Qwen1.5-14B TPS calculator

Open weights Alibaba 14B parameters February 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

241 cards that can run it

818 cards we hold specifications for

Smallest card that fits

Xeon Phi 7120P

16 GB · IQ4_XS · 17.0 tok/s

Fastest card

B200

242 tok/s · 180 GB

Which GPUs can run Qwen1.5-14B?

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

241 cards match

Calculating

					Needs	Quantisation	Fit
242 tok/s 206–290	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	21.1 GB	Q8_0	Comfortable
242 tok/s 206–290	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	21.1 GB	Q8_0	Comfortable
193 tok/s 116–309 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	21.1 GB	Q8_0	Comfortable
193 tok/s 116–309 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	21.1 GB	Q8_0	Comfortable
155 tok/s 93–247 · low confidence	Radeon Instinct MI300 AMD	128 GB	6,550 GB/s	Jan 2023	21.1 GB	Q8_0	Comfortable
148 tok/s 126–178	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	21.1 GB	Q8_0	Comfortable
148 tok/s 126–178	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	21.1 GB	Q8_0	Comfortable
142 tok/s 85–227 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	21.1 GB	Q8_0	Comfortable
126 tok/s 75–201 · low confidence	Radeon Instinct MI300A AMD	128 GB	5,325 GB/s	Dec 2023	21.1 GB	Q8_0	Comfortable
126 tok/s 75–201 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	21.1 GB	Q8_0	Comfortable
126 tok/s 75–201 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	21.1 GB	Q8_0	Comfortable
119 tok/s 101–143	H100 NVL 94 GB NVIDIA	94 GB	3,940 GB/s	Mar 2023	21.1 GB	Q8_0	Comfortable
102 tok/s 86–122	H100 PCIe 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	21.1 GB	Q8_0	Comfortable
102 tok/s 86–122	H100 SXM5 80 GB NVIDIA	80 GB	3,360 GB/s	Oct 2022	21.1 GB	Q8_0	Comfortable
102 tok/s 86–122	H100 SXM5 94 GB NVIDIA	94 GB	3,360 GB/s	Mar 2023	21.1 GB	Q8_0	Comfortable
102 tok/s 86–122	H100 SXM5 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	21.1 GB	Q8_0	Comfortable
102 tok/s 86–122	H800 SXM5 NVIDIA	80 GB	3,360 GB/s	Mar 2023	21.1 GB	Q8_0	Comfortable
83.9 tok/s 71–101	Tesla V100 SXM2 16 GB NVIDIA	16 GB	1,130 GB/s	Nov 2019	13.7 GB	IQ4_XS	Tight
77.4 tok/s 46–124 · low confidence	Radeon Instinct MI250 AMD	128 GB	3,280 GB/s	Nov 2021	21.1 GB	Q8_0	Comfortable
77.4 tok/s 46–124 · low confidence	Radeon Instinct MI250X AMD	128 GB	3,280 GB/s	Nov 2021	21.1 GB	Q8_0	Comfortable
71.3 tok/s 61–86	GeForce RTX 5080 NVIDIA	16 GB	960 GB/s	Jan 2025	13.7 GB	IQ4_XS	Tight
66.6 tok/s 57–80	Tesla V100 DGXS 16 GB NVIDIA	16 GB	897 GB/s	Mar 2018	13.7 GB	IQ4_XS	Tight
66.6 tok/s 57–80	Tesla V100 PCIe 16 GB NVIDIA	16 GB	897 GB/s	Jun 2017	13.7 GB	IQ4_XS	Tight
66.6 tok/s 57–80	Tesla V100 SXM2 16 GB NVIDIA	16 GB	897 GB/s	Jun 2017	13.7 GB	IQ4_XS	Tight
66.6 tok/s 57–80	GeForce RTX 5070 Ti NVIDIA	16 GB	896 GB/s	Feb 2025	13.7 GB	IQ4_XS	Tight

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: 4 February 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: 14B
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: 3.4 × 10²³ FLOP
How it was established: Operation counting

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: Introducing Qwen1.5
Last updated: 28 November 2025

The extremes

The ten fastest GPUs that run Qwen1.5-14B

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 Qwen1.5-14B

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 7120P

Memory needed

13.7 GB

Fastest

242 tok/s

Qwen1.5-14B is small enough at 14B parameters that hardware is rarely the obstacle — 241 of the cards we track can run it, including cards several years old.

