MPT-30B TPS calculator

Open weights MosaicML 30B parameters June 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

132 cards that can run it

818 cards we hold specifications for

Smallest card that fits

RTX A4500

20 GB · IQ4_XS · 22.2 tok/s

Fastest card

B200

113 tok/s · 180 GB

Which GPUs can run MPT-30B?

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

132 cards match

Calculating

					Needs	Quantisation	Fit
113 tok/s 68–181 · low confidence	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	32.8 GB	Q8_0	Comfortable
113 tok/s 68–181 · low confidence	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	32.8 GB	Q8_0	Comfortable
90.2 tok/s 54–144 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	32.8 GB	Q8_0	Comfortable
90.2 tok/s 54–144 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	32.8 GB	Q8_0	Comfortable
72.1 tok/s 43–115 · low confidence	Radeon Instinct MI300 AMD	128 GB	6,550 GB/s	Jan 2023	32.8 GB	Q8_0	Comfortable
69.0 tok/s 41–110 · low confidence	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	32.8 GB	Q8_0	Comfortable
69.0 tok/s 41–110 · low confidence	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	32.8 GB	Q8_0	Comfortable
66.1 tok/s 40–106 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	32.8 GB	Q8_0	Comfortable
58.6 tok/s 35–94 · low confidence	Radeon Instinct MI300A AMD	128 GB	5,325 GB/s	Dec 2023	32.8 GB	Q8_0	Comfortable
58.6 tok/s 35–94 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	32.8 GB	Q8_0	Comfortable
58.6 tok/s 35–94 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	32.8 GB	Q8_0	Comfortable
55.6 tok/s 33–89 · low confidence	H100 NVL 94 GB NVIDIA	94 GB	3,940 GB/s	Mar 2023	32.8 GB	Q8_0	Comfortable
47.4 tok/s 28–76 · low confidence	H100 PCIe 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	32.8 GB	Q8_0	Comfortable
47.4 tok/s 28–76 · low confidence	H100 SXM5 80 GB NVIDIA	80 GB	3,360 GB/s	Oct 2022	32.8 GB	Q8_0	Comfortable
47.4 tok/s 28–76 · low confidence	H100 SXM5 94 GB NVIDIA	94 GB	3,360 GB/s	Mar 2023	32.8 GB	Q8_0	Comfortable
47.4 tok/s 28–76 · low confidence	H100 SXM5 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	32.8 GB	Q8_0	Comfortable
47.4 tok/s 28–76 · low confidence	H800 SXM5 NVIDIA	80 GB	3,360 GB/s	Mar 2023	32.8 GB	Q8_0	Comfortable
43.7 tok/s 26–70 · low confidence	GeForce RTX 5090 D V2 NVIDIA	24 GB	1,340 GB/s	Aug 2025	18.8 GB	Q4_K_M	Tight
39.8 tok/s 24–64 · low confidence	A30X NVIDIA	24 GB	1,220 GB/s	Apr 2021	18.8 GB	Q4_K_M	Tight
38.4 tok/s 23–61 · low confidence	DRIVE A100 PROD NVIDIA	32 GB	1,870 GB/s	May 2020	25.8 GB	Q6_K	Tight
38.4 tok/s 23–61 · low confidence	GRID A100A NVIDIA	32 GB	1,870 GB/s	May 2020	25.8 GB	Q6_K	Tight
36.7 tok/s 22–59 · low confidence	GeForce RTX 5090 NVIDIA	32 GB	1,790 GB/s	Jan 2025	25.8 GB	Q6_K	Tight
36.7 tok/s 22–59 · low confidence	GeForce RTX 5090 D NVIDIA	32 GB	1,790 GB/s	Jan 2025	25.8 GB	Q6_K	Tight
36.1 tok/s 22–58 · low confidence	Radeon Instinct MI250 AMD	128 GB	3,280 GB/s	Nov 2021	32.8 GB	Q8_0	Comfortable
36.1 tok/s 22–58 · low confidence	Radeon Instinct MI250X AMD	128 GB	3,280 GB/s	Nov 2021	32.8 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: MosaicML
Organisation type: Industry
Country: United States of America
Published: 22 June 2023

What it does

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

Domain: Language
Task: Language generation, 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: 30B
Training data: 1,050,000,000,000 tokens
Epochs: 1
Batch size: 4,096,000

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 H100 SXM5 80GB
Chips used: 512
Chip-hours: 142,541
Wall-clock time: 278 hours (11.6 days)
Power draw: 713.2 kW
Cloud vendor: Databricks

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: mosaicml

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.

