Liquid AI's LFM hits 'college graduate' intelligence at 120 tps on a MacBook Pro
JosephJacks_ · x · 2026-11-13
A repost claims Liquid AI's liquid foundation model (LFM) runs at 120 tokens per second on a MacBook Pro while delivering "college graduate intelligence." It's a hands-on impression of local inference speed vs. capability rather than a benchmark result; the specific model version isn't stated in the post.
More from Infra
- Edge0-145B: an open-source 145B-parameter model claiming frontier capabilities on your own computer — BrightCandle · 2026-11-13
- Michael Burry says 'get out' of Nvidia, citing hidden debt and leveraged customer financing — SumitGup · 2026-11-13
- Nvidia's $500B financing backstop with six asset managers has produced zero deals in months — GaryMarcus · 2026-11-13
- After Microsoft outage, open-weight model torrent seeders hit record 30,000 — WolframRvnwlf · 2026-11-13
- AWS disputes outage reports: services 'have been fine', check Health Dashboard — Kyrannio · 2026-11-13
- The math says GPU export controls are working: only a sliver of Nvidia output leaks — bookwormengr · 2026-11-13