Edge0-145B: frontier AI model runs on your own computer
Spotted 2026-11-13 12:07 (UTC+8) · original event 2026-11-12 · sources: Hacker News, Edge0 (official), Medium, Daily AI Brief · spreading on 4+ platformsHeat score
Rank score: 8540% — where it sits on the charts
Discussion score: 8040% — how much people are talking about it
Cross-platform score: 7020% — how many platforms it spread to
Composite heat score:80.0rank × 0.4 + discussion × 0.4 + cross-platform × 0.2
Why it matters
Frontier models live in the cloud with per-token fees and data leaving your machine; a 145B model that runs on a laptop would put frontier-class coding and agents in private hands - if the vendor's speed claims hold up.The angle
A 145B model that runs on a laptop at 80+ tokens/s with 29GB memory - what it really is (MoE, ~10B active per token) and what to check before believing the benchmarksSuggested format: Short video · for Developers, AI followersEvidence chain
• HN #6, 116 pts/26 cmt (2026-11-13)• Edge0 official blog 2026-11-12: open-source Edge0-145B and Edge0-120B, first open-source on-device 145B model, 29GB peak memory, 80+ tokens/s decode, 1,100+ tokens/s prefill, 128K-256K context• GitHub repo >10,000 stars• weights on Hugging Face• benchmarks are vendor-reported (64.6 DeepSWE, 90.4 GPQA-Diamond)• 2026-11-13 13:07 update: HN #4, 145 pts/37 cmt• 2026-11-13 14:07 update: HN #7, 170 pts/39 cmt• 2026-11-13 15:07 update: HN #9, 193 pts/51 cmt• 2026-11-13 16:07 update: HN #9, 219 pts/59 cmt• 2026-11-13 17:07 update: HN #7, 234 pts/69 cmt