PLLaMa TPS calculator

Open weights University of California Santa Barbara (UCSB),University of Lincoln,Chinese Academy of Agricultural Sciences,Swedish University of Agricultural Sciences 13B parameters January 2024

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 · Q3_K_M · 18.3 tok/s

Fastest card

B200

261 tok/s · 180 GB

Which GPUs can run PLLaMa?

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
261 tok/s 156–417 · low confidence	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	14.6 GB	Q8_0	Comfortable
261 tok/s 156–417 · low confidence	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	14.6 GB	Q8_0	Comfortable
208 tok/s 125–333 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	14.6 GB	Q8_0	Comfortable
208 tok/s 125–333 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	14.6 GB	Q8_0	Comfortable
166 tok/s 100–266 · low confidence	Radeon Instinct MI300 AMD	128 GB	6,550 GB/s	Jan 2023	14.6 GB	Q8_0	Comfortable
159 tok/s 96–255 · low confidence	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	14.6 GB	Q8_0	Comfortable
159 tok/s 96–255 · low confidence	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	14.6 GB	Q8_0	Comfortable
152 tok/s 91–244 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	14.6 GB	Q8_0	Comfortable
135 tok/s 81–217 · low confidence	Radeon Instinct MI300A AMD	128 GB	5,325 GB/s	Dec 2023	14.6 GB	Q8_0	Comfortable
135 tok/s 81–217 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	14.6 GB	Q8_0	Comfortable
135 tok/s 81–217 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	14.6 GB	Q8_0	Comfortable
131 tok/s 79–210 · low confidence	CMP 170HX 8 GB NVIDIA	8 GB	1,490 GB/s	Sep 2021	7.1 GB	Q3_K_M	Tight
128 tok/s 77–205 · low confidence	H100 NVL 94 GB NVIDIA	94 GB	3,940 GB/s	Mar 2023	14.6 GB	Q8_0	Comfortable
117 tok/s 70–188 · low confidence	CMP 170HX 10 GB NVIDIA	10 GB	1,560 GB/s	Sep 2021	8.6 GB	Q4_K_M	Tight
109 tok/s 66–175 · low confidence	H100 PCIe 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	14.6 GB	Q8_0	Comfortable
109 tok/s 66–175 · low confidence	H100 SXM5 80 GB NVIDIA	80 GB	3,360 GB/s	Oct 2022	14.6 GB	Q8_0	Comfortable
109 tok/s 66–175 · low confidence	H100 SXM5 94 GB NVIDIA	94 GB	3,360 GB/s	Mar 2023	14.6 GB	Q8_0	Comfortable
109 tok/s 66–175 · low confidence	H100 SXM5 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	14.6 GB	Q8_0	Comfortable
109 tok/s 66–175 · low confidence	H800 SXM5 NVIDIA	80 GB	3,360 GB/s	Mar 2023	14.6 GB	Q8_0	Comfortable
83.4 tok/s 50–133 · low confidence	Radeon Instinct MI250 AMD	128 GB	3,280 GB/s	Nov 2021	14.6 GB	Q8_0	Comfortable
83.4 tok/s 50–133 · low confidence	Radeon Instinct MI250X AMD	128 GB	3,280 GB/s	Nov 2021	14.6 GB	Q8_0	Comfortable
69.5 tok/s 42–111 · low confidence	Data Center GPU Max 1550 Intel	128 GB	3,280 GB/s	Jan 2023	14.6 GB	Q8_0	Comfortable
68.0 tok/s 41–109 · low confidence	Data Center GPU Max Subsystem Intel	128 GB	3,210 GB/s	Jan 2023	14.6 GB	Q8_0	Comfortable
67.5 tok/s 41–108 · low confidence	RTX A5000-8Q NVIDIA	8 GB	768 GB/s	Apr 2021	7.1 GB	Q3_K_M	Tight
66.5 tok/s 40–106 · low confidence	A100 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Nov 2020	14.6 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: University of California Santa Barbara (UCSB),University of Lincoln,Chinese Academy of Agricultural Sciences,Swedish University of Agricultural Sciences
Organisation type: Academia,Academia,Academia
Country: United States of America, United Kingdom of Great Britain and Northern Ireland, China, Sweden
Published: 3 January 2024
Authors: Xianjun Yang, Junfeng Gao, Wenxin Xue, Erik Alexandersson

What it does

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

Domain: Biology
Task: Language modeling/generation
Base model: Llama 2-13B

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: 13B
Training data: tokens
Epochs: 16

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: 1.6 × 10²³ FLOP
How it was established: Hardware

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
Chips used: 8
Wall-clock time: 60 hours
Power draw: 6.3 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 (unrestricted)
Training code: Unreleased
Hugging Face: Xianjun

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: 39

Sources

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

Reference: PLLaMa: An Open-source Large Language Model for Plant Science
Last updated: 25 May 2026

The extremes

The ten fastest GPUs that run PLLaMa

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 PLLaMa

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

Xeon Phi 5110P

Memory needed

7.1 GB

Fastest

261 tok/s

PLLaMa is small enough at 13B parameters that hardware is rarely the obstacle — 509 of the cards we track can run it, including cards several years old.

