Minitron 4B TPS calculator

Open weights NVIDIA 4.2B parameters November 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

818 of 818 cards that can run it

Smallest card that fits

Tesla C1080

4 GB · Q4_K_M · 20.3 tok/s

Fastest card

B200

807 tok/s · 180 GB

Which GPUs can run Minitron 4B?

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
807 tok/s 484–1,291 · low confidence	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	5.2 GB	Q8_0	Comfortable
807 tok/s 484–1,291 · low confidence	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	5.2 GB	Q8_0	Comfortable
644 tok/s 387–1,031 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	5.2 GB	Q8_0	Comfortable
644 tok/s 387–1,031 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	5.2 GB	Q8_0	Comfortable
515 tok/s 309–824 · low confidence	Radeon Instinct MI300 AMD	128 GB	6,550 GB/s	Jan 2023	5.2 GB	Q8_0	Comfortable
493 tok/s 296–789 · low confidence	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	5.2 GB	Q8_0	Comfortable
493 tok/s 296–789 · low confidence	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	5.2 GB	Q8_0	Comfortable
472 tok/s 283–755 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	5.2 GB	Q8_0	Comfortable
419 tok/s 251–670 · low confidence	Radeon Instinct MI300A AMD	128 GB	5,325 GB/s	Dec 2023	5.2 GB	Q8_0	Comfortable
419 tok/s 251–670 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	5.2 GB	Q8_0	Comfortable
419 tok/s 251–670 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	5.2 GB	Q8_0	Comfortable
397 tok/s 238–636 · low confidence	H100 NVL 94 GB NVIDIA	94 GB	3,940 GB/s	Mar 2023	5.2 GB	Q8_0	Comfortable
339 tok/s 203–542 · low confidence	H100 PCIe 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	5.2 GB	Q8_0	Comfortable
339 tok/s 203–542 · low confidence	H100 SXM5 80 GB NVIDIA	80 GB	3,360 GB/s	Oct 2022	5.2 GB	Q8_0	Comfortable
339 tok/s 203–542 · low confidence	H100 SXM5 94 GB NVIDIA	94 GB	3,360 GB/s	Mar 2023	5.2 GB	Q8_0	Comfortable
339 tok/s 203–542 · low confidence	H100 SXM5 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	5.2 GB	Q8_0	Comfortable
339 tok/s 203–542 · low confidence	H800 SXM5 NVIDIA	80 GB	3,360 GB/s	Mar 2023	5.2 GB	Q8_0	Comfortable
258 tok/s 155–413 · low confidence	Radeon Instinct MI250 AMD	128 GB	3,280 GB/s	Nov 2021	5.2 GB	Q8_0	Comfortable
258 tok/s 155–413 · low confidence	Radeon Instinct MI250X AMD	128 GB	3,280 GB/s	Nov 2021	5.2 GB	Q8_0	Comfortable
215 tok/s 129–344 · low confidence	Data Center GPU Max 1550 Intel	128 GB	3,280 GB/s	Jan 2023	5.2 GB	Q8_0	Comfortable
210 tok/s 126–337 · low confidence	Data Center GPU Max Subsystem Intel	128 GB	3,210 GB/s	Jan 2023	5.2 GB	Q8_0	Comfortable
206 tok/s 123–329 · low confidence	A100 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Nov 2020	5.2 GB	Q8_0	Comfortable
206 tok/s 123–329 · low confidence	A100X NVIDIA	80 GB	2,040 GB/s	Jun 2021	5.2 GB	Q8_0	Comfortable
206 tok/s 123–329 · low confidence	A800 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Aug 2022	5.2 GB	Q8_0	Comfortable
206 tok/s 123–329 · low confidence	H100 CNX NVIDIA	80 GB	2,040 GB/s	Mar 2023	5.2 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: NVIDIA
Organisation type: Industry
Country: United States of America
Published: 4 November 2024
Authors: Saurav Muralidharan, Sharath Turuvekere Sreenivas, Raviraj Joshi, Marcin Chochowski, Mostofa Patwary, Mohammad Shoeybi, Bryan Catanzaro, Jan Kautz, Pavlo Molchanov

What it does

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

Domain: Language
Task: Language modeling/generation, Chat, Question answering
Base model: Nemotron-4 15B

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: 4.2B
Training data: 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.

How it was established: Operation counting
Fine-tuning compute: 2.4 × 10²¹ FLOP

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 A100 SXM4 80 GB
Chips used: 8
Power draw: 6.3 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 (non-commercial)

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: Compact Language Models via Pruning and Knowledge Distillation
Last updated: 28 November 2025

The extremes

The ten fastest GPUs for Minitron 4B

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 Minitron 4B

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

Hardware requirements in practice

Minimum card

Tesla C1080

Memory needed

3.2 GB

Fastest

807 tok/s

Minitron 4B is small enough at 4.2B parameters that hardware is rarely the obstacle — 818 of the cards we track can run it, including cards several years old.

