Mamba-2.8B TPS calculator

Open weights Carnegie Mellon University (CMU),Princeton University 2.8B parameters December 2023

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 · Q6_K · 19.1 tok/s

Fastest card

B200

1,210 tok/s · 180 GB

Which GPUs can run Mamba-2.8B?

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
1,210 tok/s 726–1,936 · low confidence	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	3.7 GB	Q8_0	Comfortable
1,210 tok/s 726–1,936 · low confidence	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	3.7 GB	Q8_0	Comfortable
966 tok/s 580–1,546 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	3.7 GB	Q8_0	Comfortable
966 tok/s 580–1,546 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	3.7 GB	Q8_0	Comfortable
773 tok/s 464–1,236 · low confidence	Radeon Instinct MI300 AMD	128 GB	6,550 GB/s	Jan 2023	3.7 GB	Q8_0	Comfortable
740 tok/s 444–1,183 · low confidence	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	3.7 GB	Q8_0	Comfortable
740 tok/s 444–1,183 · low confidence	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	3.7 GB	Q8_0	Comfortable
708 tok/s 425–1,133 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	3.7 GB	Q8_0	Comfortable
628 tok/s 377–1,005 · low confidence	Radeon Instinct MI300A AMD	128 GB	5,325 GB/s	Dec 2023	3.7 GB	Q8_0	Comfortable
628 tok/s 377–1,005 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	3.7 GB	Q8_0	Comfortable
628 tok/s 377–1,005 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	3.7 GB	Q8_0	Comfortable
596 tok/s 358–954 · low confidence	H100 NVL 94 GB NVIDIA	94 GB	3,940 GB/s	Mar 2023	3.7 GB	Q8_0	Comfortable
508 tok/s 305–813 · low confidence	H100 PCIe 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	3.7 GB	Q8_0	Comfortable
508 tok/s 305–813 · low confidence	H100 SXM5 80 GB NVIDIA	80 GB	3,360 GB/s	Oct 2022	3.7 GB	Q8_0	Comfortable
508 tok/s 305–813 · low confidence	H100 SXM5 94 GB NVIDIA	94 GB	3,360 GB/s	Mar 2023	3.7 GB	Q8_0	Comfortable
508 tok/s 305–813 · low confidence	H100 SXM5 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	3.7 GB	Q8_0	Comfortable
508 tok/s 305–813 · low confidence	H800 SXM5 NVIDIA	80 GB	3,360 GB/s	Mar 2023	3.7 GB	Q8_0	Comfortable
387 tok/s 232–619 · low confidence	Radeon Instinct MI250 AMD	128 GB	3,280 GB/s	Nov 2021	3.7 GB	Q8_0	Comfortable
387 tok/s 232–619 · low confidence	Radeon Instinct MI250X AMD	128 GB	3,280 GB/s	Nov 2021	3.7 GB	Q8_0	Comfortable
322 tok/s 193–516 · low confidence	Data Center GPU Max 1550 Intel	128 GB	3,280 GB/s	Jan 2023	3.7 GB	Q8_0	Comfortable
316 tok/s 189–505 · low confidence	Data Center GPU Max Subsystem Intel	128 GB	3,210 GB/s	Jan 2023	3.7 GB	Q8_0	Comfortable
309 tok/s 185–494 · low confidence	A100 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Nov 2020	3.7 GB	Q8_0	Comfortable
309 tok/s 185–494 · low confidence	A100X NVIDIA	80 GB	2,040 GB/s	Jun 2021	3.7 GB	Q8_0	Comfortable
309 tok/s 185–494 · low confidence	A800 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Aug 2022	3.7 GB	Q8_0	Comfortable
309 tok/s 185–494 · low confidence	H100 CNX NVIDIA	80 GB	2,040 GB/s	Mar 2023	3.7 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: Carnegie Mellon University (CMU),Princeton University
Organisation type: Academia,Academia
Country: United States of America
Published: 1 December 2023
Authors: Albert Gu, Tri Dao

What it does

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

Domain: Language
Task: Language generation, Question answering

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: 2.8B
Training data: 300,000,000,000 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: 5.4 × 10²¹ 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

How it is classified

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

Record confidence: Likely
Citations: 7,063

Sources

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

Reference: Mamba: Linear-Time Sequence Modeling with Selective State Spaces
Last updated: 25 May 2026

The extremes

The ten fastest GPUs that run Mamba-2.8B

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 Mamba-2.8B

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 C1080

Memory needed

3.0 GB

Fastest

1,210 tok/s

Mamba-2.8B is small enough at 2.8B parameters that hardware is rarely the obstacle — 818 of the cards we track can run it, including cards several years old.

At the low end, a Tesla C1080 handles it — 4 GB, at Q6_K, for about 19.1 tokens per second.

At the other end, a B200 generates roughly 1,210 tokens per second on it, on the strength of 8,000 GB/s of memory bandwidth.

