release aidev NEEDS REVIEW SIG 1/5

Qwen3.6-35B-A3B MoE multimodal model published

Qwen published Qwen3.6-35B-A3B, a mixture-of-experts model with 35B total parameters and 3B active parameters supporting image-text-to-text (multimodal) tasks. Licensed under Apache 2.0 with endpoint compatibility for SageMaker and Azure deployment.

PUBLISHED2026-04-15
OBSERVED2026-08-11
AGE4mo
SOURCES1
  • Pipeline: image-text-to-text via Transformers
  • Architecture: MoE (35B total, 3B active)
  • Tags: qwen3_5_moe, conversational, eval-results, endpoints_compatible
  • License: Apache-2.0
  • Format: safetensors
  • Deploy: SageMaker, Azure
  • Hosted on Hugging Face under Qwen organisation
capability

COMMUNITY

No curated reactions recorded for this event. Facts and takes are kept in separate layers — community context is added by hand, never blended into the record above.