xAI releases Grok-1 base model weights and architecture under Apache 2.0
Grok-1 base model weights and architecture released under Apache 2.0 — 314B MoE, 25% active per token, in-house JAX+Rust stack
Why it matters
The largest Apache 2.0 open-weight MoE at the time. But as a raw checkpoint without fine-tuning for dialogue, its practical usability was limited
Source — Primary sources first; secondary reports are labelled “Press”
Officialx.aihttps://x.ai/news/grok-osAdded in Week 35, 2026 · See that week