Nex-AGI drops three Apache 2.0 agentic models, topping out at 1.6T params
AdinaYakup · x · 2026-09-08
Nex-AGI released the Nex-N2.5 series on Hugging Face, all under Apache 2.0: a 35B mini model with tool-calling on 2×H100, a 397B hybrid-attention MoE Pro deployable on a single 8×H100 node (weights coming soon), and a 1.6T MoE Max.
Related event: Nex-AGI releases three Apache 2.0 open models up to 1.6T params(2 posts)→
More from Models
- Magic's roadmap: long-context RL, latent-knowledge alignment, then a model release — magicailabs · 2026-09-09
- Thomson Reuters' frontier-competitive legal model Thomson trained for just $450K with curated data — schwarzjn_ · 2026-09-09
- Scoop: Anthropic reportedly prepping fresh Fable-class pretrain to launch before September IPO — teortaxesTex · 2026-09-09
- User claims GPT-6 'Astra' is a step-function leap in generality, effectively AGI — brandon_galang · 2026-09-09
- OUI-1: first open-weights Generative UI model hits 71.7% with just 4B params — iamrobotbear · 2026-09-09
- How GPT-6 Astra's computer use works: it rides on the accessibility tree — iamrobotbear · 2026-09-09