Qwen3.5 397B-A17B TPS calculator

Open weights Alibaba 397B parameters February 2026

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

6 of 818 cards that can run it

Smallest card that fits

Radeon Instinct MI300X

192 GB · Q3_K_M · 66.4 tok/s

Fastest card

B300

109 tok/s · 288 GB

Which GPUs can run Qwen3.5 397B-A17B?

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

6 cards match

Calculating

					Needs	Quantisation	Fit
109 tok/s 66–175 · low confidence	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	213.2 GB	Q4_K_M	Comfortable
87.4 tok/s 52–140 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	213.2 GB	Q4_K_M	Comfortable
87.4 tok/s 52–140 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	213.2 GB	Q4_K_M	Comfortable
66.4 tok/s 40–106 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	167.0 GB	Q3_K_M	Tight
66.4 tok/s 40–106 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	167.0 GB	Q3_K_M	Tight
64.0 tok/s 38–102 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	213.2 GB	Q4_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: 13 February 2026

What it does

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

Domain: Language, Vision
Task: Language modeling/generation, Vision-language 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: 397B
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)
Hugging Face: Qwen

How it is classified

Labels the source dataset applies when tracking notable models, and how confident it is in the entry.

Why it is tracked: Discretionary
Record confidence: Likely

Sources

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

Reference: Qwen3.5: Towards Native Multimodal Agents
Last updated: 8 April 2026

The extremes

The ten fastest GPUs for Qwen3.5 397B-A17B

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 Qwen3.5 397B-A17B

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

Hardware requirements in practice

Minimum card

Radeon Instinct MI300X

Memory needed

167.0 GB

Fastest

109 tok/s

At 397B parameters, Qwen3.5 397B-A17B is beyond what any single graphics card holds. Running it means either splitting it across several cards or renting hardware built for the job — 6 of the cards we track can hold it on their own, and all of them are datacentre parts.

The entry point is the Radeon Instinct MI300X: 192 GB of memory, Q3_K_M compression, roughly 66.4 tokens per second.

At the other end, a B300 generates roughly 109 tokens per second on it, on the strength of 8,000 GB/s of memory bandwidth.

Background

Qwen3.5 397B-A17B was published by Alibaba, in China, in February 2026. It comes out of industry.

It works in Language, Vision, and is recorded as doing language modeling/generation, Vision-language generation.

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

Reading the throughput figures

Half the cards that hold it manage more than 76.9 tokens per second, and 6 exceed reading speed outright.

Mixture-of-experts routing is why the speeds here look high for the parameter count. Only a fraction is read per token, but the whole thing has to be loaded.

Memory here is estimated from size rather than computed from the architecture, which is not recorded for this model — the numbers are indicative rather than exact.

Training and provenance

Its inclusion criterion is discretionary.

Step by step

How to choose a GPU for Qwen3.5 397B-A17B

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

The table lists every card that can hold Qwen3.5 397B-A17B — around 167.0 GB at Q3_K_M. That figure, not the card's headline performance, is what decides whether it runs.
02

Set the context length you will work at

The conversation occupies memory too, and grows as it goes. Set the slider to the length you expect: at long context Qwen3.5 397B-A17B can slip off a card that handles short questions easily.
03

Decide how much compression you will accept

Compression is what makes Qwen3.5 397B-A17B fit smaller cards, at some cost in accuracy — Q3_K_M on the smallest card that fits. A minimum quality removes the ones that go too far.
04

Sort by speed

Sort by speed to see how cards rank for Qwen3.5 397B-A17B. It will not match a gaming ordering — generation is bound by memory bandwidth, which is why the B300 tops it at 109 tok/s.
05

Check the fit verdict before buying

A tight fit runs Qwen3.5 397B-A17B but leaves nothing spare for a longer conversation; comfortable has headroom. If you expect to grow the context, buy for comfortable.
06

See what else that card runs

Each card page repeats this sweep for every model we hold. It answers what else the hardware is good for, beyond Qwen3.5 397B-A17B.

Answers

Qwen3.5 397B-A17B — common questions

Where can I download Qwen3.5 397B-A17B?

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 Qwen3.5 397B-A17B if it does not fit in my GPU?

It can be split between the card and system memory, but Qwen3.5 397B-A17B generates painfully slowly that way — the nearest miss we calculate is short by 51.2 GB. Nothing on this page assumes offloading.

Would two GPUs run Qwen3.5 397B-A17B faster?

A second card roughly doubles the memory available but not the generation rate. With 6 cards already able to run Qwen3.5 397B-A17B alone, the case for pairing is weak.

Why does the quantisation differ between cards for Qwen3.5 397B-A17B?

Because capacity varies, so does how hard Qwen3.5 397B-A17B has to be squeezed — 2 distinct levels appear in the table above. Set a minimum quality to compare at one.

How accurate are these Qwen3.5 397B-A17B speed estimates?

They are calculated from specifications rather than measured, and each carries a range — 66–175 tok/s on the B300, 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 Qwen3.5 397B-A17B?

The smallest card in our catalogue that holds Qwen3.5 397B-A17B is the Radeon Instinct MI300X, with 192 GB of memory. It runs the model at Q3_K_M using about 167.0 GB, and produces roughly 66.4 tokens per second. 6 cards in total can run it.

How fast is Qwen3.5 397B-A17B on a GPU?

It depends on the card. The quickest we calculate is a B300 at about 109 tokens per second; the slowest that still runs it manages considerably less. Reading speed is around ten tokens per second, and 6 of the cards that can run Qwen3.5 397B-A17B clear that.

How much VRAM does Qwen3.5 397B-A17B need?

About 167.0 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 Qwen3.5 397B-A17B open source?

Its weights are published, so Qwen3.5 397B-A17B 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 Qwen3.5 397B-A17B have?

Qwen3.5 397B-A17B has 397B parameters. "it comprises 397 billion total 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 Qwen3.5 397B-A17B?

Qwen3.5 397B-A17B was published by Alibaba, based in China, categorised as industry.

When was Qwen3.5 397B-A17B released?

Qwen3.5 397B-A17B was published in February 2026.

What is Qwen3.5 397B-A17B used for?

Qwen3.5 397B-A17B works in Language, Vision, and is recorded as handling language modeling/generation, Vision-language generation. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.

Source

Original publication

Record last updated 8 April 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