DeepSeek V4.1 rumored to run 1M context with only ~1GB KV cache
AIFlow_ML · x · 2026-11-03
An unverified claim circulating on X says DeepSeek V4.1 needs only about 1GB of KV cache at 1M-token context — an unreal level of optimization, if true. No official release of V4.1 has been announced.
More from Models
- GPT-6 Astra edits 0.016% of Qwen3.5-0.8B weights, boosting math up to 6x with no training — _lewtun · 2026-11-03
- Alignment debate: treat AI as allies—slow down and stop deceiving them — davidmanheim · 2026-11-03
- Alleged 14T Anthropic "numbat" leak debunked: weights regenerate from name-seeded random noise — djcroman · 2026-11-03
- Altman: Next GPT Solved Navier-Stokes With 10,000 Agents Working 4 Days Straight — DeryaTR_ · 2026-11-03
- DeepSeek V5 reportedly planned to be pre-trained on Huawei Ascend chips — hedgehog0 · 2026-11-03
- Loyal Google user: Gemini replaced Assistant and everything got worse — alpinesteveo · 2026-11-03