← Back to the wire

PrismML — Introducing Bonsai 2 27B: Near-Lossless Compression in a 9x Smaller Footprint

AnnouncementModelSep 17, 2026

PrismML has released Ternary Bonsai 2 27B, a compressed model based on Qwen3.8 27B that retains 98.2% of the full-precision model's aggregate benchmark performance while being more than 9x smaller. The model uses ternary weights with 1.76 effective bits per weight, occupying 5.9GB, and supports a 262K-token context window with multimodal input. It reaches up to 143 tokens/second on an RTX 5090 and is released under Apache 2.0.

Receipt № 19521 source · awaiting confirmation ◐

Evidence

1source· awaiting independent confirmation

No score is assigned. Sources and their independence are shown in the citation chain below.

Citation chain · 1 source

01highPRIMARY
PrismMLCompanyBonsai 27BModelQwen3.8 27BModelTernary Bonsai 2 27BModel
Canonical: https://prismml.com/news/bonsai-2-27b