code
Qwen3-Coder-Next
Alibaba's open coder model, 80B total and 3B active; offered free in Kiro.
Levelmodel
Classcode
Parameters80B
Context262,144
Released3 Feb 2026
Opennessopen weights permissive
Runs onconsumer GPU
Statusactive
From the model's own page; who made each picture and where it comes from are listed on the Image Credits page.
Benchmark Results
vendor-reported
SWE-bench Procoding
scaffold not statedvendor-reported
44.3
050100
Score in %. Higher is better.
SWE-bench Verifiedcoding
scaffold not statedvendor-reported
70.6
050100
Score in %. Higher is better.
Terminal-Bench 2.0agents and tool use
scaffold not statedvendor-reported
36.2
050100
Score in %. Higher is better.
Where this comes from
Every score names who ran it: vendor-reported, maintainer-run or independent. A rank is shown with the population it was ranked in (gap rule 3).
Identity
- Developer
- Alibaba (Qwen)
- Family
- Qwen3-Coder
- Released
- 3 Feb 2026 sourcesregistry date
- Weights published
- –
- Record checked
- 10 Oct 2026
Where this comes from
Developer and dates from the research notes. Release date is the vendor's public announcement; weights date is when open weights were published.
Architecture and Size
- Architecture
- hybrid Gated DeltaNet plus gated attention hybrid MoE, 512 experts; non-thinking only
- Total parameters
- 80B sources
- Active parameters
- 3B
- Checkpoint parameters
- –
- Context length
- 262,144 tokens
- Input
- text
- Output
- text
Where this comes from
Parameter counts as the developer states them. Where the checkpoint holds a different total, both are shown (register A16).
Openness and Access
- Openness
- open weights permissive
- Licence
- Apache License 2.0 sources
- Access routes
- open weights download
Where this comes from
The licence file governs over registry tags and aggregator labels.
Deployment
- Runs on
- consumer GPU
- Footprint
- T4 estimate; needs memory for 80B weights (unverified).
- Runtimes
- not in the notes
Where this comes from
Deployment tiers and runtimes as named in the notes. Footprint is the notes' figure, not a measurement by AURION.
Indonesia
- Indonesian support
- not stated
- Regional languages
- not in the notes
- Jakarta hosting
- unknown
- Languages
- not in the notes
Where this comes from
Indonesia fields are carried on every model; unknown is an allowed value.
Lineage
The notes record no lineage for this model.
Industry Use Cases
No industry use case links this model.
Links
DeveloperAlibaba (Qwen)big tech, China
Alibaba (Qwen)big tech, ChinaModelQwen3-Coder-NextAlibaba (Qwen), code
Qwen3-Coder-NextAlibaba (Qwen), codeUse Casesnone recorded
Who Runs Itnone recorded
Organisations 1
Sources
- Qwen/Qwen3-Coder-Next , Hugging Face huggingface.co https://huggingface.co/Qwen/Qwen3-Coder-Next
- Models - Docs - Kiro kiro.dev https://kiro.dev/docs/models/
To cite this page: Project AURION, AI Use-Cases Research & Innovation, "Qwen3-Coder-Next", https://aurion.semai.id/models/alibaba-qwen3-coder-next/, records of October 2026.