Pokee AI demos 36B agent model running fully local on Snapdragon X2 Elite with 32GB RAM
Kyrannio · x · 2026-09-25
Pokee AI previewed Pokee-Isaac-fast live on the Snapdragon Summit main stage with Qualcomm: a 36B agent model running fully locally on a Snapdragon X2 Elite device with just 32GB RAM, at roughly 1,000 tok/s prefill and 20 tok/s generation. The team says it's building next-generation models that fit within users' private compute, with more to come.
Related event: Pokee Runs 36B Agent Model Fully On-Device on Snapdragon Laptop(2 posts)→
More from coding & agent
- SkillRL (NeurIPS 2026): 7B model beats GPT-4o by 41% via recursive skill evolution — cihangxie · 2026-09-25
- Weave Code Max offers $50+ of coding model usage for $10/month — ycombinator · 2026-09-25
- Mad science: Jev autopilot lands a plane in a terminal flight simulator — bilawalsidhu · 2026-09-25
- Greptile reviewed 395K PRs at NVIDIA, cutting merge time from 24h to 6h — ycombinator · 2026-09-25
- Open-source Claude skill turns one prompt into stop-motion claymation films in Blender — angrypenguinPNG · 2026-09-25
- Descript launches MCP to edit video from inside Claude, ChatGPT, and Codex — descript · 2026-09-25