inclusionAI Launches 100B MoE Diffusion Language Model LLaDA2.2-flash

inclusionAI has released LLaDA2.2-flash on Hugging Face, a 100B Mixture-of-Experts diffusion language model designed for AI agents. It supports a 128K context length and introduces edit-based diffusion to enhance multi-turn interactions and tool use.

2026-07-23 ~ 2026-07-24 · 2 related posts

• LLaDA2.2-flash brings 128K context and Levenshtein Editing to agentic diffusion models — pmttyji · 2026-07-23
• LLaDA2.2-flash brings 100B MoE diffusion model with 128K context and Apache 2.0 — QuixiAI · 2026-07-24