LaMemo TPS calculator

Open weights Tsinghua University,NetEase,Oppo Mobile Telecommunications 151M parameters April 2022

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 · 244 tok/s

Fastest card

B200

22,439 tok/s · 180 GB

Which GPUs can run LaMemo?

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
22,439 tok/s 13,463–35,902 · low confidence	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	0.9 GB	Q8_0	Comfortable
22,439 tok/s 13,463–35,902 · low confidence	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	0.9 GB	Q8_0	Comfortable
17,918 tok/s 10,751–28,669 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	0.9 GB	Q8_0	Comfortable
17,918 tok/s 10,751–28,669 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	0.9 GB	Q8_0	Comfortable
14,330 tok/s 8,598–22,928 · low confidence	Radeon Instinct MI300 AMD	128 GB	6,550 GB/s	Jan 2023	0.9 GB	Q8_0	Comfortable
13,716 tok/s 8,229–21,945 · low confidence	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	0.9 GB	Q8_0	Comfortable
13,716 tok/s 8,229–21,945 · low confidence	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	0.9 GB	Q8_0	Comfortable
13,127 tok/s 7,876–21,003 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	0.9 GB	Q8_0	Comfortable
11,650 tok/s 6,990–18,640 · low confidence	Radeon Instinct MI300A AMD	128 GB	5,325 GB/s	Dec 2023	0.9 GB	Q8_0	Comfortable
11,650 tok/s 6,990–18,640 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	0.9 GB	Q8_0	Comfortable
11,650 tok/s 6,990–18,640 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	0.9 GB	Q8_0	Comfortable
11,051 tok/s 6,631–17,682 · low confidence	H100 NVL 94 GB NVIDIA	94 GB	3,940 GB/s	Mar 2023	0.9 GB	Q8_0	Comfortable
9,424 tok/s 5,655–15,079 · low confidence	H100 PCIe 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	0.9 GB	Q8_0	Comfortable
9,424 tok/s 5,655–15,079 · low confidence	H100 SXM5 80 GB NVIDIA	80 GB	3,360 GB/s	Oct 2022	0.9 GB	Q8_0	Comfortable
9,424 tok/s 5,655–15,079 · low confidence	H100 SXM5 94 GB NVIDIA	94 GB	3,360 GB/s	Mar 2023	0.9 GB	Q8_0	Comfortable
9,424 tok/s 5,655–15,079 · low confidence	H100 SXM5 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	0.9 GB	Q8_0	Comfortable
9,424 tok/s 5,655–15,079 · low confidence	H800 SXM5 NVIDIA	80 GB	3,360 GB/s	Mar 2023	0.9 GB	Q8_0	Comfortable
7,176 tok/s 4,306–11,481 · low confidence	Radeon Instinct MI250 AMD	128 GB	3,280 GB/s	Nov 2021	0.9 GB	Q8_0	Comfortable
7,176 tok/s 4,306–11,481 · low confidence	Radeon Instinct MI250X AMD	128 GB	3,280 GB/s	Nov 2021	0.9 GB	Q8_0	Comfortable
5,980 tok/s 3,588–9,568 · low confidence	Data Center GPU Max 1550 Intel	128 GB	3,280 GB/s	Jan 2023	0.9 GB	Q8_0	Comfortable
5,852 tok/s 3,511–9,364 · low confidence	Data Center GPU Max Subsystem Intel	128 GB	3,210 GB/s	Jan 2023	0.9 GB	Q8_0	Comfortable
5,722 tok/s 3,433–9,155 · low confidence	A100 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Nov 2020	0.9 GB	Q8_0	Comfortable
5,722 tok/s 3,433–9,155 · low confidence	A100X NVIDIA	80 GB	2,040 GB/s	Jun 2021	0.9 GB	Q8_0	Comfortable
5,722 tok/s 3,433–9,155 · low confidence	A800 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Aug 2022	0.9 GB	Q8_0	Comfortable
5,722 tok/s 3,433–9,155 · low confidence	H100 CNX NVIDIA	80 GB	2,040 GB/s	Mar 2023	0.9 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: Tsinghua University,NetEase,Oppo Mobile Telecommunications
Organisation type: Academia,Industry,Industry
Country: China
Published: 15 April 2022
Authors: Haozhe Ji, Rongsheng Zhang, Zhenyu Yang, Zhipeng Hu, Minlie Huang

What it does

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

Domain: Language
Task: Language modeling/generation

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: 151M
Training data: 103,227,021 tokens
Epochs: 79.53

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: Open source

How it is classified

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

Citations: 4
Benchmark data: LaMemo

Sources

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

Reference: LaMemo: Language Modeling with Look-Ahead Memory
Last updated: 25 May 2026

The extremes

The ten fastest GPUs that run LaMemo

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 LaMemo

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

0.9 GB

Fastest

22,439 tok/s

LaMemo is small enough at 151M 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 244 tokens per second.

