Qwen3-Coder-480B-A35B TPS calculator
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
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
- Training data
- 7,500,000,000,000 tokens
"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"
"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
- How it was established
- Operation counting
6 FLOP / parameter / token * 35 * 10^9 active parameters * 7.5 * 10^12 tokens = 1.575e+24 FLOP`
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
Apache 2.0 https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct
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
- Confident
Major Alibaba release
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 for 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.
The smallest GPUs that still run Qwen3-Coder-480B-A35B
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 MI325X
Memory needed
205.7 GB
Fastest
96.3 tok/s
At 480B parameters, Qwen3-Coder-480B-A35B is beyond what any single graphics card holds. Running it means either splitting it across several cards or renting hardware built for the job — 4 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 MI325X: 256 GB of memory, Q3_K_M compression, roughly 61.9 tokens per second.
A B300 is the fastest we calculate for it: about 96.3 tokens per second, from 8,000 GB/s of memory bandwidth.
About this model
Qwen3-Coder-480B-A35B was published by Alibaba, in China, in July 2025. The organisation is categorised as industry.
It works in Language, and is recorded as doing 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. It is published under the Qwen organisation on Hugging Face.
How fast it runs, and why
Half the cards that hold it manage more than 76.9 tokens per second, and 4 exceed reading speed outright.
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 describes the cost of creating it and has no bearing on how quickly it generates text.
Around 7,500,000,000,000 tokens went into training it.
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.
-
01
Read the memory figure first
Every card here has been checked against Qwen3-Coder-480B-A35B — around 205.7 GB at Q3_K_M. Capacity is the gate — a card either holds it or it does not.
-
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 Qwen3-Coder-480B-A35B stops fitting a card that seemed fine.
-
03
Set a quality floor
The quantisation column varies by card, because a bigger card holds a more accurate copy of Qwen3-Coder-480B-A35B — Q3_K_M on the smallest card that fits. Set a floor to hold the comparison at one level.
-
04
Sort by speed
The speed ordering for Qwen3-Coder-480B-A35B is effectively an ordering by memory bandwidth, which is why the B300 tops it at 96.3 tok/s.
-
05
Read the fit column last
Tight means Qwen3-Coder-480B-A35B loads and works, with no room to raise the context later. Comfortable means you can. The difference matters more than a few tokens per second.
-
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-Coder-480B-A35B.
Answers
Qwen3-Coder-480B-A35B — common questions
How many parameters does Qwen3-Coder-480B-A35B have?
Qwen3-Coder-480B-A35B has 480B parameters. "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.
Who created Qwen3-Coder-480B-A35B?
Qwen3-Coder-480B-A35B was published by Alibaba, based in China, categorised as industry.
When was Qwen3-Coder-480B-A35B released?
Qwen3-Coder-480B-A35B was published in July 2025.
What is Qwen3-Coder-480B-A35B used for?
Qwen3-Coder-480B-A35B works in Language, and is recorded as handling 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.
Where can I download Qwen3-Coder-480B-A35B?
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.
How much compute was used to train Qwen3-Coder-480B-A35B?
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.
Can I run Qwen3-Coder-480B-A35B if it does not fit in my GPU?
It can be split between the card and system memory, but Qwen3-Coder-480B-A35B generates painfully slowly that way — the nearest miss we calculate is short by 88.8 GB. Nothing on this page assumes offloading.
Would two GPUs run Qwen3-Coder-480B-A35B faster?
Two cards buy memory rather than speed. That matters for Qwen3-Coder-480B-A35B only if one card cannot hold it — 4 can, so a second adds little.
Why does the quantisation differ between cards for Qwen3-Coder-480B-A35B?
Because capacity varies, so does how hard Qwen3-Coder-480B-A35B 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-Coder-480B-A35B speed estimates?
Every figure is derived from memory bandwidth and model size, not benchmarked. That is why each is published as a range such as 58–154 tok/s on the B300 rather than a single number.
What GPU do I need to run Qwen3-Coder-480B-A35B?
The smallest card in our catalogue that holds Qwen3-Coder-480B-A35B is the Radeon Instinct MI325X, with 256 GB of memory. It runs the model at Q3_K_M using about 205.7 GB, and produces roughly 61.9 tokens per second. 4 cards in total can run it.
How fast is Qwen3-Coder-480B-A35B on a GPU?
It depends on the card. The quickest we calculate is a 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 4 of the cards that can run Qwen3-Coder-480B-A35B clear that.
How much VRAM does Qwen3-Coder-480B-A35B need?
About 205.7 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-Coder-480B-A35B open source?
Its weights are published, so Qwen3-Coder-480B-A35B 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.
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.