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.
More from coding & agent
- Alex Townsend posts 200 open problems in numerical linear algebra for humans and AI agents — IgorCarron · 2026-09-11
- Kimi K2.8 Preview rolls out: near-K3 coding performance, 1M context for all tiers — teortaxesTex · 2026-09-11
- Looking for a classifier of software engineering task shapes to pick models per task — StewartalsopIII · 2026-09-11
- Steal this idea: prompt-to-hardware where agents assemble custom devices — paraschopra · 2026-09-11
- Model Is the Least Interesting Part: A Guide to Six Core AI Architectures from RAG to Multi-Agent — goyalshaliniuk · 2026-09-11
- Non-coder builds layered memory architecture: 20k tokens tracks a year of agent conversations — matteoianni · 2026-09-11