At the low end, a Xeon Phi 7120P handles it — 16 GB, at IQ4_XS, for about 17.0 tokens per second.

Top of the range is the B200, at roughly 242 tokens per second thanks to 8,000 GB/s of bandwidth.

Background

Qwen1.5-14B was published by Alibaba, in China, in February 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.

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. It is published under the Qwen organisation on Hugging Face.

Reading the throughput figures

The median result is around 28.5 tokens per second; 220 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 attention layout is on file, so the memory figures are computed exactly rather than approximated.

What went into building it

The training run consumed about 3.4 × 10²³ FLOP. That figure describes the cost of creating it and has no bearing on how quickly it generates text.

Step by step

How to choose a GPU for Qwen1.5-14B

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

Look at what Qwen1.5-14B actually needs — around 13.7 GB at IQ4_XS. No amount of processing power compensates for a card that cannot hold it.
02

Set the context length you will work at

Longer conversations cost memory on top of what the weights need. Move the slider to your real working length before trusting any row for Qwen1.5-14B.
03

Decide how much compression you will accept

Compression is what makes Qwen1.5-14B fit smaller cards, at some cost in accuracy — IQ4_XS on the smallest card that fits. A minimum quality removes the ones that go too far.
04

Rank by throughput rather than spec sheet

Ranking by tokens per second for Qwen1.5-14B follows memory bandwidth, not core counts, which is why the B200 tops it at 242 tok/s.
05

Look at the headroom, not just the fit

The fit column separates cards that just manage Qwen1.5-14B from those with room to spare. Buy for the second if the context might grow.
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 Qwen1.5-14B alone — a card is usually bought for more than one model.

Answers

Qwen1.5-14B — common questions

Where can I download Qwen1.5-14B?

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.

How much compute was used to train Qwen1.5-14B?

Around 3.4 × 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 Qwen1.5-14B if it does not fit in my GPU?

It can be split between the card and system memory, but Qwen1.5-14B generates painfully slowly that way — the nearest miss we calculate is short by 3.7 GB. Nothing on this page assumes offloading.

Would two GPUs run Qwen1.5-14B faster?

Two cards buy memory rather than speed. That matters for Qwen1.5-14B only if one card cannot hold it — 241 can, so a second adds little.

Why does the quantisation differ between cards for Qwen1.5-14B?

Because capacity varies, so does how hard Qwen1.5-14B has to be squeezed — 3 distinct levels appear in the table above. Set a minimum quality to compare at one.

How accurate are these Qwen1.5-14B speed estimates?

They are calculated from specifications rather than measured, and each carries a range — 206–290 tok/s on the B200, for instance. The same model and card vary by thirty to fifty per cent depending on the inference software and its version.

What GPU do I need to run Qwen1.5-14B?

The smallest card in our catalogue that holds Qwen1.5-14B is the Xeon Phi 7120P, with 16 GB of memory. It runs the model at IQ4_XS using about 13.7 GB, and produces roughly 17.0 tokens per second. 241 cards in total can run it.

How fast is Qwen1.5-14B on a GPU?

It depends on the card. The quickest we calculate is a B200 at about 242 tokens per second; the slowest that still runs it manages considerably less. Reading speed is around ten tokens per second, and 220 of the cards that can run Qwen1.5-14B clear that.

How much VRAM does Qwen1.5-14B need?

About 13.7 GB at IQ4_XS 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 Qwen1.5-14B on a 16 GB GPU?

Yes. A Tesla V100 SXM2 16 GB with 16 GB runs it at IQ4_XS, using about 13.7 GB and generating roughly 83.9 tokens per second — a tight fit.

Can I run Qwen1.5-14B on a 24 GB GPU?

Yes. A GeForce RTX 5090 D V2 with 24 GB runs it at Q8_0, using about 21.1 GB and generating roughly 40.5 tokens per second — a tight fit.

Is Qwen1.5-14B open source?

Its weights are published, so Qwen1.5-14B 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 Qwen1.5-14B have?

Qwen1.5-14B has 14B parameters. 14B. 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 Qwen1.5-14B?

Qwen1.5-14B was published by Alibaba, based in China, categorised as industry.

When was Qwen1.5-14B released?

Qwen1.5-14B was published in February 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 Qwen1.5-14B used for?

Qwen1.5-14B works in Language, and is recorded as handling chat, Language modeling/generation, Quantitative reasoning, Code generation, Translation. 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.

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