Llama-3.1-Minitron-4B TPS calculator

Open weights NVIDIA 4B 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 cards that can run it

818 cards we hold specifications for

Smallest card that fits

Tesla C1080

4 GB · Q3_K_M · 24.9 tok/s

Fastest card

B200

847 tok/s · 180 GB

Which GPUs can run Llama-3.1-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
847 tok/s 720–1,016	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	5.7 GB	Q8_0	Comfortable
847 tok/s 720–1,016	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	5.7 GB	Q8_0	Comfortable
676 tok/s 406–1,082 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	5.7 GB	Q8_0	Comfortable
676 tok/s 406–1,082 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	5.7 GB	Q8_0	Comfortable
541 tok/s 325–866 · low confidence	Radeon Instinct MI300 AMD	128 GB	6,550 GB/s	Jan 2023	5.7 GB	Q8_0	Comfortable
518 tok/s 440–621	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	5.7 GB	Q8_0	Comfortable
518 tok/s 440–621	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	5.7 GB	Q8_0	Comfortable
496 tok/s 297–793 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	5.7 GB	Q8_0	Comfortable
440 tok/s 264–704 · low confidence	Radeon Instinct MI300A AMD	128 GB	5,325 GB/s	Dec 2023	5.7 GB	Q8_0	Comfortable
440 tok/s 264–704 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	5.7 GB	Q8_0	Comfortable
440 tok/s 264–704 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	5.7 GB	Q8_0	Comfortable
417 tok/s 355–501	H100 NVL 94 GB NVIDIA	94 GB	3,940 GB/s	Mar 2023	5.7 GB	Q8_0	Comfortable
356 tok/s 302–427	H100 PCIe 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	5.7 GB	Q8_0	Comfortable
356 tok/s 302–427	H100 SXM5 80 GB NVIDIA	80 GB	3,360 GB/s	Oct 2022	5.7 GB	Q8_0	Comfortable
356 tok/s 302–427	H100 SXM5 94 GB NVIDIA	94 GB	3,360 GB/s	Mar 2023	5.7 GB	Q8_0	Comfortable
356 tok/s 302–427	H100 SXM5 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	5.7 GB	Q8_0	Comfortable
356 tok/s 302–427	H800 SXM5 NVIDIA	80 GB	3,360 GB/s	Mar 2023	5.7 GB	Q8_0	Comfortable
271 tok/s 163–433 · low confidence	Radeon Instinct MI250 AMD	128 GB	3,280 GB/s	Nov 2021	5.7 GB	Q8_0	Comfortable
271 tok/s 163–433 · low confidence	Radeon Instinct MI250X AMD	128 GB	3,280 GB/s	Nov 2021	5.7 GB	Q8_0	Comfortable
226 tok/s 135–361 · low confidence	Data Center GPU Max 1550 Intel	128 GB	3,280 GB/s	Jan 2023	5.7 GB	Q8_0	Comfortable
221 tok/s 133–353 · low confidence	Data Center GPU Max Subsystem Intel	128 GB	3,210 GB/s	Jan 2023	5.7 GB	Q8_0	Comfortable
216 tok/s 184–259	A100 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Nov 2020	5.7 GB	Q8_0	Comfortable
216 tok/s 184–259	A100X NVIDIA	80 GB	2,040 GB/s	Jun 2021	5.7 GB	Q8_0	Comfortable
216 tok/s 184–259	A800 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Aug 2022	5.7 GB	Q8_0	Comfortable
216 tok/s 184–259	H100 CNX NVIDIA	80 GB	2,040 GB/s	Mar 2023	5.7 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: 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: Llama 3.1-8B

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: 4B
Training data: tokens

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 (unrestricted)

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 that run Llama-3.1-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 Llama-3.1-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

3.4 GB

Fastest

847 tok/s

Llama-3.1-Minitron-4B is small enough at 4B 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, Q3_K_M compression, roughly 24.9 tokens per second.

A B200 is the fastest we calculate for it: about 847 tokens per second, from 8,000 GB/s of memory bandwidth.

Where it came from

Llama-3.1-Minitron-4B was published by NVIDIA, in United States of America, in November 2024. industry is the category the publisher falls under.

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

It builds on Llama 3.1-8B, which is why it shares that model's general shape and size.

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

Understanding the speeds

Half the cards that hold it manage more than 35.2 tokens per second, and 781 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.

Because the architecture is recorded, the memory column is derived rather than estimated.

