conv.

← The whole story
AI
PrismML releases Ternary Bonsai 2 27B, 9x compressed model retaining 98% performance

Community explores model deployment in browsers and on local hardware

2 Sep 17 5:56 PM · 8d ago · 1 comment · 1 source · development 2 of 4

Developers report successfully running the model in browsers via WebGPU kernels and on consumer hardware including Mac Mini M2 and NVIDIA GPUs, with observed throughputs of 7-8 tokens/second on M2 and 143 tokens/second on RTX 5090.

Community explores model deployment in browsers and on local hardware
prismml.com

“These are small enough that you can run them entirely in the browser”

Aurornis

PrismML Model developer and publisherAurornis Community tester

The whole story articlespostscomments the bright band is this development · numbered dots are the others · click one to jump

Peak 8 pieces in two hours at Sep 17, 4 PM; 50 pieces over 9 days (5 articles · 3 posts · 42 comments) Sep 17, 4 PM — 8 pieces · 3 articles · 1 post · 4 comments — Hacker News 5, Newswires 3Sep 17, 6 PM — 6 pieces · 6 comments — Hacker News 6Sep 17, 8 PM — 5 pieces · 1 post · 4 comments — Hacker News 4, Mastodon 1Sep 17, 10 PM — 5 pieces · 2 articles · 3 comments — Hacker News 3, Newswires 2Sep 18, 12 AM — quietSep 18, 2 AM — 4 pieces · 1 post · 3 comments — Hacker News 2, Lobsters 2Sep 18, 4 AM — 3 pieces · 3 comments — Hacker News 3Sep 18, 6 AM — 1 piece · 1 comment — Lobsters 1Sep 18, 8 AM — 3 pieces · 3 comments — Hacker News 3Sep 18, 10 AM — 2 pieces · 2 comments — Hacker News 1, Lobsters 1Sep 18, 12 PM — quietSep 18, 2 PM — 2 pieces · 2 comments — Lobsters 1, Hacker News 1Sep 18, 4 PM — 2 pieces · 2 comments — Lobsters 2Sep 18, 6 PM — quietSep 18, 8 PM — quietSep 18, 10 PM — 2 pieces · 2 comments — Lobsters 2Sep 19, 12 AM — 2 pieces · 2 comments — Lobsters 2Sep 19, 2 AM — 3 pieces · 3 comments — Lobsters 2, Hacker News 1Sep 19, 4 AM — quietSep 19, 6 AM — quietSep 19, 8 AM — quietSep 19, 10 AM — quietSep 19, 12 PM — 1 piece · 1 comment — Lobsters 1Sep 19, 2 PM — quietSep 19, 4 PM — 1 piece · 1 comment — Hacker News 1Sep 19, 6 PM — quietSep 19, 8 PM — quietSep 19, 10 PM — quietSep 20, 12 AM — quietSep 20, 2 AM — quietSep 20, 4 AM — quietSep 20, 6 AM — quietSep 20, 8 AM — quietSep 20, 10 AM — quietSep 20, 12 PM — quietSep 20, 2 PM — quietSep 20, 4 PM — quietSep 20, 6 PM — quietSep 20, 8 PM — quietSep 20, 10 PM — quietSep 21, 12 AM — quietSep 21, 2 AM — quietSep 21, 4 AM — quietSep 21, 6 AM — quietSep 21, 8 AM — quietSep 21, 10 AM — quietSep 21, 12 PM — quietSep 21, 2 PM — quietSep 21, 4 PM — quietSep 21, 6 PM — quietSep 21, 8 PM — quietSep 21, 10 PM — quietSep 22, 12 AM — quietSep 22, 2 AM — quietSep 22, 4 AM — quietSep 22, 6 AM — quietSep 22, 8 AM — quietSep 22, 10 AM — quietSep 22, 12 PM — quietSep 22, 2 PM — quietSep 22, 4 PM — quietSep 22, 6 PM — quietSep 22, 8 PM — quietSep 22, 10 PM — quietSep 23, 12 AM — quietSep 23, 2 AM — quietSep 23, 4 AM — quietSep 23, 6 AM — quietSep 23, 8 AM — quietSep 23, 10 AM — quietSep 23, 12 PM — quietSep 23, 2 PM — quietSep 23, 4 PM — quietSep 23, 6 PM — quietSep 23, 8 PM — quietSep 23, 10 PM — quietSep 24, 12 AM — quietSep 24, 2 AM — quietSep 24, 4 AM — quietSep 24, 6 AM — quietSep 24, 8 AM — quietSep 24, 10 AM — quietSep 24, 12 PM — quietSep 24, 2 PM — quietSep 24, 4 PM — quietSep 24, 6 PM — quietSep 24, 8 PM — quietSep 24, 10 PM — quietYesterday, 12 AM — quietYesterday, 2 AM — quietYesterday, 4 AM — quietYesterday, 6 AM — quietYesterday, 8 AM — quietYesterday, 10 AM — quietYesterday, 12 PM — quietYesterday, 2 PM — quietYesterday, 4 PM — quietYesterday, 6 PM — quietYesterday, 8 PM — quietYesterday, 10 PM — quietToday, 12 AM — quietToday, 2 AM — quietToday, 4 AM — quietToday, 6 AM — quietToday, 8 AM — quietToday, 10 AM — quietToday, 12 PM — quietToday, 2 PM — quiet 1–4
1–4Community explores model deployment in…
Sep 18Sep 19Sep 20Sep 21Sep 22Sep 23Sep 24yesterdaynow · 4:30 PM ET

What people said 1 voice · verbatim

All 4 developments of PrismML releases Ternary Bonsai 2 27B, 9x compressed model… →

NewswiresHacker NewsMastodonLobsters