Qwen-14B TPS calculator

Open weights Alibaba 14B parameters September 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

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 Qwen-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: 28 September 2023
Authors: Jinze Bai, Shuai Bai, Yunfei Chu, Zeyu Cui, Kai Dang, Xiaodong Deng, Yang Fan, Wenbin Ge, Yu Han, Fei Huang, Binyuan Hui, Luo Ji, Mei Li, Junyang Lin, Runji Lin, Dayiheng Liu, Gao Liu, Chengqiang Lu, Keming Lu, Jianxin Ma, Rui Men, Xingzhang Ren, Xuancheng Ren, Chuanqi Tan, Sinan Tan, Jianhong Tu, Peng Wang, Shijie Wang, Wei Wang, Shengguang Wu, Benfeng Xu, Jin Xu, An Yang, Hao Yang, Jian Yang, Sh…

What it does

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

Domain: Language
Task: Language modeling/generation

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: 3,000,000,000,000 tokens
Epochs: 1
Batch size: 4,000,000

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: 2.5 × 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 (restricted use)
Training code: Unreleased

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: 3,775

Sources

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

Reference: Qwen Technical Report
Last updated: 25 May 2026

The extremes

The ten fastest GPUs that run Qwen-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 Qwen-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

What you need to run it

Minimum card

Xeon Phi 7120P

Memory needed

13.7 GB

Fastest

242 tok/s

Qwen-14B reaches a parameter count of 14B. That is small enough that hardware is rarely the obstacle, including on cards several years old. The number of cards we track that can run it: 241.

The least hardware that works is Xeon Phi 7120P, with a memory capacity of 16 GB, running it at a compression of IQ4_XS and producing around 17.0 tokens per second.

Top of the range is B200, generating roughly 242 tokens per second on the strength of a memory bandwidth of 8,000 GB/s.

What this model is

Qwen-14B was published by Alibaba, in the country recorded as China, during September 2023. The publishing organisation is categorised as industry.

It works in the domain of Language, and is recorded as performing the task of language modeling/generation.

Because its weights were released, nothing about running it depends on a provider staying available — it is yours once downloaded.

What decides the speed

Half the cards that hold it manage more than 28.5 tokens per second. Clearing the ten tokens per second that roughly matches reading speed: 220 of them.

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.

Because the architecture is recorded, the memory column is derived rather than estimated.

Training and provenance

Producing it required arithmetic totalling around 2.5 × 10²³ FLOP. That figure measures what producing the model cost, and has no bearing on how fast it answers.

It was trained on a corpus of about 3,000,000,000,000 tokens of text.

Step by step

How to choose a GPU for Qwen-14B

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 Qwen-14B, needing around 13.7 GB at a compression of IQ4_XS. Capacity is the gate — a card either holds it or it does not.
02

Match the context to your actual use

The conversation occupies memory too, and grows as it goes. Set the slider to the length you expect, because at long context a card that handles short questions easily can be dropped by Qwen-14B.
03

Choose how far you will compress it

Compression is what makes a model fit smaller cards, at some cost in accuracy, reaching a compression of IQ4_XS on the smallest card that fits. Setting a minimum quality drops the cards that only manage it by squeezing further than you would want, and holds the comparison at one level.
04

Sort by speed

Sort by speed to see how cards rank for Qwen-14B. It will not match a gaming ordering, because generation is bound by memory bandwidth. The card topping the list is B200, at 242 tok/s.
05

Look at the headroom, not just the fit

A tight fit runs, but leaves nothing spare for a longer conversation, in the case of Qwen-14B. Comfortable means you can grow the context later. That difference matters more than a few tokens per second, so buy for comfortable if you expect to.
06

Check the card from the other side

Following a card through to its own page shows every other model it can hold, which is the question that follows once you have settled on Qwen-14B.

Answers

Qwen-14B — common questions

Qwen-14B— how much VRAM does it need?

It needs about 13.7 GB at a compression of IQ4_XS, 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.

Qwen-14B— can I run it on a GPU holding 16 GB?

Yes. The card Tesla V100 SXM2 16 GB, holding 16 GB, runs it at a compression of IQ4_XS, using about 13.7 GB and generating roughly 83.9 tokens per second. The fit is tight.

Qwen-14B— can I run it on a GPU holding 24 GB?

Yes. The card GeForce RTX 5090 D V2, holding 24 GB, runs it at a compression of Q8_0, using about 21.1 GB and generating roughly 40.5 tokens per second. The fit is tight.

Qwen-14B— is it open source?

Its weights are published, so it 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.

Qwen-14B— how many parameters does it have?

It has a parameter count of 14B. 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.

Qwen-14B— who created it?

It was published by Alibaba, based in China, an organisation categorised as industry.

Qwen-14B— when was it released?

It was published in September 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.

Qwen-14B— what is it used for?

It works in the domain of Language, and is recorded as handling the task of language modeling/generation. 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.

Qwen-14B— where can I download it?

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

Qwen-14B— how much compute was used to train it?

Training consumed around 2.5 × 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.

Qwen-14B— can I run it 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 model is rarely worth using. The nearest miss we calculate falls short by 3.7 GB. Every figure here assumes the whole model is resident on the card.

Qwen-14B— would two GPUs run it faster?

Two cards buy memory rather than speed, which matters only if one card cannot hold it. The number that can: 241. So a second card is rarely the answer here.

Qwen-14B— why does the quantisation differ between cards?

Because capacity varies, so does how hard it has to be squeezed. The number of distinct levels in the table above: 3. Bigger cards get the more accurate version, and the quality floor above pins the comparison to one level.

Qwen-14B— how accurate are these speed estimates?

Every figure is derived from memory bandwidth and model size, not benchmarked, which is why each is published as a range rather than a single number. One example: 206–290 tok/s on B200. The same model and card vary by thirty to fifty per cent depending on the inference software and its version.

Qwen-14B— what GPU do I need to run it?

The smallest card in our catalogue that holds it is Xeon Phi 7120P, with a memory capacity of 16 GB. It runs the model at a compression of IQ4_XS using about 13.7 GB, and produces roughly 17.0 tokens per second. The number of cards able to run it in total: 241.

Qwen-14B— how fast is it on a GPU?

It depends on the card. The quickest we calculate is 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 the number of cards clearing that: 220.

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