MAP-Neo TPS calculator

Open weights University of Waterloo,01.AI,Wuhan University 7B parameters July 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

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 MAP-Neo?

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: University of Waterloo,01.AI,Wuhan University
Organisation type: Academia,Industry,Academia
Country: Canada, China
Published: 10 July 2024
Authors: Ge Zhang, Scott Qu, Jiaheng Liu, Chenchen Zhang, Chenghua Lin, Chou Leuang Yu, Danny Pan, Esther Cheng, Jie Liu, Qunshu Lin, Raven Yuan, Tuney Zheng, Wei Pang, Xinrun Du, Yiming Liang, Yinghao Ma, Yizhi Li, Ziyang Ma, Bill Lin, Emmanouil Benetos, Huan Yang, Junting Zhou, Kaijing Ma, Minghao Liu, Morry Niu, Noah Wang, Quehry Que, Ruibo Liu, Sine Liu, Shawn Guo, Soren Gao, Wangchunshu Zhou, Xinyue Z…

What it does

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

Domain: Language
Task: Language modeling/generation, Question answering, Quantitative reasoning, Translation, Code 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: 7B
Training data: 4,500,000,000,000 tokens

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: 1.9 × 10²³ FLOP
How it was established: Operation counting

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 H800 SXM5
Chips used: 512
Power draw: 707.2 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: Open source
Hugging Face: m-a-p

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

Sources

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

Reference: MAP-Neo: Highly Capable and Transparent Bilingual Large Language Model Series
Last updated: 28 November 2025

The extremes

The ten fastest GPUs that run MAP-Neo

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 MAP-Neo

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

MAP-Neo 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.

A B200 is the fastest we calculate for it: about 484 tokens per second, from 8,000 GB/s of memory bandwidth.

About this model

MAP-Neo was published by University of Waterloo,01.AI,Wuhan University, in Canada, in July 2024. The organisation is categorised as academia,Industry,Academia.

It works in Language, and is recorded as doing language modeling/generation, Question answering, Quantitative reasoning, Translation, Code generation.

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 m-a-p organisation on Hugging Face.

How fast it runs, and why

Across every card that can run it, the middle of the range is about 26.1 tokens per second, and 559 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.

Memory here is estimated from size rather than computed from the architecture, which is not recorded for this model — the numbers are indicative rather than exact.

How it was trained

Producing it required around 1.9 × 10²³ FLOP of arithmetic, on NVIDIA H800 SXM5, which is a statement about the training budget rather than about inference.

The training set ran to roughly 4,500,000,000,000 tokens.

Step by step

How to choose a GPU for MAP-Neo

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 MAP-Neo — around 4.1 GB at Q3_K_M. Capacity is the gate — a card either holds it or it does not.
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 MAP-Neo can slip off a card that handles short questions easily.
03

Decide how much compression you will accept

Compression is what makes MAP-Neo fit smaller cards, at some cost in accuracy — Q3_K_M on the smallest card that fits. A minimum quality removes the ones that go too far.
04

Sort by speed

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

Check the fit verdict before buying

Tight means MAP-Neo 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

See what else that card runs

Each card page repeats this sweep for every model we hold. It answers what else the hardware is good for, beyond MAP-Neo.

Answers

MAP-Neo — common questions

How much compute was used to train MAP-Neo?

Around 1.9 × 10²³ FLOP, on NVIDIA H800 SXM5. 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 MAP-Neo 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 1.3 GB. Our figures for MAP-Neo assume it is fully resident.

Would two GPUs run MAP-Neo faster?

Capacity adds across cards; throughput does not. Since 589 of the cards we track already hold MAP-Neo on their own, a second card is rarely the answer here.

Why does the quantisation differ between cards for MAP-Neo?

A larger card holds a more accurate copy. Across the cards that run MAP-Neo, 4 compression levels are used; the floor control above pins it to one.

How accurate are these MAP-Neo 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 290–774 tok/s on the B200 rather than a single number.

What GPU do I need to run MAP-Neo?

The smallest card in our catalogue that holds MAP-Neo 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 MAP-Neo 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 MAP-Neo clear that.

How much VRAM does MAP-Neo 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 MAP-Neo 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 MAP-Neo 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 MAP-Neo 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 MAP-Neo 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 MAP-Neo open source?

Its weights are published, so MAP-Neo 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 MAP-Neo have?

MAP-Neo has 7B parameters. 7B. 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 MAP-Neo?

MAP-Neo was published by University of Waterloo,01.AI,Wuhan University, based in Canada, categorised as academia,Industry,Academia.

When was MAP-Neo released?

MAP-Neo was published in July 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 MAP-Neo used for?

MAP-Neo works in Language, and is recorded as handling language modeling/generation, Question answering, Quantitative reasoning, Translation, Code generation. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.

Where can I download MAP-Neo?

Its weights are published under the m-a-p 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 28 November 2025

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