Dolly 2.0-12b TPS calculator

Open weights Databricks 12B parameters April 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 · 19.8 tok/s

Fastest card

B200

282 tok/s · 180 GB

Which GPUs can run Dolly 2.0-12b?

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
282 tok/s 169–452 · low confidence	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	13.5 GB	Q8_0	Comfortable
282 tok/s 169–452 · low confidence	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	13.5 GB	Q8_0	Comfortable
225 tok/s 135–361 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	13.5 GB	Q8_0	Comfortable
225 tok/s 135–361 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	13.5 GB	Q8_0	Comfortable
180 tok/s 108–289 · low confidence	Radeon Instinct MI300 AMD	128 GB	6,550 GB/s	Jan 2023	13.5 GB	Q8_0	Comfortable
173 tok/s 104–276 · low confidence	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	13.5 GB	Q8_0	Comfortable
173 tok/s 104–276 · low confidence	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	13.5 GB	Q8_0	Comfortable
165 tok/s 99–264 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	13.5 GB	Q8_0	Comfortable
147 tok/s 88–235 · low confidence	Radeon Instinct MI300A AMD	128 GB	5,325 GB/s	Dec 2023	13.5 GB	Q8_0	Comfortable
147 tok/s 88–235 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	13.5 GB	Q8_0	Comfortable
147 tok/s 88–235 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	13.5 GB	Q8_0	Comfortable
142 tok/s 85–227 · low confidence	CMP 170HX 8 GB NVIDIA	8 GB	1,490 GB/s	Sep 2021	6.6 GB	Q3_K_M	Tight
139 tok/s 83–222 · low confidence	H100 NVL 94 GB NVIDIA	94 GB	3,940 GB/s	Mar 2023	13.5 GB	Q8_0	Comfortable
127 tok/s 76–203 · low confidence	CMP 170HX 10 GB NVIDIA	10 GB	1,560 GB/s	Sep 2021	8.0 GB	Q4_K_M	Tight
119 tok/s 71–190 · low confidence	H100 PCIe 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	13.5 GB	Q8_0	Comfortable
119 tok/s 71–190 · low confidence	H100 SXM5 80 GB NVIDIA	80 GB	3,360 GB/s	Oct 2022	13.5 GB	Q8_0	Comfortable
119 tok/s 71–190 · low confidence	H100 SXM5 94 GB NVIDIA	94 GB	3,360 GB/s	Mar 2023	13.5 GB	Q8_0	Comfortable
119 tok/s 71–190 · low confidence	H100 SXM5 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	13.5 GB	Q8_0	Comfortable
119 tok/s 71–190 · low confidence	H800 SXM5 NVIDIA	80 GB	3,360 GB/s	Mar 2023	13.5 GB	Q8_0	Comfortable
90.3 tok/s 54–144 · low confidence	Radeon Instinct MI250 AMD	128 GB	3,280 GB/s	Nov 2021	13.5 GB	Q8_0	Comfortable
90.3 tok/s 54–144 · low confidence	Radeon Instinct MI250X AMD	128 GB	3,280 GB/s	Nov 2021	13.5 GB	Q8_0	Comfortable
75.3 tok/s 45–120 · low confidence	Data Center GPU Max 1550 Intel	128 GB	3,280 GB/s	Jan 2023	13.5 GB	Q8_0	Comfortable
73.6 tok/s 44–118 · low confidence	Data Center GPU Max Subsystem Intel	128 GB	3,210 GB/s	Jan 2023	13.5 GB	Q8_0	Comfortable
73.1 tok/s 44–117 · low confidence	RTX A5000-8Q NVIDIA	8 GB	768 GB/s	Apr 2021	6.6 GB	Q3_K_M	Tight
72.0 tok/s 43–115 · low confidence	A100 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Nov 2020	13.5 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: Databricks
Organisation type: Industry
Country: United States of America
Published: 12 April 2023
Authors: Mike Conover, Matt Hayes, Ankit Mathur, Jianwei Xie, Jun Wan, Sam Shah, Ali Ghodsi, Patrick Wendell, Matei Zaharia, Reynold Xin

What it does

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

Domain: Language
Task: Chat
Base model: Pythia-12b

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: 12B
Training data: 1,186,286 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.

Fine-tuning compute: 2.5 × 10¹⁴ FLOP

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: 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: Confident

Sources

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

Reference: Free Dolly: Introducing the World's First Truly Open Instruction-Tuned LLM
Last updated: 28 November 2025

The extremes

The ten fastest GPUs that run Dolly 2.0-12b

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 Dolly 2.0-12b

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

Xeon Phi 5110P

Memory needed

6.6 GB

Fastest

282 tok/s

Dolly 2.0-12b is small enough at 12B parameters that hardware is rarely the obstacle — 509 of the cards we track can run it, including cards several years old.

