Llemma 7B TPS calculator

Open weights Princeton University,EleutherAI,University of Toronto,Vector Institute,University of Cambridge,Carnegie Mellon University (CMU),University of Washington 7B 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

589 cards that can run it

818 cards we hold specifications for

Smallest card that fits

Tesla K20c

5 GB · Q3_K_M · 28.9 tok/s

Fastest card

B200

484 tok/s · 180 GB

Which GPUs can run Llemma 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

589 cards match

Calculating

					Needs	Quantisation	Fit
484 tok/s 290–774 · low confidence	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	8.2 GB	Q8_0	Comfortable
484 tok/s 290–774 · low confidence	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	8.2 GB	Q8_0	Comfortable
387 tok/s 232–618 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	8.2 GB	Q8_0	Comfortable
387 tok/s 232–618 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	8.2 GB	Q8_0	Comfortable
309 tok/s 185–495 · low confidence	Radeon Instinct MI300 AMD	128 GB	6,550 GB/s	Jan 2023	8.2 GB	Q8_0	Comfortable
296 tok/s 178–473 · low confidence	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	8.2 GB	Q8_0	Comfortable
296 tok/s 178–473 · low confidence	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	8.2 GB	Q8_0	Comfortable
283 tok/s 170–453 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	8.2 GB	Q8_0	Comfortable
251 tok/s 151–402 · low confidence	Radeon Instinct MI300A AMD	128 GB	5,325 GB/s	Dec 2023	8.2 GB	Q8_0	Comfortable
251 tok/s 151–402 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	8.2 GB	Q8_0	Comfortable
251 tok/s 151–402 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	8.2 GB	Q8_0	Comfortable
238 tok/s 143–381 · low confidence	H100 NVL 94 GB NVIDIA	94 GB	3,940 GB/s	Mar 2023	8.2 GB	Q8_0	Comfortable
203 tok/s 122–325 · low confidence	H100 PCIe 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	8.2 GB	Q8_0	Comfortable
203 tok/s 122–325 · low confidence	H100 SXM5 80 GB NVIDIA	80 GB	3,360 GB/s	Oct 2022	8.2 GB	Q8_0	Comfortable
203 tok/s 122–325 · low confidence	H100 SXM5 94 GB NVIDIA	94 GB	3,360 GB/s	Mar 2023	8.2 GB	Q8_0	Comfortable
203 tok/s 122–325 · low confidence	H100 SXM5 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	8.2 GB	Q8_0	Comfortable
203 tok/s 122–325 · low confidence	H800 SXM5 NVIDIA	80 GB	3,360 GB/s	Mar 2023	8.2 GB	Q8_0	Comfortable
155 tok/s 93–248 · low confidence	Radeon Instinct MI250 AMD	128 GB	3,280 GB/s	Nov 2021	8.2 GB	Q8_0	Comfortable
155 tok/s 93–248 · low confidence	Radeon Instinct MI250X AMD	128 GB	3,280 GB/s	Nov 2021	8.2 GB	Q8_0	Comfortable
131 tok/s 79–210 · low confidence	CMP 170HX 8 GB NVIDIA	8 GB	1,490 GB/s	Sep 2021	6.6 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	8.2 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	8.2 GB	Q8_0	Comfortable
123 tok/s 74–197 · low confidence	A100 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Nov 2020	8.2 GB	Q8_0	Comfortable
123 tok/s 74–197 · low confidence	A100X NVIDIA	80 GB	2,040 GB/s	Jun 2021	8.2 GB	Q8_0	Comfortable
123 tok/s 74–197 · low confidence	A800 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Aug 2022	8.2 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,EleutherAI,University of Toronto,Vector Institute,University of Cambridge,Carnegie Mellon University (CMU),University of Washington
Organisation type: Academia,Research collective,Academia,Academia,Academia,Academia,Academia
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-7B
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: 7B
Training data: 55,000,000,000 tokens
Epochs: 3.64
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: 1.2 × 10²³ FLOP
How it was established: Operation counting,Hardware
Fine-tuning compute: 8.1 × 10²¹ 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: 23,000
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 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 Llemma 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

Tesla K20c

Memory needed

4.1 GB

Fastest

484 tok/s

Llemma 7B is small enough at 7B parameters that hardware is rarely the obstacle — 589 of the cards we track can run it, including cards several years old.

