conv.

All stories
Active · 12h ↳ Antirez/h3.c: MiniMax H3 inference engine for Mac computers

Apple Silicon and macOS VMs: 11–16× Faster LLM Inference with Llama.cpp

7 items289 engagement43 comments Hacker NewsMastodonPress
Apple Silicon and macOS VMs: 11–16× Faster LLM Inference with Llama.cpp
github.com

Conversation activity · last 13 hours peak 3/30m

Peak 3 items in one 30m at Aug 11, 10 AM; 7 items over 13 hours Aug 11, 10:08 AM — no itemsAug 11, 10:38 AM — 3 items · Press 2, Hacker News 1Aug 11, 11:08 AM — no itemsAug 11, 11:38 AM — 1 item · Mastodon 1Aug 11, 12:08 PM — no itemsAug 11, 12:38 PM — no itemsAug 11, 1:08 PM — no itemsAug 11, 1:38 PM — no itemsAug 11, 2:08 PM — no itemsAug 11, 2:38 PM — 1 item · Mastodon 1Aug 11, 3:08 PM — no itemsAug 11, 3:38 PM — 1 item · Mastodon 1Aug 11, 4:08 PM — no itemsAug 11, 4:38 PM — no itemsAug 11, 5:08 PM — no itemsAug 11, 5:38 PM — no itemsAug 11, 6:08 PM — no itemsAug 11, 6:38 PM — no itemsAug 11, 7:08 PM — no itemsAug 11, 7:38 PM — no itemsAug 11, 8:08 PM — no itemsAug 11, 8:38 PM — no itemsAug 11, 9:08 PM — 1 item · Mastodon 1Aug 11, 9:38 PM — no itemsAug 11, 10:08 PM — no itemsAug 11, 10:38 PM — no items 3 items · 10:38 AM
12 PM4 PM8 PMnow · 11:08 PM

Clustered from 7 items across 3 sources. Not yet parsed — the coverage below is the raw record.

Press coverage 2

Social posts 2

More in this narrative