The entry point is the Tesla C1080: 4 GB of memory, Q4_K_M compression, roughly 20.3 tokens per second.

The quickest result comes from a B200 at around 807 tokens per second — its 8,000 GB/s of bandwidth is what buys that.

About this model

Minitron 4B was published by NVIDIA, in United States of America, in November 2024. It comes out of industry.

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

Its starting point was Nemotron-4 15B — most models at this scale are adapted from an existing base rather than built from nothing.

Because its weights were released, nothing about running it depends on a provider staying available — it is yours once downloaded.

How fast it runs, and why

Half the cards that hold it manage more than 29.8 tokens per second, and 778 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.

Its internal architecture is not on file, so memory is approximated from the parameter count and marked accordingly. Expect the real figure to differ, more so at long context.

Step by step

How to choose a GPU for Minitron 4B

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

The table lists every card that can hold Minitron 4B — around 3.2 GB at Q4_K_M. That figure, not the card's headline performance, is what decides whether it runs.
02

Match the context to your actual use

Set the context to what you will actually use. The cache grows with the conversation, and it is the usual reason Minitron 4B stops fitting a card that seemed fine.
03

Decide how much compression you will accept

Compression is what makes Minitron 4B fit smaller cards, at some cost in accuracy — Q4_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 Minitron 4B is effectively an ordering by memory bandwidth, which is why the B200 tops it at 807 tok/s.
05

Look at the headroom, not just the fit

A tight fit runs Minitron 4B 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

Each card page repeats this sweep for every model we hold. It answers what else the hardware is good for, beyond Minitron 4B.

Answers

Minitron 4B — common questions

How many parameters does Minitron 4B have?

Minitron 4B has 4.2B parameters. 4.2B (table 4) including 2.6B non-embedding parameters "Minitron-4B-Base uses a model embedding size of 3072, 32 attention heads, and an MLP intermediate dimension of 9216. It also uses Grouped-Query Attention (GQA) and Rotary Position Embeddings (RoPE).". 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 Minitron 4B?

Minitron 4B was published by NVIDIA, based in United States of America, categorised as industry.

When was Minitron 4B released?

Minitron 4B was published in November 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 Minitron 4B used for?

Minitron 4B works in Language, and is recorded as handling language modeling/generation, Chat, Question answering. These are the areas it was designed around; they describe intent rather than a hard boundary.

Where can I download Minitron 4B?

The weights for Minitron 4B are published, though we do not hold a repository link for it. This site calculates hardware requirements rather than hosting model files.

Can I run Minitron 4B 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. Our figures for Minitron 4B assume it is fully resident.

Would two GPUs run Minitron 4B faster?

A second card roughly doubles the memory available but not the generation rate. With 818 cards already able to run Minitron 4B alone, the case for pairing is weak.

Why does the quantisation differ between cards for Minitron 4B?

A larger card holds a more accurate copy. Across the cards that run Minitron 4B, 3 compression levels are used; the floor control above pins it to one.

How accurate are these Minitron 4B speed estimates?

These are estimates with real error bars. The fastest result here, 484–1,291 tok/s on the B200, could reasonably land anywhere in its published range depending on which runtime you use.

What GPU do I need to run Minitron 4B?

The smallest card in our catalogue that holds Minitron 4B is the Tesla C1080, with 4 GB of memory. It runs the model at Q4_K_M using about 3.2 GB, and produces roughly 20.3 tokens per second. 818 cards in total can run it.

How fast is Minitron 4B on a GPU?

It depends on the card. The quickest we calculate is a B200 at about 807 tokens per second; the slowest that still runs it manages considerably less. Reading speed is around ten tokens per second, and 778 of the cards that can run Minitron 4B clear that.

How much VRAM does Minitron 4B need?

About 3.2 GB at Q4_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 Minitron 4B on a 8 GB GPU?

Yes. A CMP 170HX 8 GB with 8 GB runs it at Q8_0, using about 5.2 GB and generating roughly 150 tokens per second — a comfortable fit.

Can I run Minitron 4B on a 12 GB GPU?

Yes. A GeForce RTX 3080 Ti with 12 GB runs it at Q8_0, using about 5.2 GB and generating roughly 92.0 tokens per second — a comfortable fit.

Can I run Minitron 4B on a 16 GB GPU?

Yes. A Tesla V100 SXM2 16 GB with 16 GB runs it at Q8_0, using about 5.2 GB and generating roughly 114 tokens per second — a comfortable fit.

Can I run Minitron 4B on a 24 GB GPU?

Yes. A GeForce RTX 5090 D V2 with 24 GB runs it at Q8_0, using about 5.2 GB and generating roughly 135 tokens per second — a comfortable fit.

Is Minitron 4B open source?

Its weights are published, so Minitron 4B 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