Vicuna-13B v0 TPS calculator

Open weights Large Model Systems Organization,University of California (UC) Berkeley 13B parameters March 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

509 cards that can run it

818 cards we hold specifications for

Smallest card that fits

Xeon Phi 5110P

8 GB · Q3_K_M · 18.3 tok/s

Fastest card

B200

261 tok/s · 180 GB

Which GPUs can run Vicuna-13B v0?

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

509 cards match

Calculating

					Needs	Quantisation	Fit
261 tok/s 156–417 · low confidence	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	14.6 GB	Q8_0	Comfortable
261 tok/s 156–417 · low confidence	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	14.6 GB	Q8_0	Comfortable
208 tok/s 125–333 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	14.6 GB	Q8_0	Comfortable
208 tok/s 125–333 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	14.6 GB	Q8_0	Comfortable
166 tok/s 100–266 · low confidence	Radeon Instinct MI300 AMD	128 GB	6,550 GB/s	Jan 2023	14.6 GB	Q8_0	Comfortable
159 tok/s 96–255 · low confidence	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	14.6 GB	Q8_0	Comfortable
159 tok/s 96–255 · low confidence	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	14.6 GB	Q8_0	Comfortable
152 tok/s 91–244 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	14.6 GB	Q8_0	Comfortable
135 tok/s 81–217 · low confidence	Radeon Instinct MI300A AMD	128 GB	5,325 GB/s	Dec 2023	14.6 GB	Q8_0	Comfortable
135 tok/s 81–217 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	14.6 GB	Q8_0	Comfortable
135 tok/s 81–217 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	14.6 GB	Q8_0	Comfortable
131 tok/s 79–210 · low confidence	CMP 170HX 8 GB NVIDIA	8 GB	1,490 GB/s	Sep 2021	7.1 GB	Q3_K_M	Tight
128 tok/s 77–205 · low confidence	H100 NVL 94 GB NVIDIA	94 GB	3,940 GB/s	Mar 2023	14.6 GB	Q8_0	Comfortable
117 tok/s 70–188 · low confidence	CMP 170HX 10 GB NVIDIA	10 GB	1,560 GB/s	Sep 2021	8.6 GB	Q4_K_M	Tight
109 tok/s 66–175 · low confidence	H100 PCIe 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	14.6 GB	Q8_0	Comfortable
109 tok/s 66–175 · low confidence	H100 SXM5 80 GB NVIDIA	80 GB	3,360 GB/s	Oct 2022	14.6 GB	Q8_0	Comfortable
109 tok/s 66–175 · low confidence	H100 SXM5 94 GB NVIDIA	94 GB	3,360 GB/s	Mar 2023	14.6 GB	Q8_0	Comfortable
109 tok/s 66–175 · low confidence	H100 SXM5 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	14.6 GB	Q8_0	Comfortable
109 tok/s 66–175 · low confidence	H800 SXM5 NVIDIA	80 GB	3,360 GB/s	Mar 2023	14.6 GB	Q8_0	Comfortable
83.4 tok/s 50–133 · low confidence	Radeon Instinct MI250 AMD	128 GB	3,280 GB/s	Nov 2021	14.6 GB	Q8_0	Comfortable
83.4 tok/s 50–133 · low confidence	Radeon Instinct MI250X AMD	128 GB	3,280 GB/s	Nov 2021	14.6 GB	Q8_0	Comfortable
69.5 tok/s 42–111 · low confidence	Data Center GPU Max 1550 Intel	128 GB	3,280 GB/s	Jan 2023	14.6 GB	Q8_0	Comfortable
68.0 tok/s 41–109 · low confidence	Data Center GPU Max Subsystem Intel	128 GB	3,210 GB/s	Jan 2023	14.6 GB	Q8_0	Comfortable
67.5 tok/s 41–108 · low confidence	RTX A5000-8Q NVIDIA	8 GB	768 GB/s	Apr 2021	7.1 GB	Q3_K_M	Tight
66.5 tok/s 40–106 · low confidence	A100 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Nov 2020	14.6 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: Large Model Systems Organization,University of California (UC) Berkeley
Organisation type: Academia,Academia
Country: United States of America
Published: 30 March 2023
Authors: Wei-Lin Chiang, Zhuohan Li, Zi Lin, Ying Sheng, Zhanghao Wu, Hao Zhang, Lianmin Zheng, Siyuan Zhuang, Yonghao Zhuang, Joseph E. Gonzalez, Ion Stoica, Eric P. Xing

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
Base model: LLaMA-13B

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: 13B
Training data: 207,200,000 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

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
Chips used: 8
Power draw: 6.4 kW
Compute cost: $300

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 (restricted use)
Training code: Open source

How it is classified

Labels the source dataset applies when tracking notable models, and how confident it is in the entry.

Record confidence: Likely

Sources

Where this record came from and when it was last checked.

Reference: Vicuna: An Open-Source Chatbot Impressing GPT-4 with 90%* ChatGPT Quality
Last updated: 28 November 2025

The extremes

The ten fastest GPUs that run Vicuna-13B v0

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 Vicuna-13B v0

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

Xeon Phi 5110P

Memory needed

7.1 GB

Fastest

261 tok/s

Vicuna-13B v0 is small enough at 13B parameters that hardware is rarely the obstacle — 509 of the cards we track can run it, including cards several years old.

