PrismML ships Ternary Bonsai 2 at 2B-27B: 430MB 2B runs 500 tok/s in-browser via WebGPU
victormustar · x · 2026-10-16
PrismML released more Ternary Bonsai 2 open-source models on Hugging Face in 2B, 4B, 9B and 27B sizes. At 1.8 bits per weight, the 2B LM weights are just 430MB and 4B about 950MB (plus 365MB for 8-bit vision weights). A tester reports the 2B hits up to 500 tok/s on an M4 Max entirely in the browser using custom WebGPU kernels, calling it a big day for open-source and local agentic AI.
Related event: PrismML open-sources ternary Bonsai 2 models, 2B runs in browser at 0.43GB(8 posts)→
More from Infra
- Google's Willow chip cuts quantum errors 40x, raising Q-Day concerns for Bitcoin — jamestagg · 2026-10-16
- Vibe Coding a Data Pipeline Is Easy; Running It at Billions of Rows Is Not — Zachly · 2026-10-16
- Large data centers employ only ~50-150 permanent on-site staff, Microsoft says — brezina · 2026-10-16
- Prediction: Opus 5.5-level models on laptops by 2027, backed by Qwen 27B data — cephaloform · 2026-10-16
- Oracle down 12% in a week, nearly 50% off June high as OpenAI exposure spooks market — alvelda · 2026-10-16
- US data center moratoriums top 400 — an AI bull explains why they're actually good for AI — kevinsxu · 2026-10-16