Ling-flash-base-2.0-20T TPS calculator

Open weights Ant Group 100B parameters September 2025

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

43 cards that can run it

818 cards we hold specifications for

Smallest card that fits

Radeon Instinct MI200

64 GB · IQ4_XS · 13.3 tok/s

Fastest card

B200

33.9 tok/s · 180 GB

Which GPUs can run Ling-flash-base-2.0-20T?

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

43 cards match

Calculating

					Needs	Quantisation	Fit
33.9 tok/s 20–54 · low confidence	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	107.8 GB	Q8_0	Comfortable
33.9 tok/s 20–54 · low confidence	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	107.8 GB	Q8_0	Comfortable
32.9 tok/s 20–53 · low confidence	H100 SXM5 80 GB NVIDIA	80 GB	3,360 GB/s	Oct 2022	61.2 GB	Q4_K_M	Tight
32.9 tok/s 20–53 · low confidence	H800 SXM5 NVIDIA	80 GB	3,360 GB/s	Mar 2023	61.2 GB	Q4_K_M	Tight
27.1 tok/s 16–43 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	107.8 GB	Q8_0	Comfortable
27.1 tok/s 16–43 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	107.8 GB	Q8_0	Comfortable
24.3 tok/s 15–39 · low confidence	H100 NVL 94 GB NVIDIA	94 GB	3,940 GB/s	Mar 2023	84.5 GB	Q6_K	Tight
21.6 tok/s 13–35 · low confidence	Radeon Instinct MI300 AMD	128 GB	6,550 GB/s	Jan 2023	107.8 GB	Q8_0	Tight
21.0 tok/s 13–34 · low confidence	H100 SXM5 64 GB NVIDIA	64 GB	2,020 GB/s	Mar 2023	55.4 GB	IQ4_XS	Tight
20.7 tok/s 12–33 · low confidence	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	107.8 GB	Q8_0	Tight
20.7 tok/s 12–33 · low confidence	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	107.8 GB	Q8_0	Tight
20.7 tok/s 12–33 · low confidence	H100 PCIe 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	84.5 GB	Q6_K	Tight
20.7 tok/s 12–33 · low confidence	H100 SXM5 94 GB NVIDIA	94 GB	3,360 GB/s	Mar 2023	84.5 GB	Q6_K	Tight
20.7 tok/s 12–33 · low confidence	H100 SXM5 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	84.5 GB	Q6_K	Tight
20.0 tok/s 12–32 · low confidence	A100 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Nov 2020	61.2 GB	Q4_K_M	Tight
20.0 tok/s 12–32 · low confidence	A100X NVIDIA	80 GB	2,040 GB/s	Jun 2021	61.2 GB	Q4_K_M	Tight
20.0 tok/s 12–32 · low confidence	A800 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Aug 2022	61.2 GB	Q4_K_M	Tight
20.0 tok/s 12–32 · low confidence	H100 CNX NVIDIA	80 GB	2,040 GB/s	Mar 2023	61.2 GB	Q4_K_M	Tight
20.0 tok/s 12–32 · low confidence	H100 PCIe 80 GB NVIDIA	80 GB	2,040 GB/s	Oct 2022	61.2 GB	Q4_K_M	Tight
20.0 tok/s 12–32 · low confidence	H800 PCIe 80 GB NVIDIA	80 GB	2,040 GB/s	Mar 2023	61.2 GB	Q4_K_M	Tight
19.8 tok/s 12–32 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	107.8 GB	Q8_0	Comfortable
19.0 tok/s 11–30 · low confidence	A100 PCIe 80 GB NVIDIA	80 GB	1,940 GB/s	Jun 2021	61.2 GB	Q4_K_M	Tight
19.0 tok/s 11–30 · low confidence	A800 PCIe 80 GB NVIDIA	80 GB	1,940 GB/s	Nov 2022	61.2 GB	Q4_K_M	Tight
17.6 tok/s 11–28 · low confidence	Radeon Instinct MI300A AMD	128 GB	5,325 GB/s	Dec 2023	107.8 GB	Q8_0	Tight
17.6 tok/s 11–28 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	107.8 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: Ant Group
Organisation type: Industry
Country: China
Published: 10 September 2025
Authors: Today, Ling-flash-2.0 is officially open-sourced! 🚀 Following the release of the language model Ling-mini-2.0 and the thinking model Ring-mini-2.0, we are now open-sourcing the third MoE LLM under the Ling 2.0 architecture: Ling-flash-2.0, a language model with 100B total parameters and 6.1B activated parameters (4.8B non-embedding). Trained on 20T+ tokens of high-quality data, together with super…

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
Numerical format: FP8

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: 100B
Training data: 20,000,000,000,000 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: 7.3 × 10²³ FLOP
How it was established: Operation counting

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: inclusionAI

How it is classified

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

Record confidence: Confident

Sources

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

Reference: Ling-flash-base-2.0-20T
Last updated: 28 November 2025

The extremes

The ten fastest GPUs that run Ling-flash-base-2.0-20T

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 Ling-flash-base-2.0-20T

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

Radeon Instinct MI200

Memory needed

55.4 GB

Fastest

33.9 tok/s

Ling-flash-base-2.0-20T sits at 100B parameters, which puts it above consumer hardware and into the range where a card is bought for this purpose rather than repurposed for it. 43 of the cards we track can hold it.

