Guanaco-65B TPS calculator

Open weights University of Washington 65B parameters May 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

61 cards that can run it

818 cards we hold specifications for

Smallest card that fits

A100 PCIe 40 GB

40 GB · Q3_K_M · 27.4 tok/s

Fastest card

B200

52.1 tok/s · 180 GB

Which GPUs can run Guanaco-65B?

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

61 cards match

Calculating

					Needs	Quantisation	Fit
52.1 tok/s 31–83 · low confidence	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	70.3 GB	Q8_0	Comfortable
52.1 tok/s 31–83 · low confidence	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	70.3 GB	Q8_0	Comfortable
41.6 tok/s 25–67 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	70.3 GB	Q8_0	Comfortable
41.6 tok/s 25–67 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	70.3 GB	Q8_0	Comfortable
33.3 tok/s 20–53 · low confidence	Radeon Instinct MI300 AMD	128 GB	6,550 GB/s	Jan 2023	70.3 GB	Q8_0	Comfortable
31.9 tok/s 19–51 · low confidence	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	70.3 GB	Q8_0	Comfortable
31.9 tok/s 19–51 · low confidence	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	70.3 GB	Q8_0	Comfortable
30.5 tok/s 18–49 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	70.3 GB	Q8_0	Comfortable
28.1 tok/s 17–45 · low confidence	GRID A100B NVIDIA	48 GB	1,870 GB/s	May 2020	40.0 GB	Q4_K_M	Tight
27.4 tok/s 16–44 · low confidence	A100 PCIe 40 GB NVIDIA	40 GB	1,560 GB/s	Jun 2020	32.5 GB	Q3_K_M	Tight
27.4 tok/s 16–44 · low confidence	A100 SXM4 40 GB NVIDIA	40 GB	1,560 GB/s	May 2020	32.5 GB	Q3_K_M	Tight
27.4 tok/s 16–44 · low confidence	A800 PCIe 40 GB NVIDIA	40 GB	1,560 GB/s	Nov 2022	32.5 GB	Q3_K_M	Tight
27.1 tok/s 16–43 · low confidence	Radeon Instinct MI300A AMD	128 GB	5,325 GB/s	Dec 2023	70.3 GB	Q8_0	Comfortable
27.1 tok/s 16–43 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	70.3 GB	Q8_0	Comfortable
27.1 tok/s 16–43 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	70.3 GB	Q8_0	Comfortable
25.7 tok/s 15–41 · low confidence	H100 NVL 94 GB NVIDIA	94 GB	3,940 GB/s	Mar 2023	70.3 GB	Q8_0	Comfortable
21.9 tok/s 13–35 · low confidence	H100 PCIe 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	70.3 GB	Q8_0	Comfortable
21.9 tok/s 13–35 · low confidence	H100 SXM5 80 GB NVIDIA	80 GB	3,360 GB/s	Oct 2022	70.3 GB	Q8_0	Tight
21.9 tok/s 13–35 · low confidence	H100 SXM5 94 GB NVIDIA	94 GB	3,360 GB/s	Mar 2023	70.3 GB	Q8_0	Comfortable
21.9 tok/s 13–35 · low confidence	H100 SXM5 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	70.3 GB	Q8_0	Comfortable
21.9 tok/s 13–35 · low confidence	H800 SXM5 NVIDIA	80 GB	3,360 GB/s	Mar 2023	70.3 GB	Q8_0	Tight
20.2 tok/s 12–32 · low confidence	RTX PRO 5000 Blackwell NVIDIA	48 GB	1,340 GB/s	Mar 2025	40.0 GB	Q4_K_M	Tight
19.1 tok/s 11–31 · low confidence	H100 SXM5 64 GB NVIDIA	64 GB	2,020 GB/s	Mar 2023	55.2 GB	Q6_K	Tight
16.7 tok/s 10–27 · low confidence	Radeon Instinct MI250 AMD	128 GB	3,280 GB/s	Nov 2021	70.3 GB	Q8_0	Comfortable
16.7 tok/s 10–27 · low confidence	Radeon Instinct MI250X AMD	128 GB	3,280 GB/s	Nov 2021	70.3 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: University of Washington
Organisation type: Academia
Country: United States of America
Published: 23 May 2023
Authors: Tim Dettmers, Artidoro Pagnoni, Ari Holtzman, Luke Zettlemoyer

What it does

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

Domain: Language
Task: Chat
Base model: LLaMA-65B

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: 65B
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.

Training compute: 5.5 × 10²³ FLOP
How it was established: Hardware
Fine-tuning compute: 8 × 10¹⁸ FLOP

The training run

What it physically took to train: which chips, how many, for how long, and what that drew from the wall.

