PrismML ships Bonsai 2 ternary models: 9B fits in 2GB for local AI
gajesh · x · 2026-10-16
PrismML released Bonsai 2, a family of ternary models based on Qwen3.5 sized for everyday devices: 2B (0.43GB), 4B (0.95GB), and 9B (2.0GB). The release focuses on what makes small models useful as local assistants — instruction following, avoiding repetitive loops, and tool calling on mobile. The 9B uses 40% fewer tokens on standard instruction-following and everyday math. Darkbloom is offering day-one support, with 250M free tokens for the first 100 users.
More from Infra
- FT warns of 'Darwin moment' for AI borrowers as CoreWeave bonds sink to distress levels — firstadopter · 2026-10-16
- Phone as interface, home servers as the lab: a two-workflow local AI setup — EAccelerate_42 · 2026-10-16
- "A datacenter is a bank": CoreWeave drama revives calls for算力 supervision — arthurcolle · 2026-10-16
- DOT-MoE: converting dense models into sparse MoE via optimal transport — burkov · 2026-10-16
- Stanford CS336: A 7B model needs 14GB for weights but 84GB to train — stanfordnlp · 2026-10-16
- New NVFP4 trick: compressing block scales saves 45-48% per expert matrix, bit-exact — TheZachMueller · 2026-10-16