of Cambridge,Carnegie Mellon University (CMU),University of Washington,EleutherAI, based in United States of America, categorised as academia,Academia,Academia,Academia,Academia,Academia,Research collective.

When was Llemma 34B released?

Llemma 34B 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 Llemma 34B used for?

Llemma 34B works in Mathematics, Language, and is recorded as handling mathematical reasoning, Language modeling/generation, Question answering, Code generation. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.

Where can I download Llemma 34B?

Its weights are published under the EleutherAI organisation on Hugging Face. We do not host model files — this site calculates what hardware is needed to run them.

How much compute was used to train Llemma 34B?

Around 5.4 × 10²³ 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 Llemma 34B 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 6.9 GB. Our figures for Llemma 34B assume it is fully resident.

Would two GPUs run Llemma 34B faster?

Two cards buy memory rather than speed. That matters for Llemma 34B only if one card cannot hold it — 132 can, so a second adds little.

Why does the quantisation differ between cards for Llemma 34B?

Each card is shown running the least-compressed copy it can hold, and Llemma 34B appears at 5 different compression levels across the cards that fit it. Bigger cards get the more accurate version.

How accurate are these Llemma 34B speed estimates?

These are estimates with real error bars. The fastest result here, 60–159 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 Llemma 34B?

The smallest card in our catalogue that holds Llemma 34B is the RTX A4500, with 20 GB of memory. It runs the model at Q3_K_M using about 17.3 GB, and produces roughly 21.5 tokens per second. 132 cards in total can run it.

How fast is Llemma 34B on a GPU?

It depends on the card. The quickest we calculate is a 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 103 of the cards that can run Llemma 34B clear that.

How much VRAM does Llemma 34B need?

About 17.3 GB at Q3_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.

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