Qwen2.5 Instruct (7B) TPS calculator

Open weights Alibaba 7.6B parameters September 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

589 cards that can run it

818 cards we hold specifications for

Smallest card that fits

Tesla K20c

5 GB · Q3_K_M · 26.6 tok/s

Fastest card

B200

445 tok/s · 180 GB

Which GPUs can run Qwen2.5 Instruct (7B)?

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

589 cards match

Calculating

					Needs	Quantisation	Fit
445 tok/s 378–534	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	8.8 GB	Q8_0	Comfortable
445 tok/s 378–534	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	8.8 GB	Q8_0	Comfortable
356 tok/s 213–569 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	8.8 GB	Q8_0	Comfortable
356 tok/s 213–569 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	8.8 GB	Q8_0	Comfortable
284 tok/s 171–455 · low confidence	Radeon Instinct MI300 AMD	128 GB	6,550 GB/s	Jan 2023	8.8 GB	Q8_0	Comfortable
272 tok/s 231–327	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	8.8 GB	Q8_0	Comfortable
272 tok/s 231–327	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	8.8 GB	Q8_0	Comfortable
260 tok/s 156–417 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	8.8 GB	Q8_0	Comfortable
231 tok/s 139–370 · low confidence	Radeon Instinct MI300A AMD	128 GB	5,325 GB/s	Dec 2023	8.8 GB	Q8_0	Comfortable
231 tok/s 139–370 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	8.8 GB	Q8_0	Comfortable
231 tok/s 139–370 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	8.8 GB	Q8_0	Comfortable
219 tok/s 186–263	H100 NVL 94 GB NVIDIA	94 GB	3,940 GB/s	Mar 2023	8.8 GB	Q8_0	Comfortable
187 tok/s 159–224	H100 PCIe 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	8.8 GB	Q8_0	Comfortable
187 tok/s 159–224	H100 SXM5 80 GB NVIDIA	80 GB	3,360 GB/s	Oct 2022	8.8 GB	Q8_0	Comfortable
187 tok/s 159–224	H100 SXM5 94 GB NVIDIA	94 GB	3,360 GB/s	Mar 2023	8.8 GB	Q8_0	Comfortable
187 tok/s 159–224	H100 SXM5 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	8.8 GB	Q8_0	Comfortable
187 tok/s 159–224	H800 SXM5 NVIDIA	80 GB	3,360 GB/s	Mar 2023	8.8 GB	Q8_0	Comfortable
142 tok/s 85–228 · low confidence	Radeon Instinct MI250 AMD	128 GB	3,280 GB/s	Nov 2021	8.8 GB	Q8_0	Comfortable
142 tok/s 85–228 · low confidence	Radeon Instinct MI250X AMD	128 GB	3,280 GB/s	Nov 2021	8.8 GB	Q8_0	Comfortable
120 tok/s 102–145	CMP 170HX 8 GB NVIDIA	8 GB	1,490 GB/s	Sep 2021	7.0 GB	Q6_K	Tight
119 tok/s 71–190 · low confidence	Data Center GPU Max 1550 Intel	128 GB	3,280 GB/s	Jan 2023	8.8 GB	Q8_0	Comfortable
116 tok/s 70–186 · low confidence	Data Center GPU Max Subsystem Intel	128 GB	3,210 GB/s	Jan 2023	8.8 GB	Q8_0	Comfortable
114 tok/s 97–136	A100 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Nov 2020	8.8 GB	Q8_0	Comfortable
114 tok/s 97–136	A100X NVIDIA	80 GB	2,040 GB/s	Jun 2021	8.8 GB	Q8_0	Comfortable
114 tok/s 97–136	A800 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Aug 2022	8.8 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: 19 September 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: Code generation, Code autocompletion, Quantitative reasoning, Question answering, Language modeling/generation
Base model: Qwen2.5-7B

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: 7.6B
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: Qwen2.5: A Party of Foundation Models!
Last updated: 11 February 2026

The extremes

The ten fastest GPUs that run Qwen2.5 Instruct (7B)

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 Qwen2.5 Instruct (7B)

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

Tesla K20c

Memory needed

4.4 GB

Fastest

445 tok/s

Qwen2.5 Instruct (7B) is small enough at 7.6B parameters that hardware is rarely the obstacle — 589 of the cards we track can run it, including cards several years old.

At the low end, a Tesla K20c handles it — 5 GB, at Q3_K_M, for about 26.6 tokens per second.

At the other end, a B200 generates roughly 445 tokens per second on it, on the strength of 8,000 GB/s of memory bandwidth.

About this model

Qwen2.5 Instruct (7B) was published by Alibaba, in China, in September 2024. The organisation is categorised as industry.

It works in Language, and is recorded as doing code generation, Code autocompletion, Quantitative reasoning, Question answering, Language modeling/generation.

It is derived from Qwen2.5-7B rather than trained from scratch, which is the usual way a specialised model is produced.

