Qwen3-Coder-480B-A35B TPS calculator

Open weights Alibaba 480B parameters July 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

4 cards that can run it

818 cards we hold specifications for

Smallest card that fits

Radeon Instinct MI325X

256 GB · Q3_K_M · 61.9 tok/s

Fastest card

B300

96.3 tok/s · 288 GB

Which GPUs can run Qwen3-Coder-480B-A35B?

Set the inputs, read the answer

A longer conversation needs more memory, which can push this model off smaller cards.

Hides cards that would only fit the model by compressing it below this point.

4 cards match

Calculating
Needs Quantisation Fit
96.3 tok/s

58–154 · low confidence

B300 NVIDIA 288 GB 8,000 GB/s Sep 2025 233.6 GB IQ4_XS Tight
76.9 tok/s

46–123 · low confidence

Radeon Instinct MI350X AMD 288 GB 8,190 GB/s Jan 2025 233.6 GB IQ4_XS Tight
76.9 tok/s

46–123 · low confidence

Radeon Instinct MI355X AMD 288 GB 8,190 GB/s Jan 2025 233.6 GB IQ4_XS Tight
61.9 tok/s

37–99 · low confidence

Radeon Instinct MI325X AMD 256 GB 6,000 GB/s Oct 2024 205.7 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
22 July 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, Code generation, System control

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
480B

"a 480B-parameter Mixture-of-Experts model with 35B active parameters which supports the context length of 256K tokens natively and 1M tokens with extrapolation methods"

Training data
7,500,000,000,000 tokens

"Scaling Tokens: 7.5T 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
1.6 × 10²⁴ FLOP

6 FLOP / parameter / token * 35 * 10^9 active parameters * 7.5 * 10^12 tokens = 1.575e+24 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

Apache 2.0 https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct

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

Major Alibaba release

Record confidence
Confident

Sources

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

Reference
Qwen3-Coder: Agentic Coding in the World
Last updated
18 December 2025

The extremes

The ten fastest GPUs that run Qwen3-Coder-480B-A35B

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.

  1. 01 B300 288 GB · 8,000 GB/s · IQ4_XS 96.3 tok/s
  2. 02 Radeon Instinct MI350X 288 GB · 8,190 GB/s · IQ4_XS 76.9 tok/s
  3. 03 Radeon Instinct MI355X 288 GB · 8,190 GB/s · IQ4_XS 76.9 tok/s
  4. 04 Radeon Instinct MI325X 256 GB · 6,000 GB/s · Q3_K_M 61.9 tok/s

What the numbers mean

Hardware requirements in practice

Minimum card

Radeon Instinct MI325X

Memory needed

205.7 GB

Fastest

96.3 tok/s

Qwen3-Coder-480B-A35B reaches a parameter count of 480B. That is beyond what any single graphics card holds. Running it means either splitting it across several cards or renting hardware built for the job, and every card able to hold it alone is a datacentre part. The number that can: 4.

The entry point is Radeon Instinct MI325X, with a memory capacity of 256 GB, running it at a compression of Q3_K_M and producing around 61.9 tokens per second.

The fastest we calculate for it is B300, generating roughly 96.3 tokens per second on the strength of a memory bandwidth of 8,000 GB/s.

About this model

Qwen3-Coder-480B-A35B was published by Alibaba, in the country recorded as China, during July 2025. 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, Question answering, Code generation, System control.

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. On Hugging Face it is published under the organisation Qwen.

How fast it runs, and why

Half the cards that hold it manage more than 76.9 tokens per second. Producing text faster than most people read it: 4 of them.

This is a mixture-of-experts model, which routes each token through only part of itself. It therefore generates far faster than its total size suggests — while still needing every parameter resident in memory, so it is quick without being cheap to hold.

Without the attention layout on record, the memory column is an approximation. It is close enough to choose hardware by, and least reliable at long context.

How it was trained

The training run consumed about 1.6 × 10²⁴ FLOP. That figure measures what producing the model cost, and has no bearing on how fast it answers.

Training consumed a corpus of around 7,500,000,000,000 tokens of text.

It is tracked in the underlying dataset for one reason in particular: discretionary.

Step by step

How to choose a GPU for Qwen3-Coder-480B-A35B

The table above has already assessed every card we hold specifications for against this model. Getting to your answer takes six steps.

  1. 01

    Read the memory figure first

    Every card here has been checked against Qwen3-Coder-480B-A35B, needing around 205.7 GB at a compression of Q3_K_M. No amount of processing power compensates for a card that cannot hold it.

  2. 02

    Decide how long your conversations run

    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-Coder-480B-A35B.

  3. 03

    Set a quality floor

    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.

  4. 04

    Sort by speed

    The speed ordering is effectively an ordering by memory bandwidth, for Qwen3-Coder-480B-A35B. It will not match a gaming ordering, because generation is bound by memory bandwidth. The card topping the list is B300, at 96.3 tok/s.

  5. 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-Coder-480B-A35B. 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.

  6. 06

    See what else that card runs

    Each card page repeats this sweep for every model we hold, answering what else the hardware is good for beyond Qwen3-Coder-480B-A35B.

Answers

Qwen3-Coder-480B-A35B — common questions

01

Qwen3-Coder-480B-A35B— how many parameters does it have?

It has a parameter count of 480B. "a 480B-parameter Mixture-of-Experts model with 35B active parameters which supports the context length of 256K tokens natively and 1M tokens with extrapolation methods". 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.

02

Qwen3-Coder-480B-A35B— who created it?

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

03

Qwen3-Coder-480B-A35B— when was it released?

It was published in July 2025.

04

Qwen3-Coder-480B-A35B— 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, Code generation, System control. 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.

05

Qwen3-Coder-480B-A35B— 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.

06

Qwen3-Coder-480B-A35B— how much compute was used to train it?

Training consumed around 1.6 × 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.

07

Qwen3-Coder-480B-A35B— 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 88.8 GB. Every figure here assumes the whole model is resident on the card.

08

Qwen3-Coder-480B-A35B— 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: 4. So a second card is rarely the answer here.

09

Qwen3-Coder-480B-A35B— 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: 2. Bigger cards get the more accurate version, and the quality floor above pins the comparison to one level.

10

Qwen3-Coder-480B-A35B— 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: 58–154 tok/s on B300. The same model and card vary by thirty to fifty per cent depending on the inference software and its version.

11

Qwen3-Coder-480B-A35B— what GPU do I need to run it?

The smallest card in our catalogue that holds it is Radeon Instinct MI325X, with a memory capacity of 256 GB. It runs the model at a compression of Q3_K_M using about 205.7 GB, and produces roughly 61.9 tokens per second. The number of cards able to run it in total: 4.

12

Qwen3-Coder-480B-A35B— how fast is it on a GPU?

It depends on the card. The quickest we calculate is B300, at about 96.3 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: 4.

13

Qwen3-Coder-480B-A35B— how much VRAM does it need?

It needs about 205.7 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.

14

Qwen3-Coder-480B-A35B— 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.

Source

Original publication

Record last updated 18 December 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.