Local Agent trend: JetBrains and Perplexity optimize for on-device inference
ycombinator · x · 2026-08-28
Local deployment trends emerged this week with JetBrains and Perplexity launching local agents based on the 27B Qwen model. The key challenge lies in optimizing agent behavior on consumer hardware. JetBrains found that agents spend most of their time reading, leading Junie Local to adopt the M5 chip for a 40% speed boost in reading tasks. Additionally, tests indicated that the Qwen 3.8B model requires 'thinking' mode enabled for reliable behavior.
More from coding & agent
- Study: AI Coding Agents Are Reshaping PR Vocabulary — ycombinator · 2026-08-28
- Harness launches AI code repository designed for high-volume Agent commits — rseroter · 2026-08-28
- Survey: 72% of Devs Prefer 5x Speed Over 20% Smarter Models — sonic_op · 2026-08-28
- Opinion: Buying Cursor might be one of Elon's smartest moves — prasenx · 2026-08-28
- Artie deploys bespoke Hermes AI agents across teams: sales, design, engineering — Teknium · 2026-08-28
- Ramp enables agents to pay by card, attach receipts, and code transactions — kleffew94 · 2026-08-28