The smallest card that holds it is the Radeon Instinct MI200 with 64 GB, running it at IQ4_XS and producing around 13.3 tokens per second.

Top of the range is the B200, at roughly 33.9 tokens per second thanks to 8,000 GB/s of bandwidth.

Background

Ling-flash-base-2.0-20T was published by Ant Group, in China, in September 2025. The organisation is categorised as industry.

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

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 inclusionAI organisation on Hugging Face.

Reading the throughput figures

Half the cards that hold it manage more than 19.0 tokens per second, and 36 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.

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.

Training and provenance

Producing it required around 7.3 × 10²³ FLOP of arithmetic, which is a statement about the training budget rather than about inference.

The training set ran to roughly 20,000,000,000,000 tokens.

Step by step

How to choose a GPU for Ling-flash-base-2.0-20T

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

The table lists every card that can hold Ling-flash-base-2.0-20T — around 55.4 GB at IQ4_XS. That figure, not the card's headline performance, is what decides whether it runs.
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 Ling-flash-base-2.0-20T stops fitting a card that seemed fine.
03

Decide how much compression you will accept

The quantisation column varies by card, because a bigger card holds a more accurate copy of Ling-flash-base-2.0-20T — IQ4_XS on the smallest card that fits. Set a floor to hold the comparison at one level.
04

Sort by speed

Sort by speed to see how cards rank for Ling-flash-base-2.0-20T. It will not match a gaming ordering — generation is bound by memory bandwidth, which is why the B200 tops it at 33.9 tok/s.
05

Check the fit verdict before buying

A tight fit runs Ling-flash-base-2.0-20T 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

Each card page repeats this sweep for every model we hold. It answers what else the hardware is good for, beyond Ling-flash-base-2.0-20T.

Answers

Ling-flash-base-2.0-20T — common questions

How many parameters does Ling-flash-base-2.0-20T have?

Ling-flash-base-2.0-20T has 100B parameters. 100B total parameters and 6.1B activated parameters (4.8B non-embedding). 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 Ling-flash-base-2.0-20T?

Ling-flash-base-2.0-20T was published by Ant Group, based in China, categorised as industry.

When was Ling-flash-base-2.0-20T released?

Ling-flash-base-2.0-20T was published in September 2025.

What is Ling-flash-base-2.0-20T used for?

Ling-flash-base-2.0-20T works in Language, and is recorded as handling language modeling/generation, Question answering. 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 Ling-flash-base-2.0-20T?

Its weights are published under the inclusionAI 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 Ling-flash-base-2.0-20T?

Around 7.3 × 10²³ FLOP. 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 Ling-flash-base-2.0-20T if it does not fit in my GPU?

It can be split between the card and system memory, but Ling-flash-base-2.0-20T generates painfully slowly that way — the nearest miss we calculate is short by 18.0 GB. Nothing on this page assumes offloading.

Would two GPUs run Ling-flash-base-2.0-20T faster?

Two cards buy memory rather than speed. That matters for Ling-flash-base-2.0-20T only if one card cannot hold it — 43 can, so a second adds little.

Why does the quantisation differ between cards for Ling-flash-base-2.0-20T?

Each card is shown running the least-compressed copy it can hold, and Ling-flash-base-2.0-20T appears at 5 different compression levels across the cards that fit it. Bigger cards get the more accurate version.

How accurate are these Ling-flash-base-2.0-20T 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 20–54 tok/s on the B200 rather than a single number.

What GPU do I need to run Ling-flash-base-2.0-20T?

The smallest card in our catalogue that holds Ling-flash-base-2.0-20T is the Radeon Instinct MI200, with 64 GB of memory. It runs the model at IQ4_XS using about 55.4 GB, and produces roughly 13.3 tokens per second. 43 cards in total can run it.

How fast is Ling-flash-base-2.0-20T on a GPU?

It depends on the card. The quickest we calculate is a B200 at about 33.9 tokens per second; the slowest that still runs it manages considerably less. Reading speed is around ten tokens per second, and 36 of the cards that can run Ling-flash-base-2.0-20T clear that.

How much VRAM does Ling-flash-base-2.0-20T need?

About 55.4 GB at IQ4_XS 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.

Is Ling-flash-base-2.0-20T open source?

Its weights are published, so Ling-flash-base-2.0-20T 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 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