At the low end, a Xeon Phi 5110P handles it — 8 GB, at Q3_K_M, for about 19.8 tokens per second.

A B200 is the fastest we calculate for it: about 282 tokens per second, from 8,000 GB/s of memory bandwidth.

Background

Dolly 2.0-12b was published by Databricks, in United States of America, in April 2023. It comes out of industry.

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

Its starting point was Pythia-12b — most models at this scale are adapted from an existing base rather than built from nothing.

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

Reading the throughput figures

The median result is around 20.8 tokens per second; 455 cards produce text faster than most people read it.

It is a dense model, so every parameter is read for every token produced. That makes speed track memory bandwidth almost exactly — a card with twice the bandwidth generates roughly twice as fast.

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

The training set ran to roughly 1,186,286 tokens.

Step by step

How to choose a GPU for Dolly 2.0-12b

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 Dolly 2.0-12b — around 6.6 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 Dolly 2.0-12b stops fitting a card that seemed fine.
03

Choose how far you will compress it

Compression is what makes Dolly 2.0-12b 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 Dolly 2.0-12b. It will not match a gaming ordering — generation is bound by memory bandwidth, which is why the B200 tops it at 282 tok/s.
05

Look at the headroom, not just the fit

A tight fit runs Dolly 2.0-12b 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

Each card page repeats this sweep for every model we hold. It answers what else the hardware is good for, beyond Dolly 2.0-12b.

Answers

Dolly 2.0-12b — common questions

When was Dolly 2.0-12b released?

Dolly 2.0-12b was published in April 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 Dolly 2.0-12b used for?

Dolly 2.0-12b works in Language, and is recorded as handling chat. These are the areas it was designed around; they describe intent rather than a hard boundary.

Where can I download Dolly 2.0-12b?

The weights for Dolly 2.0-12b 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 Dolly 2.0-12b 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 Dolly 2.0-12b is rarely worth using — the nearest miss we calculate is short by 2.6 GB. Every figure here assumes the whole model is on the card.

Would two GPUs run Dolly 2.0-12b faster?

Two cards buy memory rather than speed. That matters for Dolly 2.0-12b only if one card cannot hold it — 509 can, so a second adds little.

Why does the quantisation differ between cards for Dolly 2.0-12b?

A larger card holds a more accurate copy. Across the cards that run Dolly 2.0-12b, 5 compression levels are used; the floor control above pins it to one.

How accurate are these Dolly 2.0-12b speed estimates?

These are estimates with real error bars. The fastest result here, 169–452 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 Dolly 2.0-12b?

The smallest card in our catalogue that holds Dolly 2.0-12b is the Xeon Phi 5110P, with 8 GB of memory. It runs the model at Q3_K_M using about 6.6 GB, and produces roughly 19.8 tokens per second. 509 cards in total can run it.

How fast is Dolly 2.0-12b on a GPU?

It depends on the card. The quickest we calculate is a B200 at about 282 tokens per second; the slowest that still runs it manages considerably less. Reading speed is around ten tokens per second, and 455 of the cards that can run Dolly 2.0-12b clear that.

How much VRAM does Dolly 2.0-12b need?

About 6.6 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 Dolly 2.0-12b on a 8 GB GPU?

Yes. A CMP 170HX 8 GB with 8 GB runs it at Q3_K_M, using about 6.6 GB and generating roughly 142 tokens per second — a tight fit.

Can I run Dolly 2.0-12b on a 12 GB GPU?

Yes. A GeForce RTX 3080 Ti with 12 GB runs it at Q6_K, using about 10.8 GB and generating roughly 46.8 tokens per second — a tight fit.

Can I run Dolly 2.0-12b on a 16 GB GPU?

Yes. A Tesla V100 SXM2 16 GB with 16 GB runs it at Q8_0, using about 13.5 GB and generating roughly 39.9 tokens per second — a tight fit.

Can I run Dolly 2.0-12b on a 24 GB GPU?

Yes. A GeForce RTX 5090 D V2 with 24 GB runs it at Q8_0, using about 13.5 GB and generating roughly 47.3 tokens per second — a comfortable fit.

Is Dolly 2.0-12b open source?

Its weights are published, so Dolly 2.0-12b 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 Dolly 2.0-12b have?

Dolly 2.0-12b has 12B 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 Dolly 2.0-12b?

Dolly 2.0-12b was published by Databricks, based in United States of America, categorised as industry.

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