Released 2026-04-16 · general agent
Deployment evidence
Alibaba Qwen · 35B total · 3B active · 256K tokens
Best-fit scenarios
A comparatively deployable private multimodal agent baseline with strong ecosystem coverage.
Not recommended
- Assuming TP4 equals four production replicas
- Unvalidated parser upgrades in a critical tool loop
Private coding and office assistant
ChinaAPI inferenceThe 35B/3B-active shape and broad serving support make it a practical baseline for controlled workloads.
Visual document and UI understanding
Vendor-statedQwen3.6 is released as a native multimodal model family.
Capability sourceTool-calling agent service
Vendor-statedOfficial serving examples include tool parsing and long-context operation.
Capability sourceOfficial launch / minimum
Evidence COfficial launch shape
Official serving examples use TP4 and 262K context. Smaller quantized short-context shapes exist, but V1 does not call them the official minimum.
200-person team
Evidence EBest v1 benchmark candidate
Use two measured serving replicas as the initial HA design candidate; exact GPUs remain pending load tests.
Commercial API
Evidence EBenchmark required
Scale through replicated workers after measuring prefill-heavy and decode-heavy traffic separately.
Commercial-use check
Apache-2.0
MaaS / hosted service: No model-specific MaaS restriction identified in Apache-2.0.
Attribution: Provide the license and required notices, preserve attribution notices, and mark modified files; trademark rights are not granted.
Known limitations and open questions
- Official TP4 example is a launch shape, not a capacity guarantee
- Tool-call parser issues have been reported for related Qwen3.5 configurations