Qwen3 Next 80B A3B Thinking
Qwen · released Sep 9, 2025 · Qwen/Qwen3-Next-80B-A3B-Thinking
- Type
- Open weightsApache License 2.0
- Params
- 81.3B
- Context
- 262K
3B active per word · about 197K words of context
Our take
Written Aug 3, 2026Qwen3 Next is a thinking model from Alibaba with 81.3 billion total parameters and only 3 billion active per token, available under a permissive Apache licence. It excels at coding workloads and long-context reasoning, though its creative writing scores trail well behind its coding strength.
Choose this for coding tasks where leaderboard scores matter, or for long-context reasoning with a 262,144-token window. It suits cost-sensitive workloads on Alibaba's own hosting, which undercuts other providers on input cost. Skip it if you need image or video input, if creative writing quality is critical, or if you need consistent throughput across providers — speeds vary sixfold between hosts.
The case for it
- Strong measured coding performance within its own benchmark suite: a gap of about 97 points above its creative writing score.
- Dramatic parameter efficiency, with only 3 billion active parameters per token from an 81.3 billion total — a 27:1 ratio.
- Permissive Apache 2.0 licence allows commercial use, fine-tuning and redistribution.
- Cheapest Alibaba tier undercuts other listed providers by more than a third on input cost.
The case against it
- Creative writing lags its own coding strength by a wide margin — the same ~97-point gap.
- Throughput varies sharply by provider, with a sixfold spread between the fastest and slowest tracked host.
- Text-to-text only; no image or video input supported.
How good is it?
IntelligencePuzzles, maths, exam questions
Arena Text (overall)91st of 143 · 1369.3via Thinking
CodingWriting and fixing code on its own
Arena Coding92nd of 143 · 1420.7via Thinking
Arena Coding is the only board that has scored it for this.
AgenticPlanning, calling tools, staying on task
Nobody we watch has scored Qwen3 Next 80B A3B Thinking for this. We would take the rating from Arena Agent (IPS).
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 Next 80B A3B Thinking 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 model6 scoresEvery figure we hold, from 6 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 M2 Max (38-core GPU) · 96 GB
Room to spare. 17.8 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 6 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
- $0.15 in / $1.20 out
- Context served
- 262K
- Throughput
- Not measured
| Provider | In / out per 1M tokens | Context | Throughput | Trains on prompts | Logs prompts | Zero retention |
|---|---|---|---|---|---|---|
| Alibaba Cloud | $0.098 / $0.78 | 131K | 228 tok/s | No | Yesunknown period | Unknown |
| OpenRouter | $0.15 / $1.20 | 262K | not measured | Unknown | Unknown | Unknown |
| Google Vertex AIglobal | $0.15 / $1.20 | 262K | 38 tok/s | No | No | Confirmed |
| Alibaba Cloudfp8 | $0.15 / $1.20 | 131K | 218 tok/s | No | Yesunknown period | Unknown |
| Nebius AI Studiofp8 | $0.15 / $1.20 | 128K | 107 tok/s | No | No | Confirmed |
| Novita AI | $0.15 / $1.50 | 131K | not measured | Unknown | Unknown | Unknown |
Google Vertex AI
Nebius AI Studio
Novita AIAcross the 6 listings we hold: 4 say they do not train on prompts, 0 say they do and 2 do not say. 2 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 |
|---|---|---|---|
| Alibaba Cloud | ✓ | ✓ | ✗ |
| OpenRouter | ✓ | ✓ | ✓ |
| Google Vertex AIglobal | ✓ | ✓ | ✓ |
| Alibaba Cloudfp8 | ✓ | ✓ | ✗ |
| Nebius AI Studiofp8 | ✓ | ✓ | ✓ |
| Novita AI |
Tool calling: 5 of 6 listings say yes, 1 publishes no parameter list. JSON output: 5 of 6 listings say yes, 1 publishes no parameter list. Strict schema: 3 of 6 listings say yes, 2 say no, 1 publishes no parameter list.
When we formed this view
Dates behind this page
Prices last checked 3d 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 6 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 6 listings do not say whether they train on prompts.
- We hold no cached-input rate for any of its listings.
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-Next-80B-A3B-Thinking
- Architecture
- Mixture of experts
- Modality record
- text->text
- Catalogue slug
- qwen-qwen3-next-80b-a3b-thinking