Show HN: oMLX – SSD-backed KV cache cuts coding agent TTFT from 90s to 1s on Mac (github.com) 4 pts| 1 day ago | 1 comment
Show HN: oMLX – coding agents on local LLMs without the painful reprefill (github.com) 3 pts| 9 days ago | discuss
Show HN: oMLX – Native Mac inference server that persists KV cache to SSD (github.com) 1 pts| 14 days ago | discuss