The quickest result comes from a B200 at around 22,439 tokens per second — its 8,000 GB/s of bandwidth is what buys that.

Where it came from

LaMemo was published by Tsinghua University,NetEase,Oppo Mobile Telecommunications, in China, in April 2022. academia,Industry,Industry is the category the publisher falls under.

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

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.

Understanding the speeds

Half the cards that hold it manage more than 630.1 tokens per second, and 818 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.

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

Around 103,227,021 tokens went into training it.

Step by step

How to choose a GPU for LaMemo

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 LaMemo — around 0.9 GB at Q8_0. Capacity is the gate — a card either holds it or it does not.
02

Decide how long your conversations run

Set the context to what you will actually use. The cache grows with the conversation, and it is the usual reason LaMemo stops fitting a card that seemed fine.
03

Choose how far you will compress it

The quantisation column varies by card, because a bigger card holds a more accurate copy of LaMemo — Q8_0 on the smallest card that fits. Set a floor to hold the comparison at one level.
04

Compare tokens per second, not specifications

Sort by speed to see how cards rank for LaMemo. It will not match a gaming ordering — generation is bound by memory bandwidth, which is why the B200 tops it at 22,439 tok/s.
05

Read the fit column last

A tight fit runs LaMemo but leaves nothing spare for a longer conversation; comfortable has headroom. If you expect to grow the context, buy for comfortable.
06

Open the card you have settled on

Following a card through to its own page shows every other model it can hold, which is the question that follows once LaMemo is settled.

Answers

LaMemo — common questions

Can I run LaMemo if it does not fit in my GPU?

It can be split between the card and system memory, but LaMemo generates painfully slowly that way. Nothing on this page assumes offloading.

Would two GPUs run LaMemo faster?

A second card roughly doubles the memory available but not the generation rate. With 818 cards already able to run LaMemo alone, the case for pairing is weak.

Why does the quantisation differ between cards for LaMemo?

A larger card holds a more accurate copy. Across the cards that run LaMemo, 1 compression levels are used; the floor control above pins it to one.

How accurate are these LaMemo speed estimates?

Every figure is derived from memory bandwidth and model size, not benchmarked. That is why each is published as a range such as 13,463–35,902 tok/s on the B200 rather than a single number.

What GPU do I need to run LaMemo?

The smallest card in our catalogue that holds LaMemo is the Tesla C1080, with 4 GB of memory. It runs the model at Q8_0 using about 0.9 GB, and produces roughly 244 tokens per second. 818 cards in total can run it.

How fast is LaMemo on a GPU?

It depends on the card. The quickest we calculate is a B200 at about 22,439 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 LaMemo clear that.

How much VRAM does LaMemo need?

About 0.9 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 LaMemo on a 8 GB GPU?

Yes. A CMP 170HX 8 GB with 8 GB runs it at Q8_0, using about 0.9 GB and generating roughly 4,179 tokens per second — a comfortable fit.

Can I run LaMemo on a 12 GB GPU?

Yes. A GeForce RTX 3080 Ti with 12 GB runs it at Q8_0, using about 0.9 GB and generating roughly 2,559 tokens per second — a comfortable fit.

Can I run LaMemo on a 16 GB GPU?

Yes. A Tesla V100 SXM2 16 GB with 16 GB runs it at Q8_0, using about 0.9 GB and generating roughly 3,169 tokens per second — a comfortable fit.

Can I run LaMemo on a 24 GB GPU?

Yes. A GeForce RTX 5090 D V2 with 24 GB runs it at Q8_0, using about 0.9 GB and generating roughly 3,758 tokens per second — a comfortable fit.

Is LaMemo open source?

Its weights are published, so LaMemo 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 LaMemo have?

LaMemo has 151M parameters. Table 1. 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 LaMemo?

LaMemo was published by Tsinghua University,NetEase,Oppo Mobile Telecommunications, based in China, categorised as academia,Industry,Industry.

When was LaMemo released?

LaMemo was published in April 2022. 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 LaMemo used for?

LaMemo works in Language, 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 LaMemo?

The weights for LaMemo are published, though we do not hold a repository link for it. This site calculates hardware requirements rather than hosting model files.

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