Ternary Bonsai 2 27B quantized to a 7GB single file, runs on an 8GB GPU
cephaloform · x · 2026-09-19
User quimedesu shows a Japanese pagoda scene generated with Ternary Bonsai 2 27B (Q20) plus the Pi harness: the model ships as a single file — 6.7 GiB on Windows, 7.2GB on Linux/mac — and fits on an 8GB GPU when the VRAM isn't used for video.
More from Models
- Google finally has a SOTA rogue model, and the AI crowd is joking about relief — rao2z · 2026-09-19
- One Model, Three Skills: Programmatic Use, Chat, and Test-Taking Diverge — lateinteraction · 2026-09-19
- Want US frontier lab secrets? Just look at Chinese SOTA models, quips AI insider — gowthami_s · 2026-09-19
- Empirical analysis confirms Claude Opus 5 shows abnormally dark base-model completions — Kyrannio · 2026-09-19
- US products quietly build on Chinese open-weight models as one firm cuts spend by ~100x — generativist · 2026-09-19
- Eval model Jev goes free on Vercel AI Gateway until Sept 25 — cramforce · 2026-09-19