VILA1.5-40B TPS calculator

Open weights NVIDIA,Massachusetts Institute of Technology (MIT) 40B parameters May 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

126 of 818 cards that can run it

Smallest card that fits

Tesla M40 24 GB

24 GB · Q3_K_M · 7.0 tok/s

Fastest card

B200

84.7 tok/s · 180 GB

Which GPUs can run VILA1.5-40B?

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

126 cards match

Calculating

					Needs	Quantisation	Fit
84.7 tok/s 51–136 · low confidence	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	43.5 GB	Q8_0	Comfortable
84.7 tok/s 51–136 · low confidence	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	43.5 GB	Q8_0	Comfortable
67.6 tok/s 41–108 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	43.5 GB	Q8_0	Comfortable
67.6 tok/s 41–108 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	43.5 GB	Q8_0	Comfortable
54.1 tok/s 32–87 · low confidence	Radeon Instinct MI300 AMD	128 GB	6,550 GB/s	Jan 2023	43.5 GB	Q8_0	Comfortable
51.8 tok/s 31–83 · low confidence	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	43.5 GB	Q8_0	Comfortable
51.8 tok/s 31–83 · low confidence	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	43.5 GB	Q8_0	Comfortable
49.6 tok/s 30–79 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	43.5 GB	Q8_0	Comfortable
45.7 tok/s 27–73 · low confidence	DRIVE A100 PROD NVIDIA	32 GB	1,870 GB/s	May 2020	24.9 GB	Q4_K_M	Tight
45.7 tok/s 27–73 · low confidence	GRID A100A NVIDIA	32 GB	1,870 GB/s	May 2020	24.9 GB	Q4_K_M	Tight
44.0 tok/s 26–70 · low confidence	Radeon Instinct MI300A AMD	128 GB	5,325 GB/s	Dec 2023	43.5 GB	Q8_0	Comfortable
44.0 tok/s 26–70 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	43.5 GB	Q8_0	Comfortable
44.0 tok/s 26–70 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	43.5 GB	Q8_0	Comfortable
43.8 tok/s 26–70 · low confidence	GeForce RTX 5090 NVIDIA	32 GB	1,790 GB/s	Jan 2025	24.9 GB	Q4_K_M	Tight
43.8 tok/s 26–70 · low confidence	GeForce RTX 5090 D NVIDIA	32 GB	1,790 GB/s	Jan 2025	24.9 GB	Q4_K_M	Tight
41.7 tok/s 25–67 · low confidence	H100 NVL 94 GB NVIDIA	94 GB	3,940 GB/s	Mar 2023	43.5 GB	Q8_0	Comfortable
38.3 tok/s 23–61 · low confidence	GeForce RTX 5090 D V2 NVIDIA	24 GB	1,340 GB/s	Aug 2025	20.2 GB	Q3_K_M	Tight
35.6 tok/s 21–57 · low confidence	H100 PCIe 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	43.5 GB	Q8_0	Comfortable
35.6 tok/s 21–57 · low confidence	H100 SXM5 80 GB NVIDIA	80 GB	3,360 GB/s	Oct 2022	43.5 GB	Q8_0	Comfortable
35.6 tok/s 21–57 · low confidence	H100 SXM5 94 GB NVIDIA	94 GB	3,360 GB/s	Mar 2023	43.5 GB	Q8_0	Comfortable
35.6 tok/s 21–57 · low confidence	H100 SXM5 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	43.5 GB	Q8_0	Comfortable
35.6 tok/s 21–57 · low confidence	H800 SXM5 NVIDIA	80 GB	3,360 GB/s	Mar 2023	43.5 GB	Q8_0	Comfortable
34.9 tok/s 21–56 · low confidence	A30X NVIDIA	24 GB	1,220 GB/s	Apr 2021	20.2 GB	Q3_K_M	Tight
28.9 tok/s 17–46 · low confidence	GeForce RTX 3090 Ti NVIDIA	24 GB	1,010 GB/s	Jan 2022	20.2 GB	Q3_K_M	Tight
28.9 tok/s 17–46 · low confidence	GeForce RTX 4090 NVIDIA	24 GB	1,010 GB/s	Sep 2022	20.2 GB	Q3_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: NVIDIA,Massachusetts Institute of Technology (MIT)
Organisation type: Industry,Academia
Country: United States of America
Published: 15 May 2024

What it does

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

Domain: Multimodal, Language, Vision, Video
Task: Chat, Visual question answering, Image captioning, Language modeling/generation, Question answering, Video description

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: 40B
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 (non-commercial)
Training code: Open source
Hugging Face: Efficient-Large-Model

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: Efficient-Large-Model/VILA1.5-40b
Last updated: 28 November 2025

The extremes

The ten fastest GPUs for VILA1.5-40B

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 VILA1.5-40B

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 M40 24 GB

Memory needed

20.2 GB

Fastest

84.7 tok/s

With 40B parameters, VILA1.5-40B lands in the range a serious desktop card can handle once the weights are compressed. 126 of the cards we track can run it.