The smallest card that holds it is the Xeon Phi 5110P with 8 GB, running it at Q3_K_M and producing around 18.3 tokens per second.

The quickest result comes from a B200 at around 261 tokens per second — its 8,000 GB/s of bandwidth is what buys that.

Background

PLLaMa was published by University of California Santa Barbara (UCSB),University of Lincoln,Chinese Academy of Agricultural Sciences,Swedish University of Agricultural Sciences, in United States of America, in January 2024. academia,Academia,Academia is the category the publisher falls under.

It works in Biology, and is recorded as doing language modeling/generation.

It is derived from Llama 2-13B rather than trained from scratch, which is the usual way a specialised model is produced.

Published weights mean the model runs on your machine rather than someone else's, which is what makes the hardware question below answerable at all. It is published under the Xianjun organisation on Hugging Face.

Reading the throughput figures

The median result is around 21.2 tokens per second; 459 cards produce text faster than most people read it.

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 internal architecture is not on file, so memory is approximated from the parameter count and marked accordingly. Expect the real figure to differ, more so at long context.

What went into building it

Training it took roughly 1.6 × 10²³ FLOP of computation, on NVIDIA A100 — a measure of what producing the model cost, not of how fast it answers.

Step by step

How to choose a GPU for PLLaMa

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

Every card here has been checked against PLLaMa — around 7.1 GB at Q3_K_M. Capacity is the gate — a card either holds it or it does not.
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 PLLaMa.
03

Decide how much compression you will accept

The quantisation column varies by card, because a bigger card holds a more accurate copy of PLLaMa — Q3_K_M on the smallest card that fits. Set a floor to hold the comparison at one level.
04

Compare tokens per second, not specifications

Ranking by tokens per second for PLLaMa follows memory bandwidth, not core counts, which is why the B200 tops it at 261 tok/s.
05

Check the fit verdict before buying

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

Answers

PLLaMa — common questions

How much compute was used to train PLLaMa?

Around 1.6 × 10²³ FLOP, on NVIDIA A100. 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 PLLaMa 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 PLLaMa is rarely worth using — the nearest miss we calculate is short by 3.2 GB. Every figure here assumes the whole model is on the card.

Would two GPUs run PLLaMa faster?

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

Why does the quantisation differ between cards for PLLaMa?

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

How accurate are these PLLaMa speed estimates?

These are estimates with real error bars. The fastest result here, 156–417 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 PLLaMa?

The smallest card in our catalogue that holds PLLaMa is the Xeon Phi 5110P, with 8 GB of memory. It runs the model at Q3_K_M using about 7.1 GB, and produces roughly 18.3 tokens per second. 509 cards in total can run it.

How fast is PLLaMa on a GPU?

It depends on the card. The quickest we calculate is a B200 at about 261 tokens per second; the slowest that still runs it manages considerably less. Reading speed is around ten tokens per second, and 459 of the cards that can run PLLaMa clear that.

How much VRAM does PLLaMa need?

About 7.1 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 PLLaMa on a 8 GB GPU?

Yes. A CMP 170HX 8 GB with 8 GB runs it at Q3_K_M, using about 7.1 GB and generating roughly 131 tokens per second — a tight fit.

Can I run PLLaMa on a 12 GB GPU?

Yes. A GeForce RTX 3080 Ti with 12 GB runs it at Q5_K_M, using about 10.1 GB and generating roughly 53.1 tokens per second — a tight fit.

Can I run PLLaMa on a 16 GB GPU?

Yes. A Tesla V100 SXM2 16 GB with 16 GB runs it at Q6_K, using about 11.6 GB and generating roughly 53.5 tokens per second — a comfortable fit.

Can I run PLLaMa on a 24 GB GPU?

Yes. A GeForce RTX 5090 D V2 with 24 GB runs it at Q8_0, using about 14.6 GB and generating roughly 43.7 tokens per second — a comfortable fit.

Is PLLaMa open source?

Its weights are published, so PLLaMa 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 PLLaMa have?

PLLaMa has 13B parameters. 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 PLLaMa?

PLLaMa was published by University of California Santa Barbara (UCSB),University of Lincoln,Chinese Academy of Agricultural Sciences,Swedish University of Agricultural Sciences, based in United States of America, categorised as academia,Academia,Academia.

When was PLLaMa released?

PLLaMa was published in January 2024. 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 PLLaMa used for?

PLLaMa works in Biology, and is recorded as handling language modeling/generation. These are the areas it was designed around; they describe intent rather than a hard boundary.

Where can I download PLLaMa?

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

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