Granite Vision 3.2 2B TPS calculator

Open weights IBM 3B parameters February 2025

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 · 18.0 tok/s

Fastest card

B200

1,137 tok/s · 180 GB

Which GPUs can run Granite Vision 3.2 2B?

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
1,137 tok/s 682–1,819 · low confidence	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	3.9 GB	Q8_0	Comfortable
1,137 tok/s 682–1,819 · low confidence	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	3.9 GB	Q8_0	Comfortable
908 tok/s 545–1,453 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	3.9 GB	Q8_0	Comfortable
908 tok/s 545–1,453 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	3.9 GB	Q8_0	Comfortable
726 tok/s 436–1,162 · low confidence	Radeon Instinct MI300 AMD	128 GB	6,550 GB/s	Jan 2023	3.9 GB	Q8_0	Comfortable
695 tok/s 417–1,112 · low confidence	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	3.9 GB	Q8_0	Comfortable
695 tok/s 417–1,112 · low confidence	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	3.9 GB	Q8_0	Comfortable
665 tok/s 399–1,064 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	3.9 GB	Q8_0	Comfortable
590 tok/s 354–945 · low confidence	Radeon Instinct MI300A AMD	128 GB	5,325 GB/s	Dec 2023	3.9 GB	Q8_0	Comfortable
590 tok/s 354–945 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	3.9 GB	Q8_0	Comfortable
590 tok/s 354–945 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	3.9 GB	Q8_0	Comfortable
560 tok/s 336–896 · low confidence	H100 NVL 94 GB NVIDIA	94 GB	3,940 GB/s	Mar 2023	3.9 GB	Q8_0	Comfortable
478 tok/s 287–764 · low confidence	H100 PCIe 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	3.9 GB	Q8_0	Comfortable
478 tok/s 287–764 · low confidence	H100 SXM5 80 GB NVIDIA	80 GB	3,360 GB/s	Oct 2022	3.9 GB	Q8_0	Comfortable
478 tok/s 287–764 · low confidence	H100 SXM5 94 GB NVIDIA	94 GB	3,360 GB/s	Mar 2023	3.9 GB	Q8_0	Comfortable
478 tok/s 287–764 · low confidence	H100 SXM5 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	3.9 GB	Q8_0	Comfortable
478 tok/s 287–764 · low confidence	H800 SXM5 NVIDIA	80 GB	3,360 GB/s	Mar 2023	3.9 GB	Q8_0	Comfortable
364 tok/s 218–582 · low confidence	Radeon Instinct MI250 AMD	128 GB	3,280 GB/s	Nov 2021	3.9 GB	Q8_0	Comfortable
364 tok/s 218–582 · low confidence	Radeon Instinct MI250X AMD	128 GB	3,280 GB/s	Nov 2021	3.9 GB	Q8_0	Comfortable
303 tok/s 182–485 · low confidence	Data Center GPU Max 1550 Intel	128 GB	3,280 GB/s	Jan 2023	3.9 GB	Q8_0	Comfortable
297 tok/s 178–474 · low confidence	Data Center GPU Max Subsystem Intel	128 GB	3,210 GB/s	Jan 2023	3.9 GB	Q8_0	Comfortable
290 tok/s 174–464 · low confidence	A100 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Nov 2020	3.9 GB	Q8_0	Comfortable
290 tok/s 174–464 · low confidence	A100X NVIDIA	80 GB	2,040 GB/s	Jun 2021	3.9 GB	Q8_0	Comfortable
290 tok/s 174–464 · low confidence	A800 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Aug 2022	3.9 GB	Q8_0	Comfortable
290 tok/s 174–464 · low confidence	H100 CNX NVIDIA	80 GB	2,040 GB/s	Mar 2023	3.9 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: IBM
Organisation type: Industry
Country: United States of America
Published: 14 February 2025
Authors: Granite Vision Team: Leonid Karlinsky, Assaf Arbelle, Abraham Daniels, Ahmed Nassar, Amit Alfassi, Bo Wu, Eli Schwartz, Dhiraj Joshi, Jovana Kondic, Nimrod Shabtay, Pengyuan Li, Roei Herzig, Shafiq Abedin, Shaked Perek, Sivan Harary, Udi Barzelay, Adi Raz Goldfarb, Aude Oliva, Ben Wieles, Bishwaranjan Bhattacharjee, Brandon Huang, Christoph Auer, Dan Gutfreund, David Beymer, David Wood, Hilde Kueh…

What it does

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

Domain: Language, Multimodal, Vision
Task: Mathematical reasoning, Quantitative reasoning, Language modeling/generation, Question answering, Visual question answering
Base model: Granite 3.1 2B,SigLIP 400M

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: 3B
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 (unrestricted)
Training code: Unreleased
Hugging Face: ibm-granite

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: Granite Vision: a lightweight, open-source multimodal model for enterprise Intelligence
Last updated: 28 November 2025

The extremes

The ten fastest GPUs that run Granite Vision 3.2 2B

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 Granite Vision 3.2 2B

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 it takes to run this model

Minimum card

Tesla C1080

Memory needed

3.2 GB

Fastest

1,137 tok/s

Granite Vision 3.2 2B reaches a parameter count of 3B. That is small enough that hardware is rarely the obstacle, including on cards several years old. The number of cards we track that can run it: 818.

The smallest card that holds it is Tesla C1080, with a memory capacity of 4 GB, running it at a compression of Q6_K and producing around 18.0 tokens per second.

At the other end sits B200, generating roughly 1,137 tokens per second on the strength of a memory bandwidth of 8,000 GB/s.