At the low end, a Tesla K20c handles it — 5 GB, at Q3_K_M, for about 28.9 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.

Where it came from

Llemma 7B was published by Princeton University,EleutherAI,University of Toronto,Vector Institute,University of Cambridge,Carnegie Mellon University (CMU),University of Washington, in United States of America, in October 2023. It comes out of academia,Research collective,Academia,Academia,Academia,Academia,Academia.

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-7B — most models at this scale are adapted from an existing base rather than built from nothing.

The weights being open is what puts this page in the calculator rather than only in the catalogue: it is a model you can actually hold. It is published under the EleutherAI organisation on Hugging Face.

Understanding the speeds

Half the cards that hold it manage more than 26.1 tokens per second, and 559 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.

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.

Training and provenance

Training it took roughly 1.2 × 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 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

Look at what Llemma 7B actually needs — around 4.1 GB at Q3_K_M. No amount of processing power compensates for a card that cannot hold it.
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 Llemma 7B can slip off a card that handles short questions easily.
03

Decide how much compression you will accept

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 7B by squeezing it further than you would want.
04

Compare tokens per second, not specifications

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

Look at the headroom, not just the fit

The fit column separates cards that just manage Llemma 7B from those with room to spare. Buy for the second if the context might grow.
06

Check the card from the other side

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 7B alone — a card is usually bought for more than one model.

Answers

Llemma 7B — common questions

How many parameters does Llemma 7B have?

Llemma 7B has 7B 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 7B?

Llemma 7B was published by Princeton University,EleutherAI,University of Toronto,Vector Institute,University of Cambridge,Carnegie Mellon University (CMU),University of Washington, based in United States of America, categorised as academia,Research collective,Academia,Academia,Academia,Academia,Academia.

When was Llemma 7B released?

Llemma 7B 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 7B used for?

Llemma 7B works in Mathematics, Language, and is recorded as handling mathematical reasoning, Language modeling/generation, Question answering, 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 Llemma 7B?

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 7B?

Around 1.2 × 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 7B if it does not fit in my GPU?

Partly. Layers that do not fit sit in system memory and run at a fraction of the speed, so a mostly-offloaded Llemma 7B is rarely worth using — the nearest miss we calculate is short by 1.3 GB. Every figure here assumes the whole model is on the card.

Would two GPUs run Llemma 7B faster?

Two cards buy memory rather than speed. That matters for Llemma 7B only if one card cannot hold it — 589 can, so a second adds little.

Why does the quantisation differ between cards for Llemma 7B?

Because capacity varies, so does how hard Llemma 7B has to be squeezed — 4 distinct levels appear in the table above. Set a minimum quality to compare at one.

How accurate are these Llemma 7B speed estimates?

They are calculated from specifications rather than measured, and each carries a range — 290–774 tok/s on the B200, for instance. The same model and card vary by thirty to fifty per cent depending on the inference software and its version.

What GPU do I need to run Llemma 7B?

The smallest card in our catalogue that holds Llemma 7B is the Tesla K20c, with 5 GB of memory. It runs the model at Q3_K_M using about 4.1 GB, and produces roughly 28.9 tokens per second. 589 cards in total can run it.

How fast is Llemma 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 559 of the cards that can run Llemma 7B clear that.

How much VRAM does Llemma 7B need?

About 4.1 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.

Can I run Llemma 7B on a 8 GB GPU?

Yes. A CMP 170HX 8 GB with 8 GB runs it at Q6_K, using about 6.6 GB and generating roughly 131 tokens per second — a tight fit.

Can I run Llemma 7B on a 12 GB GPU?

Yes. A GeForce RTX 3080 Ti with 12 GB runs it at Q8_0, using about 8.2 GB and generating roughly 55.2 tokens per second — a comfortable fit.

Can I run Llemma 7B on a 16 GB GPU?

Yes. A Tesla V100 SXM2 16 GB with 16 GB runs it at Q8_0, using about 8.2 GB and generating roughly 68.4 tokens per second — a comfortable fit.

Can I run Llemma 7B on a 24 GB GPU?

Yes. A GeForce RTX 5090 D V2 with 24 GB runs it at Q8_0, using about 8.2 GB and generating roughly 81.1 tokens per second — a comfortable fit.

Is Llemma 7B open source?

Its weights are published, so Llemma 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