Wall-clock time: 24 hours

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

How it is classified

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

Likely above 10²³ FLOP: Yes
Record confidence: Confident
Citations: 4,560

Sources

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

Reference: QLoRA: Efficient Finetuning of Quantized LLMs
Last updated: 25 May 2026

The extremes

The ten fastest GPUs that run Guanaco-65B

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 Guanaco-65B

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

A100 PCIe 40 GB

Memory needed

32.5 GB

Fastest

52.1 tok/s

Guanaco-65B sits at 65B parameters, which puts it above consumer hardware and into the range where a card is bought for this purpose rather than repurposed for it. 61 of the cards we track can hold it.

The entry point is the A100 PCIe 40 GB: 40 GB of memory, Q3_K_M compression, roughly 27.4 tokens per second.

The quickest result comes from a B200 at around 52.1 tokens per second — its 8,000 GB/s of bandwidth is what buys that.

Where it came from

Guanaco-65B was published by University of Washington, in United States of America, in May 2023. academia is the category the publisher falls under.

It works in Language, and is recorded as doing chat.

It is derived from LLaMA-65B rather than trained from scratch, which 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.

Understanding the speeds

Across every card that can run it, the middle of the range is about 13.3 tokens per second, and 56 of them clear the ten tokens per second that roughly matches reading speed.

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.

Training and provenance

Producing it required around 5.5 × 10²³ FLOP of arithmetic, which is a statement about the training budget rather than about inference.

Step by step

How to choose a GPU for Guanaco-65B

The table above has already assessed every card we hold specifications for against this model. Getting to your answer takes six steps.

01

Read the memory figure first

Every card here has been checked against Guanaco-65B — around 32.5 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

Set the context to what you will actually use. The cache grows with the conversation, and it is the usual reason Guanaco-65B stops fitting a card that seemed fine.
03

Decide how much compression you will accept

The quantisation column varies by card, because a bigger card holds a more accurate copy of Guanaco-65B — Q3_K_M on the smallest card that fits. Set a floor to hold the comparison at one level.
04

Compare tokens per second, not specifications

The speed ordering for Guanaco-65B is effectively an ordering by memory bandwidth, which is why the B200 tops it at 52.1 tok/s.
05

Read the fit column last

The fit column separates cards that just manage Guanaco-65B from those with room to spare. Buy for the second if the context might grow.
06

Open the card you have settled on

Following a card through to its own page shows every other model it can hold, which is the question that follows once Guanaco-65B is settled.

Answers

Guanaco-65B — common questions

What is Guanaco-65B used for?

Guanaco-65B works in Language, and is recorded as handling chat. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.

Where can I download Guanaco-65B?

The weights for Guanaco-65B are published, though we do not hold a repository link for it. This site calculates hardware requirements rather than hosting model files.

How much compute was used to train Guanaco-65B?

Around 5.5 × 10²³ FLOP. That measures what producing the model cost and says nothing about how quickly it answers once trained — inference speed comes from memory bandwidth, not from the training budget.

Can I run Guanaco-65B if it does not fit in my GPU?

It can be split between the card and system memory, but Guanaco-65B generates painfully slowly that way — the nearest miss we calculate is short by 11.2 GB. Nothing on this page assumes offloading.

Would two GPUs run Guanaco-65B faster?

A second card roughly doubles the memory available but not the generation rate. With 61 cards already able to run Guanaco-65B alone, the case for pairing is weak.

Why does the quantisation differ between cards for Guanaco-65B?

A larger card holds a more accurate copy. Across the cards that run Guanaco-65B, 4 compression levels are used; the floor control above pins it to one.

How accurate are these Guanaco-65B 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 31–83 tok/s on the B200 rather than a single number.

What GPU do I need to run Guanaco-65B?

The smallest card in our catalogue that holds Guanaco-65B is the A100 PCIe 40 GB, with 40 GB of memory. It runs the model at Q3_K_M using about 32.5 GB, and produces roughly 27.4 tokens per second. 61 cards in total can run it.

How fast is Guanaco-65B on a GPU?

It depends on the card. The quickest we calculate is a B200 at about 52.1 tokens per second; the slowest that still runs it manages considerably less. Reading speed is around ten tokens per second, and 56 of the cards that can run Guanaco-65B clear that.

How much VRAM does Guanaco-65B need?

About 32.5 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.

Is Guanaco-65B open source?

Its weights are published, so Guanaco-65B 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 Guanaco-65B have?

Guanaco-65B has 65B parameters. from Llama-65B (also 33B, 13B, 7B variants). 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 Guanaco-65B?

Guanaco-65B was published by University of Washington, based in United States of America, categorised as academia.

When was Guanaco-65B released?

Guanaco-65B was published in May 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.

Source

Original publication

Record last updated 25 May 2026

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