Skip to main content

    Alibaba

    Qwen3.6-35B-A3B

    Alibaba's April 16, 2026 Apache 2.0 vision-language model uses a 35B-parameter MoE with 3B active parameters. It supports text, image and video inputs and local deployment. Published weights support 262,144 tokens natively, extensible to 1,010,000 with YaRN.

    262K tokens
    Multimodal
    Pro
    Provider
    Alibaba
    Context
    262K
    Catalog · As of Sep 10, 2026Recent · 1d old
    yno subscription tier
    Pro
    Released
    Apr 16, 2026
    Speed
    Fast
    Reasoning
    Advanced
    Modality
    Multimodal

    Benchmarks

    Quality

    AA Intelligence Index
    25points
    Estimated · As of Aug 11, 2026Stale · 31d old
    GPQA Diamond
    77%
    Estimated · As of Aug 11, 2026Stale · 31d old

    Speed and latency

    Output speed
    105tokens/s
    Estimated · As of Aug 11, 2026Stale · 31d old

    API pricing

    Not available

    AA measurements unavailable

    Indexes use points; evaluations use accuracy percentages. API measurements do not measure yno application performance. Methodology

    Capabilities

    • Open Source
    • MoE
    • Vision
    • Video
    • Local Deployment
    • Multilingual

    Use cases

    • Self-hosted Qwen
    • Apache-2 licensed deployments
    • Local fine-tuning
    • Cost-sensitive inference

    Strengths

    • Apache 2.0 license
    • Efficient MoE
    • Local-deployable
    • Strong multilingual

    Best for

    Teams needing an open-licensed Qwen for local or on-prem use

    Use Qwen3.6-35B-A3B in yno.ai

    No credit card required

    Related models

    Frequently asked

    What is Qwen3.6-35B-A3B?
    Alibaba's April 16, 2026 Apache 2.0 vision-language model uses a 35B-parameter MoE with 3B active parameters. It supports text, image and video inputs and local deployment. Published weights support 262,144 tokens natively, extensible to 1,010,000 with YaRN.
    How much does Qwen3.6-35B-A3B cost in yno.ai?
    Qwen3.6-35B-A3B is available on the Pro tier of yno.ai.
    What can Qwen3.6-35B-A3B do?
    Qwen3.6-35B-A3B is best for Teams needing an open-licensed Qwen for local or on-prem use. Its main capabilities include Open Source, MoE, Vision, Video, Local Deployment, Multilingual.
    How does Qwen3.6-35B-A3B compare to other models?
    Qwen3.6-35B-A3B excels at Apache 2.0 license and is recommended for Self-hosted Qwen, Apache-2 licensed deployments, Local fine-tuning, Cost-sensitive inference. See related models below.
    How do I use Qwen3.6-35B-A3B in yno.ai?
    Sign up for yno.ai, select Qwen3.6-35B-A3B from the model picker, and start chatting.