LaNet-L (CIFAR-10) TPS calculator

Open weights Brown University,Facebook 44.1M parameters June 2019

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

818 cards that can run it

818 cards we hold specifications for

Smallest card that fits

Tesla C1080

4 GB · Q8_0 · 836 tok/s

Fastest card

B200

76,831 tok/s · 180 GB

Which GPUs can run LaNet-L (CIFAR-10)?

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

818 cards match

Calculating

					Needs	Quantisation	Fit
76,831 tok/s 46,098–122,929 · low confidence	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	0.7 GB	Q8_0	Comfortable
76,831 tok/s 46,098–122,929 · low confidence	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	0.7 GB	Q8_0	Comfortable
61,351 tok/s 36,811–98,162 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	0.7 GB	Q8_0	Comfortable
61,351 tok/s 36,811–98,162 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	0.7 GB	Q8_0	Comfortable
49,066 tok/s 29,440–78,506 · low confidence	Radeon Instinct MI300 AMD	128 GB	6,550 GB/s	Jan 2023	0.7 GB	Q8_0	Comfortable
46,963 tok/s 28,178–75,140 · low confidence	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	0.7 GB	Q8_0	Comfortable
46,963 tok/s 28,178–75,140 · low confidence	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	0.7 GB	Q8_0	Comfortable
44,946 tok/s 26,968–71,914 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	0.7 GB	Q8_0	Comfortable
39,890 tok/s 23,934–63,823 · low confidence	Radeon Instinct MI300A AMD	128 GB	5,325 GB/s	Dec 2023	0.7 GB	Q8_0	Comfortable
39,890 tok/s 23,934–63,823 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	0.7 GB	Q8_0	Comfortable
39,890 tok/s 23,934–63,823 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	0.7 GB	Q8_0	Comfortable
37,839 tok/s 22,703–60,543 · low confidence	H100 NVL 94 GB NVIDIA	94 GB	3,940 GB/s	Mar 2023	0.7 GB	Q8_0	Comfortable
32,269 tok/s 19,361–51,630 · low confidence	H100 PCIe 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	0.7 GB	Q8_0	Comfortable
32,269 tok/s 19,361–51,630 · low confidence	H100 SXM5 80 GB NVIDIA	80 GB	3,360 GB/s	Oct 2022	0.7 GB	Q8_0	Comfortable
32,269 tok/s 19,361–51,630 · low confidence	H100 SXM5 94 GB NVIDIA	94 GB	3,360 GB/s	Mar 2023	0.7 GB	Q8_0	Comfortable
32,269 tok/s 19,361–51,630 · low confidence	H100 SXM5 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	0.7 GB	Q8_0	Comfortable
32,269 tok/s 19,361–51,630 · low confidence	H800 SXM5 NVIDIA	80 GB	3,360 GB/s	Mar 2023	0.7 GB	Q8_0	Comfortable
24,570 tok/s 14,742–39,313 · low confidence	Radeon Instinct MI250 AMD	128 GB	3,280 GB/s	Nov 2021	0.7 GB	Q8_0	Comfortable
24,570 tok/s 14,742–39,313 · low confidence	Radeon Instinct MI250X AMD	128 GB	3,280 GB/s	Nov 2021	0.7 GB	Q8_0	Comfortable
20,475 tok/s 12,285–32,761 · low confidence	Data Center GPU Max 1550 Intel	128 GB	3,280 GB/s	Jan 2023	0.7 GB	Q8_0	Comfortable
20,038 tok/s 12,023–32,061 · low confidence	Data Center GPU Max Subsystem Intel	128 GB	3,210 GB/s	Jan 2023	0.7 GB	Q8_0	Comfortable
19,592 tok/s 11,755–31,347 · low confidence	A100 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Nov 2020	0.7 GB	Q8_0	Comfortable
19,592 tok/s 11,755–31,347 · low confidence	A100X NVIDIA	80 GB	2,040 GB/s	Jun 2021	0.7 GB	Q8_0	Comfortable
19,592 tok/s 11,755–31,347 · low confidence	A800 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Aug 2022	0.7 GB	Q8_0	Comfortable
19,592 tok/s 11,755–31,347 · low confidence	H100 CNX NVIDIA	80 GB	2,040 GB/s	Mar 2023	0.7 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: Brown University,Facebook
Organisation type: Academia,Industry
Country: United States of America
Published: 17 June 2019
Authors: Linnan Wang, Saining Xie, Teng Li, Rodrigo Fonseca, Yuandong Tian

What it does

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

Domain: Vision
Task: Image classification, Neural Architecture Search - NAS
Approach: Supervised
Numerical format: FP16

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: 44.1M
Training data: 60,000 tokens
Epochs: 600

The training run

What it physically took to train: which chips, how many, for how long, and what that drew from the wall.

Chip-hours: 3,600

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 (non-commercial)
Training code: Open (non-commercial)

How it is classified

Labels the source dataset applies when tracking notable models, and how confident it is in the entry.

Why it is tracked: SOTA improvement
Record confidence: Confident
Citations: 48

Sources

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

Reference: Sample-Efficient Neural Architecture Search by Learning Action Space
Last updated: 11 February 2026

The extremes

The ten fastest GPUs that run LaNet-L (CIFAR-10)

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 LaNet-L (CIFAR-10)

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

Tesla C1080

Memory needed

0.7 GB

Fastest

76,831 tok/s

LaNet-L (CIFAR-10) is small enough at 44.1M parameters that hardware is rarely the obstacle — 818 of the cards we track can run it, including cards several years old.

