Kev 4B: an open-weights decision model with private TEE inference, close to Jev
bgmshana · x · 2026-10-14
bgmshana released Kev 4B, a small, fast and cheap open-weights decision model claimed to be close to Jev, aimed at private inference.
- Powered by dstack and served via Phala Network and Redpill, running in TEEs so prompts and logic stay private
- The screenshot shows a local API example: call jaredpalmer/kev-4b through a TypeSafe SDK systemOne endpoint with a state object and questions to get structured decision answers
- Aimed at developers who want decision-making capability without sending their program logic to third-party model providers
Related event: Open-Source Decision Model Kev-4B Launches with TEE Private Inference(3 posts)→
More from Infra
- RISC-V crypto accelerator SoC gets full place-and-route done with ~$2,000 of LLM tokens — IgorCarron · 2026-10-14
- SK Hynix has struggled with HBM4 back-end issues for over a year, Samsung tipped to lead HBM market next year — zephyr_z9 · 2026-10-14
- Startup Builds $18,000 Local AI Server With 128GB VRAM, Runs 16 Concurrent Sessions — bendee983 · 2026-10-14
- A used dual-RTX-3090 local LLM rig that isn't much faster — why? — jonejy · 2026-10-14
- Photonic Training of a 1B GPT-2 Without Backprop Lands in PNAS — IgorCarron · 2026-10-14
- Xinjiang's 167 GW green power, 16ms to Chongqing: the grid edge in AI race — 96Stats · 2026-10-14