Mentatcurated
Model

Qwen3.5-35B-A3B

An open-weight multimodal mixture-of-experts model from Alibaba's Qwen team: 35B total parameters but only 3B active per token, handling text, image, and video in a 262K-token context.

1 find · high confidence
Accessoss
MakerAlibaba Cloud (Qwen team)
Released2026-02-24
Visit qwen.ai →

The lenses

Scored on its own merits — not rolled up from the finds we publish.

Novelty 3
Impact · breadth 4
Impact · depth 4
Actionable 5
Substance 5
Hype 3

How this connects

Tap a node to open it