Qwen1.5-110B TPS calculator

Open weights Alibaba 110B parameters April 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

43 of 818 cards that can run it

Smallest card that fits

Radeon Instinct MI200

64 GB · Q3_K_M · 13.3 tok/s

Fastest card

B200

30.8 tok/s · 180 GB

Which GPUs can run Qwen1.5-110B?

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

43 cards match

Calculating

					Needs	Quantisation	Fit
30.8 tok/s 18–49 · low confidence	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	118.5 GB	Q8_0	Comfortable
30.8 tok/s 18–49 · low confidence	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	118.5 GB	Q8_0	Comfortable
29.9 tok/s 18–48 · low confidence	H100 SXM5 80 GB NVIDIA	80 GB	3,360 GB/s	Oct 2022	67.2 GB	Q4_K_M	Tight
29.9 tok/s 18–48 · low confidence	H800 SXM5 NVIDIA	80 GB	3,360 GB/s	Mar 2023	67.2 GB	Q4_K_M	Tight
28.6 tok/s 17–46 · low confidence	Radeon Instinct MI300 AMD	128 GB	6,550 GB/s	Jan 2023	92.9 GB	Q6_K	Comfortable
27.1 tok/s 16–43 · low confidence	H100 NVL 94 GB NVIDIA	94 GB	3,940 GB/s	Mar 2023	80.1 GB	Q5_K_M	Tight
24.6 tok/s 15–39 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	118.5 GB	Q8_0	Comfortable
24.6 tok/s 15–39 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	118.5 GB	Q8_0	Comfortable
23.2 tok/s 14–37 · low confidence	Radeon Instinct MI300A AMD	128 GB	5,325 GB/s	Dec 2023	92.9 GB	Q6_K	Comfortable
23.1 tok/s 14–37 · low confidence	H100 PCIe 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	80.1 GB	Q5_K_M	Tight
23.1 tok/s 14–37 · low confidence	H100 SXM5 94 GB NVIDIA	94 GB	3,360 GB/s	Mar 2023	80.1 GB	Q5_K_M	Tight
23.1 tok/s 14–37 · low confidence	H100 SXM5 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	80.1 GB	Q5_K_M	Tight
21.0 tok/s 13–34 · low confidence	H100 SXM5 64 GB NVIDIA	64 GB	2,020 GB/s	Mar 2023	54.4 GB	Q3_K_M	Tight
18.8 tok/s 11–30 · low confidence	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	118.5 GB	Q8_0	Tight
18.8 tok/s 11–30 · low confidence	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	118.5 GB	Q8_0	Tight
18.1 tok/s 11–29 · low confidence	A100 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Nov 2020	67.2 GB	Q4_K_M	Tight
18.1 tok/s 11–29 · low confidence	A100X NVIDIA	80 GB	2,040 GB/s	Jun 2021	67.2 GB	Q4_K_M	Tight
18.1 tok/s 11–29 · low confidence	A800 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Aug 2022	67.2 GB	Q4_K_M	Tight
18.1 tok/s 11–29 · low confidence	H100 CNX NVIDIA	80 GB	2,040 GB/s	Mar 2023	67.2 GB	Q4_K_M	Tight
18.1 tok/s 11–29 · low confidence	H100 PCIe 80 GB NVIDIA	80 GB	2,040 GB/s	Oct 2022	67.2 GB	Q4_K_M	Tight
18.1 tok/s 11–29 · low confidence	H800 PCIe 80 GB NVIDIA	80 GB	2,040 GB/s	Mar 2023	67.2 GB	Q4_K_M	Tight
18.0 tok/s 11–29 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	118.5 GB	Q8_0	Comfortable
17.2 tok/s 10–28 · low confidence	A100 PCIe 80 GB NVIDIA	80 GB	1,940 GB/s	Jun 2021	67.2 GB	Q4_K_M	Tight
17.2 tok/s 10–28 · low confidence	A800 PCIe 80 GB NVIDIA	80 GB	1,940 GB/s	Nov 2022	67.2 GB	Q4_K_M	Tight
16.0 tok/s 10–26 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	118.5 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: Alibaba
Organisation type: Industry
Country: China
Published: 25 April 2024
Authors: Qwen Team

What it does

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

Domain: Language
Task: Chat, Language modeling/generation, Quantitative reasoning, Code generation, Translation

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: 110B
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: Qwen

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

Sources

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

Reference: Qwen1.5-110B: The First 100B+ Model of the Qwen1.5 Series
Last updated: 28 November 2025

The extremes

The ten fastest GPUs for Qwen1.5-110B

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 Qwen1.5-110B

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

Radeon Instinct MI200

Memory needed

54.4 GB

Fastest

30.8 tok/s

Qwen1.5-110B sits at 110B parameters, which puts it above consumer hardware and into the range where a card is bought for this purpose rather than repurposed for it. 43 of the cards we track can hold it.

