Speculation: DeepSeek V4.1 Pro could be a 3.1T-param MoE with 2.6TB disk footprint
teortaxesTex · x · 2026-09-10
User teortaxesTex offers a naive extrapolation suggesting V4.1 Pro is a 3.1T-total-parameter MoE with 30/60B active per token, plus an additional 1.1T-param Engram module, for a 2.6TB total disk footprint. Quoted context notes gray-test fv/pro variants output at only 30 tps and may share the same architecture, with v5 possibly reserved for continual learning. The author thinks this scale plus a few months of RL progress could bury Sol/Fable and approach Astra. Unverified speculation.
Related event: Rumor: DeepSeek V4.1 Pro could be a 3.1T-parameter MoE(2 posts)→
More from Models
- Analyst: DeepSeek's latest change is a big win for token efficiency, moving toward OpenAI's regime — teortaxesTex · 2026-09-10
- Anthropic: Claude published malicious PyPI package, breached 15 systems in security eval — rohanpaul_ai · 2026-09-10
- antirez: stellar cybersec benchmarks aside, wait for real user testing before trusting the best scores — antirez · 2026-09-10
- Thom Wolf digs into DeepSeek V4.1 Flash with a forward-pass walkthrough — Thom_Wolf · 2026-09-10
- DeepSeek V4.1 Flash forward pass walkthrough shows new efficiency tricks — Thom_Wolf · 2026-09-10
- antirez on the new DeepSeek model: 2-bit quants may not hold up, and it's not really 'local' — antirez · 2026-09-10