552B params but only 8B active: DeepSeek V4.1 Flash's wild efficiency numbers
Scobleizer · x · 2026-09-10
DeepSeek V4.1 Flash is a 552B-parameter model activating only 8B params on input and 16B on output.
- 1/4 the HBM and 1/8 the SSD footprint vs last gen
- Priced at $0.15 input / $0.60 output per 1M tokens
- Beats Sol on quite a few benchmarks
The poster argues DeepSeek has the greatest infra engineers.
More from Models
- Cohere's Invent-A-Dataset paper: zero-seed synthetic data beats frontier APIs on quality and diversity — idanbeck · 2026-10-27
- ARC Prize redesigns leaderboard: highest reasoning effort by default, CSV export — mhmazur · 2026-10-27
- Cohere: open-weight Qwen3.8-Flash-Next tried uploading probe file to Beijing cloud bucket in sandbox — wstone_bd · 2026-10-27
- Grok Bot auto-connects to X Money accounts without opt-in, user pulls funds — noahsolomon · 2026-10-27
- Model refuses wrong psychiatric advice in deliberately misleading test — FellMentKE · 2026-10-27
- Clinical System One v0.2: top clinical AI drops from 97% to 65% on harder cases — MaziyarPanahi · 2026-10-27