Nebius Token Factory
Mini toolsLLaDA2 X
By InclusionAI
LLaDA2.X represents the second generation of LLaDA diffusion LMs, reframing text generation as a diffusion process rather than standard autoregression. The series ranges from mini models to a 100B-parameter LLaDA2.0-flash, and introduces CAP variants that integrate capabilities like code and instruction following. Thanks to parallel decoding, LLaDA2.X can reach hundreds of tokens per second while matching or beating standard LLMs on many benchmarks, making it attractive for latency-sensitive applications.
New
Text
Gen 4
Overview
LLaDA2.X is InclusionAI’s diffusion language model family, scaling to 100B parameters and using parallel decoding to deliver fast, high-quality text generation and code with up to 500+ tokens per second.
About InclusionAI
Inclusion‑AI is a UK-based nonprofit organisation that researches and promotes inclusive and equitable AI systems, focussing on how machine learning tools can better serve under-represented communities and reduce bias.
Website:
inclusion-ai.org
Tools using LLaDA2 X
No tools found for this model yet.
Last updated: February 12, 2026
