Skip to main content
Updated April 18, 2026 AI Industry News Major Editorial only, no paid placements

Alibaba Open-Sources Qwen3.6-35B-A3B, A Sparse MoE With Only 3B Active Params

Alibaba Open-Sources Qwen3.6-35B-A3B, A Sparse MoE With Only 3B Active Params

Alibaba’s Qwen team shipped Qwen3.6-35B-A3B on April 16, 2026 under Apache 2.0. It’s a sparse Mixture-of-Experts vision-language model with an unusually aggressive expert routing: only 3B parameters activate per token even though the full model holds 35B in weights.

What’s actually in it

Architecture:

  • Total parameters: 35B
  • Active per token: ~3B (via 256 experts, 8 routed + 1 shared per forward pass)
  • Block pattern: 10 blocks of (Gated DeltaNet → MoE) × 1
  • Context: 262,144 native, 1,010,000 extensible via YaRN
  • License: Apache 2.0 (full commercial use permitted)

Practical economics:

  • Zero licensing cost
  • Runs on a single consumer GPU if you have enough VRAM for the full 35B weights (MoE loads all experts, activates few)
  • On Apple Silicon with unified memory, practical for 32GB+ machines
  • Ollama, LM Studio, and vLLM have Day-0 support; AMD Instinct GPUs also shipped Day-0 kernels

Benchmark reality check

A viral claim circulating says Qwen 3.6 “delivers 80% of Opus 4.7’s performance.” That’s approximately correct in aggregate but hides where the gap matters.

CategoryClaude Opus 4.7Qwen 3.6 PlusQwen as % of Opus
Aggregate947782%
Agentic tasks avg74.961.682%
Coding avg72.964.889%
Knowledge tasks68.26697%
MCP Atlas (tool use)77.3%48.2%62%

The honest read: Qwen 3.6 is close on raw knowledge and not-too-far on coding, but Opus 4.7 maintains a real lead on agentic workflows and tool-use-heavy tasks. The 80% headline understates that spread.

Where Qwen wins: Speed (roughly 1.7× faster than Claude on Qwen 3.6 Plus), cost (~15× cheaper per coding-agent conversation, around $0.05 vs $0.75), and openness (Apache 2.0 beats Anthropic API lock-in for regulated or on-prem workloads).

Why this matters for 2026

Open-weight flagship parity with proprietary frontier models was the theme we flagged in the open-source-parity trend. Qwen3.6-35B-A3B, GLM-5.1, Llama 4 Scout, and Gemma 4 together close the raw-capability gap that existed through 2024. What proprietary labs still own is agentic depth, tool use reliability, and multi-step reasoning under pressure. On those dimensions, Claude Opus 4.7 and GPT-5.4 still lead.

For teams building production AI products in April 2026: Qwen 3.6 is now a credible drop-in for a meaningful slice of LLM workloads at much lower cost, with the clear caveat that agentic workflows should still route to Opus or Mythos or GPT-5.4 until the open-weight gap closes further.

Availability

Sources

Sources

Primary and corroborating references used for this news item.

3 cited sources
  1. Qwen3.6 GitHub - QwenLM/Qwen3.6
  2. Qwen Team Open-Sources Qwen3.6-35B-A3B - MarkTechPost
  3. Qwen3.6-35B-A3B on my laptop drew me a better pelican than Claude Opus 4.7 - Simon Willison
Share LinkedIn
Spotted an error or want to share your experience with Alibaba Open-Sources Qwen3.6-35B-A3B, A Sparse MoE With Only 3B Active Params?

Every tool page is re-verified on a recurring cycle, and corrections land faster when readers flag them directly. If you spot a stale fact, a missing capability, or have used Alibaba Open-Sources Qwen3.6-35B-A3B, A Sparse MoE With Only 3B Active Params and want to share what worked or didn't, the editorial desk reviews every message sent through this form.

Email editorial@aipedia.wiki