LLaDA2.2-flash brings 100B MoE diffusion model with 128K context and Apache 2.0

QuixiAI · x · 2026-07-24

inclusionAI released LLaDA2.2-flash, a 100B MoE diffusion language model aimed at agentic workloads.

The model supports a 128K context window, uses Levenshtein Editing for insert/delete-style parallel decoding, and adds Block Routing plus L-EBPO to improve long-context efficiency. According to the post, it beats Ling-2.6-flash on τ²-Bench, PinchBench, and MCP-Atlas, while delivering 1.7×–2.3× higher throughput across reported tests. The release is under Apache 2.0.

Related event: inclusionAI Launches 100B MoE Diffusion Language Model LLaDA2.2-flash(2 posts)→

Original post →

More from coding & agent

coding & agent channel →