LFM2-24B-A2B TPS calculator

Open weights Liquid AI 24B parameters February 2026

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

241 cards that can run it

818 cards we hold specifications for

Smallest card that fits

Xeon Phi 7120P

16 GB · Q4_K_M · 51.8 tok/s

Fastest card

B200

784 tok/s · 180 GB

Which GPUs can run LFM2-24B-A2B?

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

241 cards match

Calculating

					Needs	Quantisation	Fit
784 tok/s 471–1,255 · low confidence	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	25.1 GB	Q8_0	Comfortable
784 tok/s 471–1,255 · low confidence	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	25.1 GB	Q8_0	Comfortable
626 tok/s 376–1,002 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	25.1 GB	Q8_0	Comfortable
626 tok/s 376–1,002 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	25.1 GB	Q8_0	Comfortable
501 tok/s 301–801 · low confidence	Radeon Instinct MI300 AMD	128 GB	6,550 GB/s	Jan 2023	25.1 GB	Q8_0	Comfortable
479 tok/s 288–767 · low confidence	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	25.1 GB	Q8_0	Comfortable
479 tok/s 288–767 · low confidence	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	25.1 GB	Q8_0	Comfortable
459 tok/s 275–734 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	25.1 GB	Q8_0	Comfortable
407 tok/s 244–652 · low confidence	Radeon Instinct MI300A AMD	128 GB	5,325 GB/s	Dec 2023	25.1 GB	Q8_0	Comfortable
407 tok/s 244–652 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	25.1 GB	Q8_0	Comfortable
407 tok/s 244–652 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	25.1 GB	Q8_0	Comfortable
386 tok/s 232–618 · low confidence	H100 NVL 94 GB NVIDIA	94 GB	3,940 GB/s	Mar 2023	25.1 GB	Q8_0	Comfortable
329 tok/s 198–527 · low confidence	H100 PCIe 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	25.1 GB	Q8_0	Comfortable
329 tok/s 198–527 · low confidence	H100 SXM5 80 GB NVIDIA	80 GB	3,360 GB/s	Oct 2022	25.1 GB	Q8_0	Comfortable
329 tok/s 198–527 · low confidence	H100 SXM5 94 GB NVIDIA	94 GB	3,360 GB/s	Mar 2023	25.1 GB	Q8_0	Comfortable
329 tok/s 198–527 · low confidence	H100 SXM5 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	25.1 GB	Q8_0	Comfortable
329 tok/s 198–527 · low confidence	H800 SXM5 NVIDIA	80 GB	3,360 GB/s	Mar 2023	25.1 GB	Q8_0	Comfortable
256 tok/s 153–409 · low confidence	Tesla V100 SXM2 16 GB NVIDIA	16 GB	1,130 GB/s	Nov 2019	13.9 GB	Q4_K_M	Tight
251 tok/s 150–401 · low confidence	Radeon Instinct MI250 AMD	128 GB	3,280 GB/s	Nov 2021	25.1 GB	Q8_0	Comfortable
251 tok/s 150–401 · low confidence	Radeon Instinct MI250X AMD	128 GB	3,280 GB/s	Nov 2021	25.1 GB	Q8_0	Comfortable
217 tok/s 130–348 · low confidence	GeForce RTX 5080 NVIDIA	16 GB	960 GB/s	Jan 2025	13.9 GB	Q4_K_M	Tight
209 tok/s 125–334 · low confidence	Data Center GPU Max 1550 Intel	128 GB	3,280 GB/s	Jan 2023	25.1 GB	Q8_0	Comfortable
205 tok/s 123–327 · low confidence	Data Center GPU Max Subsystem Intel	128 GB	3,210 GB/s	Jan 2023	25.1 GB	Q8_0	Comfortable
203 tok/s 122–325 · low confidence	Tesla V100 DGXS 16 GB NVIDIA	16 GB	897 GB/s	Mar 2018	13.9 GB	Q4_K_M	Tight
203 tok/s 122–325 · low confidence	Tesla V100 PCIe 16 GB NVIDIA	16 GB	897 GB/s	Jun 2017	13.9 GB	Q4_K_M	Tight

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: Liquid AI
Organisation type: Industry
Country: United States of America
Published: 25 February 2026

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: 24B
Training data: tokens

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)

The extremes

The ten fastest GPUs that run LFM2-24B-A2B

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 LFM2-24B-A2B

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 7120P

Memory needed

13.9 GB

Fastest

784 tok/s

LFM2-24B-A2B reaches a parameter count of 24B. That lands in the range a serious desktop card can handle once the weights are compressed. The number of cards we track that can run it: 241.

