Qwen3-14B TPS calculator

Open weights Alibaba 14.8B parameters April 2025

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

306 cards that can run it

818 cards we hold specifications for

Smallest card that fits

P102-101

10 GB · Q3_K_M · 21.0 tok/s

Fastest card

B200

229 tok/s · 180 GB

Which GPUs can run Qwen3-14B?

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

306 cards match

Calculating

					Needs	Quantisation	Fit
229 tok/s 195–275	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	16.9 GB	Q8_0	Comfortable
229 tok/s 195–275	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	16.9 GB	Q8_0	Comfortable
183 tok/s 110–293 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	16.9 GB	Q8_0	Comfortable
183 tok/s 110–293 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	16.9 GB	Q8_0	Comfortable
146 tok/s 88–234 · low confidence	Radeon Instinct MI300 AMD	128 GB	6,550 GB/s	Jan 2023	16.9 GB	Q8_0	Comfortable
140 tok/s 119–168	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	16.9 GB	Q8_0	Comfortable
140 tok/s 119–168	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	16.9 GB	Q8_0	Comfortable
134 tok/s 80–214 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	16.9 GB	Q8_0	Comfortable
120 tok/s 102–145	CMP 170HX 10 GB NVIDIA	10 GB	1,560 GB/s	Sep 2021	8.3 GB	Q3_K_M	Tight
119 tok/s 71–190 · low confidence	Radeon Instinct MI300A AMD	128 GB	5,325 GB/s	Dec 2023	16.9 GB	Q8_0	Comfortable
119 tok/s 71–190 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	16.9 GB	Q8_0	Comfortable
119 tok/s 71–190 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	16.9 GB	Q8_0	Comfortable
113 tok/s 96–135	H100 NVL 94 GB NVIDIA	94 GB	3,940 GB/s	Mar 2023	16.9 GB	Q8_0	Comfortable
96.2 tok/s 82–115	H100 PCIe 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	16.9 GB	Q8_0	Comfortable
96.2 tok/s 82–115	H100 SXM5 80 GB NVIDIA	80 GB	3,360 GB/s	Oct 2022	16.9 GB	Q8_0	Comfortable
96.2 tok/s 82–115	H100 SXM5 94 GB NVIDIA	94 GB	3,360 GB/s	Mar 2023	16.9 GB	Q8_0	Comfortable
96.2 tok/s 82–115	H100 SXM5 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	16.9 GB	Q8_0	Comfortable
96.2 tok/s 82–115	H800 SXM5 NVIDIA	80 GB	3,360 GB/s	Mar 2023	16.9 GB	Q8_0	Comfortable
73.2 tok/s 44–117 · low confidence	Radeon Instinct MI250 AMD	128 GB	3,280 GB/s	Nov 2021	16.9 GB	Q8_0	Comfortable
73.2 tok/s 44–117 · low confidence	Radeon Instinct MI250X AMD	128 GB	3,280 GB/s	Nov 2021	16.9 GB	Q8_0	Comfortable
61.0 tok/s 37–98 · low confidence	Data Center GPU Max 1550 Intel	128 GB	3,280 GB/s	Jan 2023	16.9 GB	Q8_0	Comfortable
60.3 tok/s 51–72	GeForce RTX 3080 12 GB NVIDIA	12 GB	912 GB/s	Jan 2022	10.0 GB	Q4_K_M	Tight
60.3 tok/s 51–72	GeForce RTX 3080 Ti NVIDIA	12 GB	912 GB/s	May 2021	10.0 GB	Q4_K_M	Tight
59.7 tok/s 36–96 · low confidence	Data Center GPU Max Subsystem Intel	128 GB	3,210 GB/s	Jan 2023	16.9 GB	Q8_0	Comfortable
58.7 tok/s 50–70	CMP 90HX NVIDIA	10 GB	760 GB/s	Jul 2021	8.3 GB	Q3_K_M	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: 29 April 2025

What it does

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

Domain: Language
Task: Language modeling/generation, Question answering, Mathematical reasoning, 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: 14.8B
Training data: tokens
Epochs: 1

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: 3.2 × 10²⁴ 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: Qwen3: Think Deeper, Act Faster
Last updated: 28 November 2025

The extremes

The ten fastest GPUs that run Qwen3-14B

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 Qwen3-14B

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

P102-101

Memory needed

8.3 GB

Fastest

229 tok/s

Qwen3-14B reaches a parameter count of 14.8B. 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: 306.

