Qwen3 Coder 480B A35B
Qwen · released Jul 22, 2025 · Qwen/Qwen3-Coder-480B-A35B-Instruct
- Type
- Open weightsApache License 2.0
- Params
- 480B
- Context
- 262K
35B active per word · about 197K words of context
Our take
We have not written a summary of this model yet.
How good is it?
IntelligencePuzzles, maths, exam questions
Arena Text (overall)85th of 143 · 1387.7
CodingWriting and fixing code on its own
Arena Coding69th of 143 · 1456.8
AgenticPlanning, calling tools, staying on task
Qwen3 Coder 480B A35B is not on Arena Agent (IPS), which is where the rating would come from, so there is no rating here. It is on SWE-bench Verified, in 12th of 39 with 69.6.
WritingWe do not rate this
Two boards come close and neither tests writing: Arena Creative Writing asks people which of two replies they prefer, and LiveBench Language tests whether a model understood a passage. So we show where Qwen3 Coder 480B A35B placed and give it no mark out of five.
These tests check whether a model follows instructions — a precondition for all the work above, but not a measure of how well that work is done, which is why they get no rating.
Every published score for this model8 scoresEvery figure we hold, from 8 boards, with who ran it and a link to the source — including the boards no rating above is built on.
Can you run it yourself?
- Fits in memory
- weights load entirely on the card
- Spills to system RAM
- some weights offload; much slower
- Too large
- will not load even with offload
- est
- size is calculated; the verdict could change by 10%
GeForce RTX 4090 · 24 GB
Too large for this card. The weights do not fit even with part of them offloaded to system memory.
Apple M1 Pro (16-core GPU) · 32 GB
Too large for this card. The weights do not fit even with part of them offloaded to system memory.
Comfortable fit
Apple M3 Ultra (80-core GPU) · 512 GB
Room to spare. 70.4 GB spare means a 10% error in the size would not change the answer.
Memory use by level
Against a 24 GB card.
All 3 sizes here are calculated, not measured. We hold no measured file for this model, so each size comes from the parameter count and every verdict above inherits that uncertainty.
Check against your own machine → · All 71 devices, with every size →
Or rent it from someone else
Cheapest of 10 live listings. Picked at the widest standard context we hold, within one quantisation slice, so the numbers beside it are a price one host actually charges.
- per 1M tokens
- $0.30 in / $1.00 out
- Context served
- 262K
- Throughput
- Not measured
| Provider | In / out per 1M tokens | Context | Throughput | Trains on prompts | Logs prompts | Zero retention |
|---|---|---|---|---|---|---|
| OpenRouter | $0.30 / $1.00 | 262K | not measured | Unknown | Unknown | Unknown |
| DeepInfraturbo tierfp4 | $0.30 / $1.00 | 262K | 69 tok/s | No | No | Unknown |
| DeepInfrafp4 | $0.30 / $1.00 | 262K | 32 tok/s | No | No | Unknown |
| CoreWeavebf16 | $1.00 / $1.50 | 262K | 45 tok/s | No | No | Confirmed |
| Venice AIfp8 | $0.35 / $1.50 | 256K | 37 tok/s | No | No | Confirmed |
| Novita AI | $0.38 / $1.55 | 262K | not measured | Unknown | Unknown | Unknown |
| Novita AIfp8 | $0.38 / $1.55 | 262K | 14 tok/s | No | No | Confirmed |
| Google Vertex AIus-south1 | $0.22 / $1.80 | 262K | 25 tok/s | No | No | Confirmed |
| Alibaba Cloudfp8 | $0.97 / $4.88 | 262K | 18 tok/s | No | Yesunknown period | Unknown |
| Alibaba Cloudopensourcefp8 | $0.97 / $4.88 | 262K | 45 tok/s | No | Yesunknown period | Unknown |
DeepInfra
Novita AI
Google Vertex AIAcross the 10 listings we hold: 8 say they do not train on prompts, 0 say they do and 2 do not say. 4 appear in the zero-retention registry we check; the rest are unknown to us rather than confirmed either way.
What each host's API supports
From the parameter list each endpoint publishes. Streaming is omitted: nothing we hold reports it, for any model.
- ✓
- Supported
- ✗
- Not supported
- Not published
- host gave no parameter list
| Provider | Tool calling | JSON output | Strict schema |
|---|---|---|---|
| OpenRouter | ✓ | ✓ | ✓ |
| DeepInfraturbo · fp4 | ✓ | ✓ | ✓ |
| DeepInfrafp4 | ✓ | ✓ | ✓ |
| CoreWeavebf16 | ✓ | ✓ | ✓ |
| Venice AIfp8 | ✓ | ✓ | ✓ |
| Novita AI | |||
| Novita AIfp8 | ✓ | ✓ | ✓ |
| Google Vertex AIus-south1 | ✓ | ✓ | ✓ |
| Alibaba Cloudfp8 | ✓ | ✓ | ✓ |
| Alibaba Cloudopensource · fp8 | ✓ | ✓ | ✓ |
Tool calling: 9 of 10 listings say yes, 1 publishes no parameter list. JSON output: 9 of 10 listings say yes, 1 publishes no parameter list. Strict schema: 9 of 10 listings say yes, 1 publishes no parameter list.
Models people weigh against Qwen3 Coder 480B A35B
When we formed this view
Dates behind this page
Prices last checked 4d ago
What we do not know about this model yet
- We hold no measured file for it, so all 3 sizes on this page are calculated from the parameter count.
- 1 of 10 listings publish no parameter list, so what their API accepts is unknown to us.
- Nothing we hold says whether an endpoint streams, so we do not show it either way.
- 2 of 10 listings do not say whether they train on prompts.
Licence and identifiers
What the licence allowsApache License 2.0, what it allows commercially, and the identifiers you need to pull this model — its Hugging Face repo, our slug and a machine-readable card.
Licence
Apache License 2.0
Fully permissive: commercial use, redistribution, and derivatives allowed. Requires attribution and a copy of the license. Includes an express patent grant.
Identifiers
- Hugging Face
- Qwen/Qwen3-Coder-480B-A35B-Instruct
- Architecture
- Mixture of experts
- Modality record
- text->text
- Catalogue slug
- qwen-qwen3-coder-480b-a35b