The smallest card that holds it is the Tesla C1080 with 4 GB, running it at Q8_0 and producing around 836 tokens per second.

A B200 is the fastest we calculate for it: about 76,831 tokens per second, from 8,000 GB/s of memory bandwidth.

Background

LaNet-L (CIFAR-10) was published by Brown University,Facebook, in United States of America, in June 2019. It comes out of academia,Industry.

It works in Vision, and is recorded as doing image classification, Neural Architecture Search - NAS.

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

Reading the throughput figures

Half the cards that hold it manage more than 2,157.4 tokens per second, and 818 exceed reading speed outright.

Every weight participates in every token here, so bandwidth is the whole story: the ranking below is effectively a ranking of memory throughput.

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

The training set ran to roughly 60,000 tokens.

It is tracked in the underlying dataset for one reason in particular: sOTA improvement.

Step by step

How to choose a GPU for LaNet-L (CIFAR-10)

The table above has already assessed every card we hold specifications for against this model. Getting to your answer takes six steps.

01

Check what it needs before anything else

Every card here has been checked against LaNet-L (CIFAR-10) — around 0.7 GB at Q8_0. Capacity is the gate — a card either holds it or it does not.
02

Match the context to your actual use

The conversation occupies memory too, and grows as it goes. Set the slider to the length you expect: at long context LaNet-L (CIFAR-10) 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 — Q8_0 on the smallest card that fits. Setting a floor drops the cards that only manage LaNet-L (CIFAR-10) by squeezing it further than you would want.
04

Rank by throughput rather than spec sheet

The speed ordering for LaNet-L (CIFAR-10) is effectively an ordering by memory bandwidth, which is why the B200 tops it at 76,831 tok/s.
05

Look at the headroom, not just the fit

A tight fit runs LaNet-L (CIFAR-10) but leaves nothing spare for a longer conversation; comfortable has headroom. If you expect to grow the context, buy for comfortable.
06

Check the card from the other side

Following a card through to its own page shows every other model it can hold, which is the question that follows once LaNet-L (CIFAR-10) is settled.

Answers

LaNet-L (CIFAR-10) — common questions

Who created LaNet-L (CIFAR-10)?

LaNet-L (CIFAR-10) was published by Brown University,Facebook, based in United States of America, categorised as academia,Industry.

When was LaNet-L (CIFAR-10) released?

LaNet-L (CIFAR-10) was published in June 2019. 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 LaNet-L (CIFAR-10) used for?

LaNet-L (CIFAR-10) works in Vision, and is recorded as handling image classification, Neural Architecture Search - NAS. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.

Where can I download LaNet-L (CIFAR-10)?

The weights for LaNet-L (CIFAR-10) are published, though we do not hold a repository link for it. This site calculates hardware requirements rather than hosting model files.

Can I run LaNet-L (CIFAR-10) if it does not fit in my GPU?

It can be split between the card and system memory, but LaNet-L (CIFAR-10) generates painfully slowly that way. Nothing on this page assumes offloading.

Would two GPUs run LaNet-L (CIFAR-10) faster?

A second card roughly doubles the memory available but not the generation rate. With 818 cards already able to run LaNet-L (CIFAR-10) alone, the case for pairing is weak.

Why does the quantisation differ between cards for LaNet-L (CIFAR-10)?

Because capacity varies, so does how hard LaNet-L (CIFAR-10) has to be squeezed — 1 distinct levels appear in the table above. Set a minimum quality to compare at one.

How accurate are these LaNet-L (CIFAR-10) speed estimates?

These are estimates with real error bars. The fastest result here, 46,098–122,929 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 LaNet-L (CIFAR-10)?

The smallest card in our catalogue that holds LaNet-L (CIFAR-10) is the Tesla C1080, with 4 GB of memory. It runs the model at Q8_0 using about 0.7 GB, and produces roughly 836 tokens per second. 818 cards in total can run it.

How fast is LaNet-L (CIFAR-10) on a GPU?

It depends on the card. The quickest we calculate is a B200 at about 76,831 tokens per second; the slowest that still runs it manages considerably less. Reading speed is around ten tokens per second, and 818 of the cards that can run LaNet-L (CIFAR-10) clear that.

How much VRAM does LaNet-L (CIFAR-10) need?

About 0.7 GB at Q8_0 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 LaNet-L (CIFAR-10) on a 8 GB GPU?

Yes. A CMP 170HX 8 GB with 8 GB runs it at Q8_0, using about 0.7 GB and generating roughly 14,310 tokens per second — a comfortable fit.

Can I run LaNet-L (CIFAR-10) on a 12 GB GPU?

Yes. A GeForce RTX 3080 Ti with 12 GB runs it at Q8_0, using about 0.7 GB and generating roughly 8,763 tokens per second — a comfortable fit.

Can I run LaNet-L (CIFAR-10) on a 16 GB GPU?

Yes. A Tesla V100 SXM2 16 GB with 16 GB runs it at Q8_0, using about 0.7 GB and generating roughly 10,852 tokens per second — a comfortable fit.

Can I run LaNet-L (CIFAR-10) on a 24 GB GPU?

Yes. A GeForce RTX 5090 D V2 with 24 GB runs it at Q8_0, using about 0.7 GB and generating roughly 12,869 tokens per second — a comfortable fit.

Is LaNet-L (CIFAR-10) open source?

Its weights are published, so LaNet-L (CIFAR-10) 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 LaNet-L (CIFAR-10) have?

LaNet-L (CIFAR-10) has 44.1M parameters. 44.1M. 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.

Source

Original publication

Record last updated 11 February 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