Published weights mean the model runs on your machine rather than someone else's, which is what makes the hardware question below answerable at all. It is published under the Qwen organisation on Hugging Face.

How fast it runs, and why

The median result is around 24.0 tokens per second; 557 cards produce text faster than most people read it.

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.

Its attention layout is on file, so the memory figures are computed exactly rather than approximated.

Step by step

How to choose a GPU for Qwen2.5 Instruct (7B)

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

Every card here has been checked against Qwen2.5 Instruct (7B) — around 4.4 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

The conversation occupies memory too, and grows as it goes. Set the slider to the length you expect: at long context Qwen2.5 Instruct (7B) can slip off a card that handles short questions easily.
03

Set a quality floor

The quantisation column varies by card, because a bigger card holds a more accurate copy of Qwen2.5 Instruct (7B) — Q3_K_M on the smallest card that fits. Set a floor to hold the comparison at one level.
04

Rank by throughput rather than spec sheet

Sort by speed to see how cards rank for Qwen2.5 Instruct (7B). It will not match a gaming ordering — generation is bound by memory bandwidth, which is why the B200 tops it at 445 tok/s.
05

Check the fit verdict before buying

The fit column separates cards that just manage Qwen2.5 Instruct (7B) from those with room to spare. Buy for the second if the context might grow.
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 Qwen2.5 Instruct (7B) is settled.

Answers

Qwen2.5 Instruct (7B) — common questions

How accurate are these Qwen2.5 Instruct (7B) speed estimates?

These are estimates with real error bars. The fastest result here, 378–534 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 Qwen2.5 Instruct (7B)?

The smallest card in our catalogue that holds Qwen2.5 Instruct (7B) is the Tesla K20c, with 5 GB of memory. It runs the model at Q3_K_M using about 4.4 GB, and produces roughly 26.6 tokens per second. 589 cards in total can run it.

How fast is Qwen2.5 Instruct (7B) on a GPU?

It depends on the card. The quickest we calculate is a B200 at about 445 tokens per second; the slowest that still runs it manages considerably less. Reading speed is around ten tokens per second, and 557 of the cards that can run Qwen2.5 Instruct (7B) clear that.

How much VRAM does Qwen2.5 Instruct (7B) need?

About 4.4 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.

Can I run Qwen2.5 Instruct (7B) on a 8 GB GPU?

Yes. A CMP 170HX 8 GB with 8 GB runs it at Q6_K, using about 7.0 GB and generating roughly 120 tokens per second — a tight fit.

Can I run Qwen2.5 Instruct (7B) on a 12 GB GPU?

Yes. A GeForce RTX 3080 Ti with 12 GB runs it at Q8_0, using about 8.8 GB and generating roughly 50.8 tokens per second — a comfortable fit.

Can I run Qwen2.5 Instruct (7B) on a 16 GB GPU?

Yes. A Tesla V100 SXM2 16 GB with 16 GB runs it at Q8_0, using about 8.8 GB and generating roughly 62.9 tokens per second — a comfortable fit.

Can I run Qwen2.5 Instruct (7B) on a 24 GB GPU?

Yes. A GeForce RTX 5090 D V2 with 24 GB runs it at Q8_0, using about 8.8 GB and generating roughly 74.6 tokens per second — a comfortable fit.

Is Qwen2.5 Instruct (7B) open source?

Its weights are published, so Qwen2.5 Instruct (7B) 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 Qwen2.5 Instruct (7B) have?

Qwen2.5 Instruct (7B) has 7.6B 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 Qwen2.5 Instruct (7B)?

Qwen2.5 Instruct (7B) was published by Alibaba, based in China, categorised as industry.

When was Qwen2.5 Instruct (7B) released?

Qwen2.5 Instruct (7B) was published in September 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 Qwen2.5 Instruct (7B) used for?

Qwen2.5 Instruct (7B) works in Language, and is recorded as handling code generation, Code autocompletion, Quantitative reasoning, Question answering, Language modeling/generation. These are the areas it was designed around; they describe intent rather than a hard boundary.

Where can I download Qwen2.5 Instruct (7B)?

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 Qwen2.5 Instruct (7B) 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 Qwen2.5 Instruct (7B) is rarely worth using — the nearest miss we calculate is short by 1.7 GB. Every figure here assumes the whole model is on the card.

Would two GPUs run Qwen2.5 Instruct (7B) faster?

Capacity adds across cards; throughput does not. Since 589 of the cards we track already hold Qwen2.5 Instruct (7B) on their own, a second card is rarely the answer here.

Why does the quantisation differ between cards for Qwen2.5 Instruct (7B)?

Each card is shown running the least-compressed copy it can hold, and Qwen2.5 Instruct (7B) appears at 4 different compression levels across the cards that fit it. Bigger cards get the more accurate version.

Source

Original publication

Record last updated 11 February 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