The least hardware that works is P102-101, with a memory capacity of 10 GB, running it at a compression of Q3_K_M and producing around 21.0 tokens per second.

Top of the range is B200, generating roughly 229 tokens per second on the strength of a memory bandwidth of 8,000 GB/s.

About this model

Qwen3-14B was published by Alibaba, in the country recorded as China, during April 2025. It comes out of an organisation categorised as industry.

It works in the domain of Language, and is recorded as performing the task of language modeling/generation, Question answering, Mathematical reasoning, Quantitative reasoning, Code generation, Translation.

The weights are published, so it can be downloaded and run on your own hardware indefinitely, offline, with no account attached. On Hugging Face it is published under the organisation Qwen.

How fast it runs, and why

Across every card that can run it, the middle of the range sits at 21.4 tokens per second. Exceeding reading speed outright: 266 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

Training it took a computation budget of roughly 3.2 × 10²⁴ FLOP. That figure measures what producing the model cost, and has no bearing on how fast it answers.

Step by step

How to choose a GPU for Qwen3-14B

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

Start from what it actually needs, which is the requirement of Qwen3-14B, needing around 8.3 GB at a compression of Q3_K_M. That figure, not the headline performance of a card, is what decides whether it runs.
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 a card that seemed fine stops fitting Qwen3-14B.
03

Choose how far you will compress it

The quantisation column varies by card, because a bigger card holds a more accurate copy, reaching a compression of Q3_K_M 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

Rank by throughput rather than spec sheet

Ranking by tokens per second follows memory bandwidth rather than core counts, for Qwen3-14B. It will not match a gaming ordering, because generation is bound by memory bandwidth. The card topping the list is B200, at 229 tok/s.
05

Read the fit column last

Tight means it loads and works with no room to raise the context later, in the case of Qwen3-14B. 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 Qwen3-14B.

Answers

Qwen3-14B — common questions

Qwen3-14B— how fast is it on a GPU?

It depends on the card. The quickest we calculate is B200, at about 229 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: 266.

Qwen3-14B— how much VRAM does it need?

It needs about 8.3 GB at a compression of Q3_K_M, 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.

Qwen3-14B— can I run it on a GPU holding 12 GB?

Yes. The card GeForce RTX 3080 Ti, holding 12 GB, runs it at a compression of Q4_K_M, using about 10.0 GB and generating roughly 60.3 tokens per second. The fit is tight.

Qwen3-14B— 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 Q6_K, using about 13.4 GB and generating roughly 47.0 tokens per second. The fit is tight.

Qwen3-14B— 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 16.9 GB and generating roughly 38.4 tokens per second. The fit is comfortable.

Qwen3-14B— 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.

Qwen3-14B— how many parameters does it have?

It has a parameter count of 14.8B. Number of Parameters: 14.8B Number of Paramaters (Non-Embedding): 13.2B Number of Layers: 40 Number of Attention Heads (GQA): 40 for Q and 8 for KV Context Length: 32,768 natively and 131,072 tokens with YaRN. 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.

Qwen3-14B— who created it?

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

Qwen3-14B— when was it released?

It was published in April 2025.

Qwen3-14B— what is it used for?

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

Qwen3-14B— where can I download it?

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

Qwen3-14B— how much compute was used to train it?

Training consumed around 3.2 × 10²⁴ 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.

Qwen3-14B— can I run it if it does not fit in my GPU?

It can be split between the card and system memory, but it generates painfully slowly that way. The nearest miss we calculate falls short by 2.8 GB. Every figure here assumes the whole model is resident on the card.

Qwen3-14B— would two GPUs run it faster?

A second card roughly doubles the memory available but not the generation rate. The number already able to run it alone: 306. So a second card is rarely the answer here.

Qwen3-14B— why does the quantisation differ between cards?

Each card is shown running the least-compressed copy it can hold. The number of distinct compression levels across the cards that fit it: 5. Bigger cards get the more accurate version, and the quality floor above pins the comparison to one level.

Qwen3-14B— how accurate are these speed estimates?

They are calculated from specifications rather than measured, and each carries a range. One example: 195–275 tok/s on B200. The same model and card vary by thirty to fifty per cent depending on the inference software and its version.

Qwen3-14B— what GPU do I need to run it?

The smallest card in our catalogue that holds it is P102-101, with a memory capacity of 10 GB. It runs the model at a compression of Q3_K_M using about 8.3 GB, and produces roughly 21.0 tokens per second. The number of cards able to run it in total: 306.

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