Last updated: 28 November 2025

The extremes

The ten fastest GPUs that run MPT-30B

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 MPT-30B

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 you need to run it

Minimum card

RTX A4500

Memory needed

17.1 GB

Fastest

113 tok/s

With 30B parameters, MPT-30B lands in the range a serious desktop card can handle once the weights are compressed. 132 of the cards we track can run it.

The least hardware that works is a RTX A4500. Its 20 GB is enough at IQ4_XS compression, giving roughly 22.2 tokens per second.

Top of the range is the B200, at roughly 113 tokens per second thanks to 8,000 GB/s of bandwidth.

What this model is

MPT-30B was published by MosaicML, in United States of America, in June 2023. It comes out of industry.

It works in Language, and is recorded as doing language generation, 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 mosaicml organisation on Hugging Face.

What decides the speed

Across every card that can run it, the middle of the range is about 22.0 tokens per second, and 104 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.

Without the attention layout on record, the memory column is an approximation. It is close enough to choose hardware by, and least reliable at long context.

Training and provenance

The training run consumed about 1.9 × 10²³ FLOP, on NVIDIA H100 SXM5 80GB. That figure describes the cost of creating it and has no bearing on how quickly it generates text.

It was trained on about 1,050,000,000,000 tokens of text.

Step by step

How to choose a GPU for MPT-30B

The table above has already assessed every card we hold specifications for against this model. Getting to your answer takes six steps.

01

Check what it needs before anything else

Look at what MPT-30B actually needs — around 17.1 GB at IQ4_XS. No amount of processing power compensates for a card that cannot hold it.
02

Set the context length you will work at

Longer conversations cost memory on top of what the weights need. Move the slider to your real working length before trusting any row for MPT-30B.
03

Decide how much compression you will accept

The quantisation column varies by card, because a bigger card holds a more accurate copy of MPT-30B — 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 MPT-30B. It will not match a gaming ordering — generation is bound by memory bandwidth, which is why the B200 tops it at 113 tok/s.
05

Read the fit column last

A tight fit runs MPT-30B 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

Following a card through to its own page shows every other model it can hold, which is the question that follows once MPT-30B is settled.

Answers

MPT-30B — common questions

How accurate are these MPT-30B speed estimates?

They are calculated from specifications rather than measured, and each carries a range — 68–181 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 MPT-30B?

The smallest card in our catalogue that holds MPT-30B is the RTX A4500, with 20 GB of memory. It runs the model at IQ4_XS using about 17.1 GB, and produces roughly 22.2 tokens per second. 132 cards in total can run it.

How fast is MPT-30B on a GPU?

It depends on the card. The quickest we calculate is a B200 at about 113 tokens per second; the slowest that still runs it manages considerably less. Reading speed is around ten tokens per second, and 104 of the cards that can run MPT-30B clear that.

How much VRAM does MPT-30B need?

About 17.1 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.

Can I run MPT-30B on a 24 GB GPU?

Yes. A GeForce RTX 5090 D V2 with 24 GB runs it at Q4_K_M, using about 18.8 GB and generating roughly 43.7 tokens per second — a tight fit.

Is MPT-30B open source?

Its weights are published, so MPT-30B 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 MPT-30B have?

MPT-30B has 30B parameters. 30B. 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 MPT-30B?

MPT-30B was published by MosaicML, based in United States of America, categorised as industry.

When was MPT-30B released?

MPT-30B was published in June 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 MPT-30B used for?

MPT-30B works in Language, and is recorded as handling language generation, Code generation. These are the areas it was designed around; they describe intent rather than a hard boundary.

Where can I download MPT-30B?

Its weights are published under the mosaicml 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 MPT-30B?

Around 1.9 × 10²³ FLOP, on NVIDIA H100 SXM5 80GB. 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 MPT-30B 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 MPT-30B is rarely worth using — the nearest miss we calculate is short by 4.4 GB. Every figure here assumes the whole model is on the card.

Would two GPUs run MPT-30B faster?

Capacity adds across cards; throughput does not. Since 132 of the cards we track already hold MPT-30B on their own, a second card is rarely the answer here.

Why does the quantisation differ between cards for MPT-30B?

Because capacity varies, so does how hard MPT-30B has to be squeezed — 5 distinct levels appear in the table above. Set a minimum quality to compare at one.

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