What this model is

Mamba-2.8B was published by Carnegie Mellon University (CMU),Princeton University, in United States of America, in December 2023. academia,Academia is the category the publisher falls under.

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

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

What decides the speed

Across every card that can run it, the middle of the range is about 38.4 tokens per second, and 784 of them clear the ten tokens per second that roughly matches reading speed.

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

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

Training it took roughly 5.4 × 10²¹ FLOP of computation — a measure of what producing the model cost, not of how fast it answers.

Around 300,000,000,000 tokens went into training it.

Step by step

How to choose a GPU for Mamba-2.8B

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 Mamba-2.8B — around 3.0 GB at Q6_K. That figure, not the card's headline performance, is what decides whether it runs.
02

Set the context length you will work at

The conversation occupies memory too, and grows as it goes. Set the slider to the length you expect: at long context Mamba-2.8B can slip off a card that handles short questions easily.
03

Choose how far you will compress it

Each card runs the least-compressed copy it can hold — Q6_K on the smallest card that fits. Setting a floor drops the cards that only manage Mamba-2.8B by squeezing it further than you would want.
04

Sort by speed

The speed ordering for Mamba-2.8B is effectively an ordering by memory bandwidth, which is why the B200 tops it at 1,210 tok/s.
05

Look at the headroom, not just the fit

A tight fit runs Mamba-2.8B but leaves nothing spare for a longer conversation; comfortable has headroom. If you expect to grow the context, buy for comfortable.
06

See what else that card runs

Every card name links to its own page, which runs the same calculation across the whole model catalogue. Worth a look before buying for Mamba-2.8B alone — a card is usually bought for more than one model.

Answers

Mamba-2.8B — common questions

How many parameters does Mamba-2.8B have?

Mamba-2.8B has 2.8B parameters. 2.8B https://github.com/state-spaces/mamba. 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 Mamba-2.8B?

Mamba-2.8B was published by Carnegie Mellon University (CMU),Princeton University, based in United States of America, categorised as academia,Academia.

When was Mamba-2.8B released?

Mamba-2.8B was published in December 2023. 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 Mamba-2.8B used for?

Mamba-2.8B works in Language, and is recorded as handling language 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 Mamba-2.8B?

The weights for Mamba-2.8B are published, though we do not hold a repository link for it. This site calculates hardware requirements rather than hosting model files.

How much compute was used to train Mamba-2.8B?

Around 5.4 × 10²¹ 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 Mamba-2.8B if it does not fit in my GPU?

Partly. Layers that do not fit sit in system memory and run at a fraction of the speed, so a mostly-offloaded Mamba-2.8B is rarely worth using. Every figure here assumes the whole model is on the card.

Would two GPUs run Mamba-2.8B faster?

Capacity adds across cards; throughput does not. Since 818 of the cards we track already hold Mamba-2.8B on their own, a second card is rarely the answer here.

Why does the quantisation differ between cards for Mamba-2.8B?

Each card is shown running the least-compressed copy it can hold, and Mamba-2.8B appears at 2 different compression levels across the cards that fit it. Bigger cards get the more accurate version.

How accurate are these Mamba-2.8B speed estimates?

They are calculated from specifications rather than measured, and each carries a range — 726–1,936 tok/s on the B200, for instance. The same model and card vary by thirty to fifty per cent depending on the inference software and its version.

What GPU do I need to run Mamba-2.8B?

The smallest card in our catalogue that holds Mamba-2.8B is the Tesla C1080, with 4 GB of memory. It runs the model at Q6_K using about 3.0 GB, and produces roughly 19.1 tokens per second. 818 cards in total can run it.

How fast is Mamba-2.8B on a GPU?

It depends on the card. The quickest we calculate is a B200 at about 1,210 tokens per second; the slowest that still runs it manages considerably less. Reading speed is around ten tokens per second, and 784 of the cards that can run Mamba-2.8B clear that.

How much VRAM does Mamba-2.8B need?

About 3.0 GB at Q6_K 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 Mamba-2.8B on a 8 GB GPU?

Yes. A CMP 170HX 8 GB with 8 GB runs it at Q8_0, using about 3.7 GB and generating roughly 225 tokens per second — a comfortable fit.

Can I run Mamba-2.8B on a 12 GB GPU?

Yes. A GeForce RTX 3080 Ti with 12 GB runs it at Q8_0, using about 3.7 GB and generating roughly 138 tokens per second — a comfortable fit.

Can I run Mamba-2.8B on a 16 GB GPU?

Yes. A Tesla V100 SXM2 16 GB with 16 GB runs it at Q8_0, using about 3.7 GB and generating roughly 171 tokens per second — a comfortable fit.

Can I run Mamba-2.8B on a 24 GB GPU?

Yes. A GeForce RTX 5090 D V2 with 24 GB runs it at Q8_0, using about 3.7 GB and generating roughly 203 tokens per second — a comfortable fit.

Is Mamba-2.8B open source?

Its weights are published, so Mamba-2.8B 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 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