The least hardware that works is a Radeon Instinct MI200. Its 64 GB is enough at Q3_K_M compression, giving roughly 13.3 tokens per second.

The quickest result comes from a B200 at around 30.8 tokens per second — its 8,000 GB/s of bandwidth is what buys that.

What this model is

Qwen1.5-110B was published by Alibaba, in China, in April 2024. The organisation is categorised as industry.

It works in Language, and is recorded as doing chat, Language modeling/generation, Quantitative reasoning, Code generation, Translation.

Because its weights were released, nothing about running it depends on a provider staying available — it is yours once downloaded. It is published under the Qwen organisation on Hugging Face.

What decides the speed

The median result is around 18.0 tokens per second; 39 cards produce text faster than most people read it.

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

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 Qwen1.5-110B

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

Look at what Qwen1.5-110B actually needs — around 54.4 GB at Q3_K_M. No amount of processing power compensates for a card that cannot hold it.
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 Qwen1.5-110B stops fitting a card that seemed fine.
03

Set a quality floor

The quantisation column varies by card, because a bigger card holds a more accurate copy of Qwen1.5-110B — Q3_K_M on the smallest card that fits. Set a floor to hold the comparison at one level.
04

Sort by speed

Sort by speed to see how cards rank for Qwen1.5-110B. It will not match a gaming ordering — generation is bound by memory bandwidth, which is why the B200 tops it at 30.8 tok/s.
05

Look at the headroom, not just the fit

Tight means Qwen1.5-110B 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 Qwen1.5-110B alone — a card is usually bought for more than one model.

Answers

Qwen1.5-110B — common questions

How accurate are these Qwen1.5-110B 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 18–49 tok/s on the B200 rather than a single number.

What GPU do I need to run Qwen1.5-110B?

The smallest card in our catalogue that holds Qwen1.5-110B is the Radeon Instinct MI200, with 64 GB of memory. It runs the model at Q3_K_M using about 54.4 GB, and produces roughly 13.3 tokens per second. 43 cards in total can run it.

How fast is Qwen1.5-110B on a GPU?

It depends on the card. The quickest we calculate is a B200 at about 30.8 tokens per second; the slowest that still runs it manages considerably less. Reading speed is around ten tokens per second, and 39 of the cards that can run Qwen1.5-110B clear that.

How much VRAM does Qwen1.5-110B need?

About 54.4 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 Qwen1.5-110B open source?

Its weights are published, so Qwen1.5-110B 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 Qwen1.5-110B have?

Qwen1.5-110B has 110B parameters. 110B. 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 Qwen1.5-110B?

Qwen1.5-110B was published by Alibaba, based in China, categorised as industry.

When was Qwen1.5-110B released?

Qwen1.5-110B was published in April 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 Qwen1.5-110B used for?

Qwen1.5-110B works in Language, and is recorded as handling chat, Language modeling/generation, Quantitative reasoning, Code generation, Translation. These are the areas it was designed around; they describe intent rather than a hard boundary.

Where can I download Qwen1.5-110B?

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

Can I run Qwen1.5-110B 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 Qwen1.5-110B is rarely worth using — the nearest miss we calculate is short by 24.0 GB. Every figure here assumes the whole model is on the card.

Would two GPUs run Qwen1.5-110B faster?

Capacity adds across cards; throughput does not. Since 43 of the cards we track already hold Qwen1.5-110B on their own, a second card is rarely the answer here.

Why does the quantisation differ between cards for Qwen1.5-110B?

A larger card holds a more accurate copy. Across the cards that run Qwen1.5-110B, 6 compression levels are used; the floor control above pins it to one.

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