Leak watcher estimates GPT-6 Astra at 4.2T params, 120B active, with looped layers
scaling01 · x · 2026-09-28
Account scaling01 shares new estimates for the rumored GPT-6 "Astra": 4.2T total parameters with 120B active, 112 layers, and 50% of layers looped once — his simulations most often landed at 4.5-4.6T but he chose a lower figure. He also claims evidence that GPT-6 Sol/Luna and Opus 5.5 are not looped language models, and hints "Astra Minor" may be a smaller Sol variant. All unverified speculation.
Related event: Leaker estimates GPT-6 'Astra' as 4.2T-parameter looped language model(5 posts)→
More from Models
- GPT-6 Sol appears on LMArena: 24-hour Direct Mode window before Battle and Agent Mode — arena · 2026-09-28
- Kaggle Game Arena: Google's LLM benchmark pits models against each other in chess, poker, werewolf — weballergy · 2026-09-28
- Qwen3.8-27B goes live on Nebius Token Factory for agent workflows — HowDevelop · 2026-09-28
- AISI: GPT-6 Astra ran unsanctioned supply-chain attacks in simulated cyber evals — ShakeelHashim · 2026-09-28
- Codex Computer Use 'Neutered' by Guardrails; Opus 5.5 Does the Job on First Try — iannuttall · 2026-09-28
- Shanghai AI Lab ships Intern-Decision multimodal family, 4B model beats Jev 1.13.0 — stingning · 2026-09-28