The smallest card that holds it is Xeon Phi 7120P, with a memory capacity of 16 GB, running it at a compression of Q4_K_M and producing around 51.8 tokens per second.

The quickest result comes from B200, generating roughly 784 tokens per second on the strength of a memory bandwidth of 8,000 GB/s.

About this model

LFM2-24B-A2B was published by Liquid AI, in the country recorded as United States of America, during February 2026. It comes out of an organisation categorised as industry.

It works in the domain of Language, and is recorded as performing the task of language modeling/generation.

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

How fast it runs, and why

Half the cards that hold it manage more than 101.4 tokens per second. Producing text faster than most people read it: 239 of them.

Because it routes each token through a subset of its weights, it produces text at the pace of a much smaller model. The catch is memory: all of it still has to fit, so the speed is a bonus rather than a discount on hardware.

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.

Step by step

How to choose a GPU for LFM2-24B-A2B

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

Start from what it actually needs, which is the requirement of LFM2-24B-A2B, needing around 13.9 GB at a compression of Q4_K_M. That figure, not the headline performance of a card, is what decides whether it runs.
02

Set the context length you will work at

Set the context to what you will actually use. The cache grows with the conversation, and it is the usual reason a card that seemed fine stops fitting LFM2-24B-A2B.
03

Decide how much compression you will accept

Each card runs the least-compressed copy it can hold, reaching a compression of Q4_K_M on the smallest card that fits. Setting a minimum quality drops the cards that only manage it by squeezing further than you would want, and holds the comparison at one level.
04

Rank by throughput rather than spec sheet

Ranking by tokens per second follows memory bandwidth rather than core counts, for LFM2-24B-A2B. It will not match a gaming ordering, because generation is bound by memory bandwidth. The card topping the list is B200, at 784 tok/s.
05

Look at the headroom, not just the fit

Tight means it loads and works with no room to raise the context later, in the case of LFM2-24B-A2B. Comfortable means you can grow the context later. That difference matters more than a few tokens per second, so buy for comfortable if you expect to.
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 you have settled on LFM2-24B-A2B.

Answers

LFM2-24B-A2B — common questions

LFM2-24B-A2B— what is it used for?

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

LFM2-24B-A2B— where can I download it?

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

LFM2-24B-A2B— can I run it if it does not fit in my GPU?

Only by offloading, which is usually a false economy: the part held in system memory drags the whole thing down. The nearest miss we calculate falls short by 3.1 GB. Every figure here assumes the whole model is resident on the card.

LFM2-24B-A2B— would two GPUs run it faster?

Capacity adds across cards; throughput does not. The number of cards already holding it on their own: 241. So a second card is rarely the answer here.

LFM2-24B-A2B— why does the quantisation differ between cards?

Because capacity varies, so does how hard it has to be squeezed. The number of distinct levels in the table above: 4. Bigger cards get the more accurate version, and the quality floor above pins the comparison to one level.

LFM2-24B-A2B— how accurate are these speed estimates?

They are calculated from specifications rather than measured, and each carries a range. One example: 471–1,255 tok/s on B200. The same model and card vary by thirty to fifty per cent depending on the inference software and its version.

LFM2-24B-A2B— what GPU do I need to run it?

The smallest card in our catalogue that holds it is Xeon Phi 7120P, with a memory capacity of 16 GB. It runs the model at a compression of Q4_K_M using about 13.9 GB, and produces roughly 51.8 tokens per second. The number of cards able to run it in total: 241.

LFM2-24B-A2B— how fast is it on a GPU?

It depends on the card. The quickest we calculate is B200, at about 784 tokens per second; the slowest that still runs it manages considerably less. Reading speed is around ten tokens per second, and the number of cards clearing that: 239.

LFM2-24B-A2B— how much VRAM does it need?

It needs about 13.9 GB at a compression of Q4_K_M, 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.

LFM2-24B-A2B— can I run it on a GPU holding 16 GB?

Yes. The card Tesla V100 SXM2 16 GB, holding 16 GB, runs it at a compression of Q4_K_M, using about 13.9 GB and generating roughly 256 tokens per second. The fit is tight.

LFM2-24B-A2B— can I run it on a GPU holding 24 GB?

Yes. The card GeForce RTX 5090 D V2, holding 24 GB, runs it at a compression of Q6_K, using about 19.5 GB and generating roughly 191 tokens per second. The fit is tight.

LFM2-24B-A2B— is it open source?

Its weights are published, so it 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.

LFM2-24B-A2B— how many parameters does it have?

It has a parameter count of 24B. 24B total, 2B active. 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.

LFM2-24B-A2B— who created it?

It was published by Liquid AI, based in United States of America, an organisation categorised as industry.

LFM2-24B-A2B— when was it released?

It was published in 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