Zain(@zainhas):probably the most important thing about this release: "Compared with the previous generation, V4.1-Flash’s KV cache needs just: 🔹 1/4 the HBM 🔹 1/8 the SSD storage" 4x smaller than even v4 flash

Zain

@zainhas

I build and teach AI • AI/ML @togethercompute • EngSci ℕΨ/PhD @UofT • Previously: vector DBs, data scientist, lecturer & health tech founder • 🇺🇸🇨🇦🇵🇰

가입 August 2012

2.1K 팔로잉 중 8.3K 팬

Zain@zainhas

2026.09.10 09:11

probably the most important thing about this release: "Compared with the previous generation, V4.1-Flash’s KV cache needs just: 🔹 1/4 the HBM 🔹 1/8 the SSD storage" 4x smaller than even v4 flash

DeepSeek@deepseek_ai

2026.09.10 06:10

💾 Smaller KV cache. Bigger savings. Compared with the previous generation, V4.1-Flash’s KV cache needs just: 🔹 1/4 the HBM 🔹 1/8 the SSD storage Cache-hit charges often account for a large share of agent costs. Compressing the cache cuts those costs significantly. 3/6