At the low end, a Tesla M40 24 GB handles it — 24 GB, at Q3_K_M, for about 7.0 tokens per second.

The quickest result comes from a B200 at around 84.7 tokens per second — its 8,000 GB/s of bandwidth is what buys that.

Where it came from

VILA1.5-40B was published by NVIDIA,Massachusetts Institute of Technology (MIT), in United States of America, in May 2024. industry,Academia is the category the publisher falls under.

It works in Multimodal, Language, Vision, Video, and is recorded as doing chat, Visual question answering, Image captioning, Language modeling/generation, Question answering, Video description.

The weights being open is what puts this page in the calculator rather than only in the catalogue: it is a model you can actually hold. It is published under the Efficient-Large-Model organisation on Hugging Face.

Understanding the speeds

Across every card that can run it, the middle of the range is about 21.2 tokens per second, and 106 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.

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 VILA1.5-40B

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

Every card here has been checked against VILA1.5-40B — around 20.2 GB at Q3_K_M. Capacity is the gate — a card either holds it or it does not.
02

Match the context to your actual use

The conversation occupies memory too, and grows as it goes. Set the slider to the length you expect: at long context VILA1.5-40B can slip off a card that handles short questions easily.
03

Set a quality floor

Compression is what makes VILA1.5-40B fit smaller cards, at some cost in accuracy — Q3_K_M on the smallest card that fits. A minimum quality removes the ones that go too far.
04

Sort by speed

Sort by speed to see how cards rank for VILA1.5-40B. It will not match a gaming ordering — generation is bound by memory bandwidth, which is why the B200 tops it at 84.7 tok/s.
05

Read the fit column last

The fit column separates cards that just manage VILA1.5-40B from those with room to spare. Buy for the second if the context might grow.
06

Check the card from the other side

Each card page repeats this sweep for every model we hold. It answers what else the hardware is good for, beyond VILA1.5-40B.

Answers

VILA1.5-40B — common questions

Who created VILA1.5-40B?

VILA1.5-40B was published by NVIDIA,Massachusetts Institute of Technology (MIT), based in United States of America, categorised as industry,Academia.

When was VILA1.5-40B released?

VILA1.5-40B was published in May 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 VILA1.5-40B used for?

VILA1.5-40B works in Multimodal, Language, Vision, Video, and is recorded as handling chat, Visual question answering, Image captioning, Language modeling/generation, Question answering, Video description. 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 VILA1.5-40B?

Its weights are published under the Efficient-Large-Model organisation on Hugging Face. We do not host model files — this site calculates what hardware is needed to run them.

Can I run VILA1.5-40B 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 VILA1.5-40B is rarely worth using — the nearest miss we calculate is short by 6.9 GB. Every figure here assumes the whole model is on the card.

Would two GPUs run VILA1.5-40B faster?

Two cards buy memory rather than speed. That matters for VILA1.5-40B only if one card cannot hold it — 126 can, so a second adds little.

Why does the quantisation differ between cards for VILA1.5-40B?

Each card is shown running the least-compressed copy it can hold, and VILA1.5-40B appears at 4 different compression levels across the cards that fit it. Bigger cards get the more accurate version.

How accurate are these VILA1.5-40B speed estimates?

These are estimates with real error bars. The fastest result here, 51–136 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 VILA1.5-40B?

The smallest card in our catalogue that holds VILA1.5-40B is the Tesla M40 24 GB, with 24 GB of memory. It runs the model at Q3_K_M using about 20.2 GB, and produces roughly 7.0 tokens per second. 126 cards in total can run it.

How fast is VILA1.5-40B on a GPU?

It depends on the card. The quickest we calculate is a B200 at about 84.7 tokens per second; the slowest that still runs it manages considerably less. Reading speed is around ten tokens per second, and 106 of the cards that can run VILA1.5-40B clear that.

How much VRAM does VILA1.5-40B need?

About 20.2 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.

Can I run VILA1.5-40B on a 24 GB GPU?

Yes. A GeForce RTX 5090 D V2 with 24 GB runs it at Q3_K_M, using about 20.2 GB and generating roughly 38.3 tokens per second — a tight fit.

Is VILA1.5-40B open source?

Its weights are published, so VILA1.5-40B 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 VILA1.5-40B have?

VILA1.5-40B has 40B parameters. 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.

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