Step by step

How to choose a GPU for Llama-3.1-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

Start from the memory column

The table lists every card that can hold Llama-3.1-Minitron-4B — around 3.4 GB at Q3_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 Llama-3.1-Minitron-4B stops fitting a card that seemed fine.
03

Choose how far you will compress it

Each card runs the least-compressed copy it can hold — Q3_K_M on the smallest card that fits. Setting a floor drops the cards that only manage Llama-3.1-Minitron-4B by squeezing it further than you would want.
04

Sort by speed

Sort by speed to see how cards rank for Llama-3.1-Minitron-4B. It will not match a gaming ordering — generation is bound by memory bandwidth, which is why the B200 tops it at 847 tok/s.
05

Check the fit verdict before buying

A tight fit runs Llama-3.1-Minitron-4B but leaves nothing spare for a longer conversation; comfortable has headroom. If you expect to grow the context, buy for comfortable.
06

Check the card from the other side

Every card name links to its own page, which runs the same calculation across the whole model catalogue. Worth a look before buying for Llama-3.1-Minitron-4B alone — a card is usually bought for more than one model.

Answers

Llama-3.1-Minitron-4B — common questions

Can I run Llama-3.1-Minitron-4B on a 8 GB GPU?

Yes. A CMP 170HX 8 GB with 8 GB runs it at Q8_0, using about 5.7 GB and generating roughly 158 tokens per second — a comfortable fit.

Can I run Llama-3.1-Minitron-4B on a 12 GB GPU?

Yes. A GeForce RTX 3080 Ti with 12 GB runs it at Q8_0, using about 5.7 GB and generating roughly 96.6 tokens per second — a comfortable fit.

Can I run Llama-3.1-Minitron-4B on a 16 GB GPU?

Yes. A Tesla V100 SXM2 16 GB with 16 GB runs it at Q8_0, using about 5.7 GB and generating roughly 120 tokens per second — a comfortable fit.

Can I run Llama-3.1-Minitron-4B on a 24 GB GPU?

Yes. A GeForce RTX 5090 D V2 with 24 GB runs it at Q8_0, using about 5.7 GB and generating roughly 142 tokens per second — a comfortable fit.

Is Llama-3.1-Minitron-4B open source?

Its weights are published, so Llama-3.1-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.

How many parameters does Llama-3.1-Minitron-4B have?

Llama-3.1-Minitron-4B has 4B parameters. 4b Llama-3.1-Minitron-4B-Width-Base uses a model embedding size of 3072, 32 attention heads, MLP intermediate dimension of 9216, with 32 layers in total. Additionally, it uses Grouped-Query Attention (GQA) and Rotary Position Embeddings (RoPE). Architecture Type: Transformer Decoder (Auto-Regressive Language Model) Network Architecture: Llama-3.1. 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 Llama-3.1-Minitron-4B?

Llama-3.1-Minitron-4B was published by NVIDIA, based in United States of America, categorised as industry.

When was Llama-3.1-Minitron-4B released?

Llama-3.1-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 Llama-3.1-Minitron-4B used for?

Llama-3.1-Minitron-4B works in Language, and is recorded as handling language modeling/generation, Chat, Question answering. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.

Where can I download Llama-3.1-Minitron-4B?

The weights for Llama-3.1-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 Llama-3.1-Minitron-4B if it does not fit in my GPU?

It can be split between the card and system memory, but Llama-3.1-Minitron-4B generates painfully slowly that way. Nothing on this page assumes offloading.

Would two GPUs run Llama-3.1-Minitron-4B faster?

Capacity adds across cards; throughput does not. Since 818 of the cards we track already hold Llama-3.1-Minitron-4B on their own, a second card is rarely the answer here.

Why does the quantisation differ between cards for Llama-3.1-Minitron-4B?

Because capacity varies, so does how hard Llama-3.1-Minitron-4B has to be squeezed — 4 distinct levels appear in the table above. Set a minimum quality to compare at one.

How accurate are these Llama-3.1-Minitron-4B 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 720–1,016 tok/s on the B200 rather than a single number.

What GPU do I need to run Llama-3.1-Minitron-4B?

The smallest card in our catalogue that holds Llama-3.1-Minitron-4B is the Tesla C1080, with 4 GB of memory. It runs the model at Q3_K_M using about 3.4 GB, and produces roughly 24.9 tokens per second. 818 cards in total can run it.

How fast is Llama-3.1-Minitron-4B on a GPU?

It depends on the card. The quickest we calculate is a B200 at about 847 tokens per second; the slowest that still runs it manages considerably less. Reading speed is around ten tokens per second, and 781 of the cards that can run Llama-3.1-Minitron-4B clear that.

How much VRAM does Llama-3.1-Minitron-4B need?

About 3.4 GB at Q3_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.

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