The least hardware that works is a Xeon Phi 5110P. Its 8 GB is enough at Q3_K_M compression, giving roughly 18.3 tokens per second.

The quickest result comes from a B200 at around 261 tokens per second — its 8,000 GB/s of bandwidth is what buys that.

Where it came from

Vicuna-13B v0 was published by Large Model Systems Organization,University of California (UC) Berkeley, in United States of America, in March 2023. It comes out of academia,Academia.

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

Its starting point was LLaMA-13B — most models at this scale are adapted from an existing base rather than built from nothing.

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.

Understanding the speeds

The median result is around 21.2 tokens per second; 459 cards produce text faster than most people read it.

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.

How it was trained

It was trained on about 207,200,000 tokens of text.

Step by step

How to choose a GPU for Vicuna-13B v0

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

Every card here has been checked against Vicuna-13B v0 — around 7.1 GB at Q3_K_M. Capacity is the gate — a card either holds it or it does not.
02

Decide how long your conversations run

The conversation occupies memory too, and grows as it goes. Set the slider to the length you expect: at long context Vicuna-13B v0 can slip off a card that handles short questions easily.
03

Decide how much compression you will accept

Compression is what makes Vicuna-13B v0 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

Rank by throughput rather than spec sheet

Sort by speed to see how cards rank for Vicuna-13B v0. It will not match a gaming ordering — generation is bound by memory bandwidth, which is why the B200 tops it at 261 tok/s.
05

Look at the headroom, not just the fit

Tight means Vicuna-13B v0 loads and works, with no room to raise the context later. Comfortable means you can. The difference matters more than a few tokens per second.
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. Worth a look before buying for Vicuna-13B v0 alone — a card is usually bought for more than one model.

Answers

Vicuna-13B v0 — common questions

Can I run Vicuna-13B v0 on a 12 GB GPU?

Yes. A GeForce RTX 3080 Ti with 12 GB runs it at Q5_K_M, using about 10.1 GB and generating roughly 53.1 tokens per second — a tight fit.

Can I run Vicuna-13B v0 on a 16 GB GPU?

Yes. A Tesla V100 SXM2 16 GB with 16 GB runs it at Q6_K, using about 11.6 GB and generating roughly 53.5 tokens per second — a comfortable fit.

Can I run Vicuna-13B v0 on a 24 GB GPU?

Yes. A GeForce RTX 5090 D V2 with 24 GB runs it at Q8_0, using about 14.6 GB and generating roughly 43.7 tokens per second — a comfortable fit.

Is Vicuna-13B v0 open source?

Its weights are published, so Vicuna-13B v0 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 Vicuna-13B v0 have?

Vicuna-13B v0 has 13B 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.

Who created Vicuna-13B v0?

Vicuna-13B v0 was published by Large Model Systems Organization,University of California (UC) Berkeley, based in United States of America, categorised as academia,Academia.

When was Vicuna-13B v0 released?

Vicuna-13B v0 was published in March 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 Vicuna-13B v0 used for?

Vicuna-13B v0 works in Language, and is recorded as handling language modeling/generation, Chat. These are the areas it was designed around; they describe intent rather than a hard boundary.

Where can I download Vicuna-13B v0?

The weights for Vicuna-13B v0 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 Vicuna-13B v0 if it does not fit in my GPU?

It can be split between the card and system memory, but Vicuna-13B v0 generates painfully slowly that way — the nearest miss we calculate is short by 3.2 GB. Nothing on this page assumes offloading.

Would two GPUs run Vicuna-13B v0 faster?

Two cards buy memory rather than speed. That matters for Vicuna-13B v0 only if one card cannot hold it — 509 can, so a second adds little.

Why does the quantisation differ between cards for Vicuna-13B v0?

Each card is shown running the least-compressed copy it can hold, and Vicuna-13B v0 appears at 5 different compression levels across the cards that fit it. Bigger cards get the more accurate version.

How accurate are these Vicuna-13B v0 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 156–417 tok/s on the B200 rather than a single number.

What GPU do I need to run Vicuna-13B v0?

The smallest card in our catalogue that holds Vicuna-13B v0 is the Xeon Phi 5110P, with 8 GB of memory. It runs the model at Q3_K_M using about 7.1 GB, and produces roughly 18.3 tokens per second. 509 cards in total can run it.

How fast is Vicuna-13B v0 on a GPU?

It depends on the card. The quickest we calculate is a B200 at about 261 tokens per second; the slowest that still runs it manages considerably less. Reading speed is around ten tokens per second, and 459 of the cards that can run Vicuna-13B v0 clear that.

How much VRAM does Vicuna-13B v0 need?

About 7.1 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 Vicuna-13B v0 on a 8 GB GPU?

Yes. A CMP 170HX 8 GB with 8 GB runs it at Q3_K_M, using about 7.1 GB and generating roughly 131 tokens per second — a tight fit.

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