LLMfamily
Qwen3.5
Alibaba's Qwen3.5 family, Apache 2.0, hybrid DeltaNet architecture; card claims 201 languages.
Levelfamily
ClassLLM
Parametersnot in the notes
Context262,000
Released2 Mar 2026
Opennessopen weights permissive
Runs onnot in the notes
Statusactive
Benchmark Results
vendor-reportedmaintainer-run
GPQAknowledge and reasoning
GPQA Diamondknowledge and reasoning
MMLU-Proknowledge and reasoning
SEA-HELMSoutheast Asian and Indonesian
77.93 95% CI [-1.29, +1.25]
04080
Score in index. Higher is better.
rank 3, SEA-HELM Indonesian
Qwen3.5-122B-A10Bmaintainer-run
77.93 95% CI [-1.29, +1.25]
rank 3, SEA-HELM Indonesian, open-weight models, average of 2,000 bootstraps
Qwen3.5-35B-A3BCheckpoint Qwen3.5-35B-A3B as listed; release view (data last updated 18 Sep 2026); score is the average of 2000 bootstrapsmaintainer-run
77.55 95% CI [-1.18, +1.21]
SEA-HELM leaderboard, 58 models, Indonesian (ID)
Qwen3.5-122B-A10Bmaintainer-run
74.66 95% CI [-0.64, +0.61]
rank 2, SEA-HELM SEA average, open-weight models
Qwen3.5-9BCheckpoint Qwen3.5-9B as listed; release view (data last updated 18 Sep 2026); score is the average of 2000 bootstrapsmaintainer-run
74.23 95% CI [-1.29, +1.28]
SEA-HELM leaderboard, 58 models, Indonesian (ID)
Qwen3.5-35B-A3BCheckpoint Qwen3.5-35B-A3B as listed; release view (data last updated 18 Sep 2026); score is the average of 2000 bootstrapsmaintainer-run
73.55 95% CI [-0.62, +0.60]
SEA-HELM leaderboard, 58 models, SEA average
Qwen3.5-4BCheckpoint Qwen3.5-4B as listed; release view (data last updated 18 Sep 2026); score is the average of 2000 bootstrapsmaintainer-run
69.66 95% CI [-1.30, +1.32]
SEA-HELM leaderboard, 58 models, Indonesian (ID)
Qwen3.5-9BCheckpoint Qwen3.5-9B as listed; release view (data last updated 18 Sep 2026); score is the average of 2000 bootstrapsmaintainer-run
69.13 95% CI [-0.64, +0.63]
SEA-HELM leaderboard, 58 models, SEA average
Qwen3.5-4BCheckpoint Qwen3.5-4B as listed; release view (data last updated 18 Sep 2026); score is the average of 2000 bootstrapsmaintainer-run
63.82 95% CI [-0.65, +0.64]
04080
Score in score. Higher is better.
SEA-HELM leaderboard, 58 models, SEA average
SWE-bench Verifiedcoding
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).
Lineage
Qwen3.5 small (0.8B, 2B, 4B, 9B) belongs to this familymultimodal LLM2 Mar 2026Qwen3.5-0.8B belongs to this familymultimodal LLM2 Mar 2026800MQwen3.5-2B belongs to this familymultimodal LLM2 Mar 20262BQwen3.5-35B-A3B belongs to this familyLLM2 Mar 202635BQwen3.5-4B belongs to this familymultimodal LLM2 Mar 20264BQwen3.5-9B belongs to this familymultimodal LLM2 Mar 20269BQwen3.5-122B-A10B belongs to this familymultimodal LLMFeb 2026122BQwen3.5-397B-A17B belongs to this familymultimodal LLMFeb 2026397BWhere this comes from
Parent and child relations from model cards, Hugging Face base_model fields and the genealogy tables of the research notes. Confidence and evidence are the notes' own.
R&D Topics
Identity
- Developer
- Alibaba (Qwen)
- Family
- not in the notes
- Released
- 2 Mar 2026 sourcesnotes
- 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 Hybrid Gated DeltaNet plus full attention
- Total parameters
- – sources
- Active parameters
- –
- Checkpoint parameters
- –
- Context length
- 262,000 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
- not in the notes
- Footprint
- not in the notes
- 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.
Industry Use Cases
No industry use case links this model.
Links
DeveloperAlibaba (Qwen)big tech, China
Alibaba (Qwen)big tech, ChinaModelQwen3.5Alibaba (Qwen), LLM
Qwen3.5Alibaba (Qwen), LLMR&D TopicsEfficiency Architectures (MoE, Sparse Attention, Long Context)Open-Weight Frontier Releases as Research Substrate
Use CasesClinical LLM (Open Weights)HealthcareProcess Optimisation and Advanced Process ControlIndustrialTelecom Domain LLMs and BenchmarksTelecomUse cases of models in the same R&D topic; none is recorded for this model itself.
Who Runs It
PT Amman Mineral Nusa Tenggara (AMMAN)In production, 8 Jul 2026MIND IDResearch, 14 Oct 2025
Conch CementIn production, 23 Jun 2025
PT Kalbe Morinaga IndonesiaIn production, Oct 2024+2 moreDeployments of these use cases; none names this model.
PT Amman Mineral Nusa Tenggara (AMMAN)In production, 8 Jul 2026MIND IDResearch, 14 Oct 2025Conch CementIn production, 23 Jun 2025PT Kalbe Morinaga IndonesiaIn production, Oct 2024+2 moreDeployments of these use cases; none names this model.Models 8
Qwen3.5-397B-A17BAlibaba (Qwen), multimodal LLMFamilyQwen3.5-122B-A10BAlibaba (Qwen), multimodal LLMFamilyQwen3.5 small (0.8B, 2B, 4B, 9B)Alibaba (Qwen), multimodal LLMFamilyQwen3.5-0.8BAlibaba (Qwen), multimodal LLMFamilyQwen3.5-2BAlibaba (Qwen), multimodal LLMFamilyQwen3.5-35B-A3BAlibaba (Qwen), LLMFamilyQwen3.5-4BAlibaba (Qwen), multimodal LLMFamilyQwen3.5-9BAlibaba (Qwen), multimodal LLMFamilyOrganisations 1
Sources
- Qwen3.5 - a Qwen Collection huggingface.co https://huggingface.co/collections/Qwen/qwen35
- Qwen 3.5 Small Models: 9B Parameters That Beat 120B rits.shanghai.nyu.edu https://rits.shanghai.nyu.edu/ai/qwen-3-5-small-models-9b-parameters-that-beat-120b
To cite this page: Project AURION, AI Use-Cases Research & Innovation, "Qwen3.5", https://aurion.semai.id/models/alibaba-qwen3-5/, records of October 2026.