About this model

Granite Vision 3.2 2B was published by IBM, in the country recorded as United States of America, during February 2025. The publishing organisation is categorised as industry.

It works in the domain of Language, Multimodal, Vision, and is recorded as performing the task of mathematical reasoning, Quantitative reasoning, Language modeling/generation, Question answering, Visual question answering.

Rather than being trained from scratch, it is derived from Granite 3.1 2B,SigLIP 400M. That is the usual way a specialised model is produced.

The weights are published, so it can be downloaded and run on your own hardware indefinitely, offline, with no account attached. On Hugging Face it is published under the organisation ibm-granite.

How fast it runs, and why

Across every card that can run it, the middle of the range sits at 36.1 tokens per second. Exceeding reading speed outright: 783 of them.

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

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.

Step by step

How to choose a GPU for Granite Vision 3.2 2B

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 able to hold Granite Vision 3.2 2B, needing around 3.2 GB at a compression of Q6_K. That figure, not the headline performance of a card, is what decides whether it runs.
02

Match the context to your actual use

Longer conversations cost memory on top of what the weights need. Move the slider to your real working length before trusting any row for Granite Vision 3.2 2B.
03

Set a quality floor

The quantisation column varies by card, because a bigger card holds a more accurate copy, reaching a compression of Q6_K on the smallest card that fits. Setting a minimum quality drops the cards that only manage it by squeezing further than you would want, and holds the comparison at one level.
04

Sort by speed

Ranking by tokens per second follows memory bandwidth rather than core counts, for Granite Vision 3.2 2B. It will not match a gaming ordering, because generation is bound by memory bandwidth. The card topping the list is B200, at 1,137 tok/s.
05

Read the fit column last

The fit column separates cards that just manage it from those with room to spare, in the case of Granite Vision 3.2 2B. Comfortable means you can grow the context later. That difference matters more than a few tokens per second, so buy for comfortable if you expect to.
06

Open the card you have settled on

Every card name links to its own page, which runs the same calculation across the whole model catalogue. A card is usually bought for more than one model, so it is worth a look before buying for Granite Vision 3.2 2B.

Answers

Granite Vision 3.2 2B — common questions

Granite Vision 3.2 2B— can I run it if it does not fit in my GPU?

Only by offloading, which is usually a false economy: the part held in system memory drags the whole thing down. Every figure here assumes the whole model is resident on the card.

Granite Vision 3.2 2B— would two GPUs run it faster?

Capacity adds across cards; throughput does not. The number of cards already holding it on their own: 818. So a second card is rarely the answer here.

Granite Vision 3.2 2B— why does the quantisation differ between cards?

Because capacity varies, so does how hard it has to be squeezed. The number of distinct levels in the table above: 2. Bigger cards get the more accurate version, and the quality floor above pins the comparison to one level.

Granite Vision 3.2 2B— how accurate are these speed estimates?

These are estimates with real error bars, and any of them could reasonably land anywhere in its published range depending on which runtime you use. The fastest result here: 682–1,819 tok/s on B200. The same model and card vary by thirty to fifty per cent depending on the inference software and its version.

Granite Vision 3.2 2B— what GPU do I need to run it?

The smallest card in our catalogue that holds it is Tesla C1080, with a memory capacity of 4 GB. It runs the model at a compression of Q6_K using about 3.2 GB, and produces roughly 18.0 tokens per second. The number of cards able to run it in total: 818.

Granite Vision 3.2 2B— how fast is it on a GPU?

It depends on the card. The quickest we calculate is B200, at about 1,137 tokens per second; the slowest that still runs it manages considerably less. Reading speed is around ten tokens per second, and the number of cards clearing that: 783.

Granite Vision 3.2 2B— how much VRAM does it need?

It needs about 3.2 GB at a compression of Q6_K, 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.

Granite Vision 3.2 2B— can I run it on a GPU holding 8 GB?

Yes. The card CMP 170HX 8 GB, holding 8 GB, runs it at a compression of Q8_0, using about 3.9 GB and generating roughly 212 tokens per second. The fit is comfortable.

Granite Vision 3.2 2B— can I run it on a GPU holding 12 GB?

Yes. The card GeForce RTX 3080 Ti, holding 12 GB, runs it at a compression of Q8_0, using about 3.9 GB and generating roughly 130 tokens per second. The fit is comfortable.

Granite Vision 3.2 2B— can I run it on a GPU holding 16 GB?

Yes. The card Tesla V100 SXM2 16 GB, holding 16 GB, runs it at a compression of Q8_0, using about 3.9 GB and generating roughly 161 tokens per second. The fit is comfortable.

Granite Vision 3.2 2B— can I run it on a GPU holding 24 GB?

Yes. The card GeForce RTX 5090 D V2, holding 24 GB, runs it at a compression of Q8_0, using about 3.9 GB and generating roughly 190 tokens per second. The fit is comfortable.

Granite Vision 3.2 2B— is it open source?

Its weights are published, so it 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.

Granite Vision 3.2 2B— how many parameters does it have?

It has a parameter count of 3B. 2.98B. 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.

Granite Vision 3.2 2B— who created it?

It was published by IBM, based in United States of America, an organisation categorised as industry.

Granite Vision 3.2 2B— when was it released?

It was published in February 2025.

Granite Vision 3.2 2B— what is it used for?

It works in the domain of Language, Multimodal, Vision, and is recorded as handling the task of mathematical reasoning, Quantitative reasoning, Language modeling/generation, Question answering, Visual 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.

Granite Vision 3.2 2B— where can I download it?

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

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