Ternary Bonsai 2 hits Hugging Face: 27B ternary reasoning model under 6GB, runs in browser
cephaloform · x · 2026-09-18
Ternary has released Bonsai 2 on Hugging Face — a 27B reasoning model using ternary weights, built for the agentic era.
Key numbers:
- 9x smaller than FP16 while retaining 98.2% of the intelligence
- Under 6GB, runs 100% locally in the browser via WebGPU
- Available now for anyone to try
A notable showcase of extreme low-bit quantization for local and in-browser deployment.
Related event: PrismML's Ternary Bonsai 2 27B Shrinks to 5.9GB, Retains 98.2% Performance(20 posts)→
More from Infra
- Amazon's $215B capex exceeds $168B operating cash flow, FCF turns -$42B — thealexbanks · 2026-11-02
- BofA: B200 and H100 GPU rental prices hit new highs, up 47% and 31% YTD — TheZachMueller · 2026-11-02
- vikhyat predicts alternating compute oversupply and undersupply on the road to AGI — TheZachMueller · 2026-11-02
- PyTorch Mac downloads hit 3.29M in October, up 20.5% MoM — LysandreJik · 2026-11-02
- CVSS 9.8 ingress-nginx flaw lets unauthenticated attackers get RCE and steal cluster Secrets — evilsocket · 2026-11-02
- RAM prices tripled, so Tesla cut a third of memory from Optimus's brain — aakashgupta · 2026-11-02