Unverified50% confidenceFactExact time
Bonsai 2 is a ternary-quantized large model released by Prism ML, retrained from scratch on a Qwen3-27B base, with an overall file size of approximately 6 GB.
1
Sources
50%
Confidence
Long-term
Relevance
10/4/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThe model file for Ternary Bonsai 2 is less than 6GB.72% similarUnverifiedThe core claim of the Bonsai 2 27B project is to compress the model size to one-ninth of the original while keeping the model's capabilities nearly intact.69% similarUnverified1-bit Bonsai achieves an intelligence density score of 0.53/GB, which is more than 10 times that of the full-precision model and approximately 2.7 times that of the best low-bit alternatives65% similarUnverifiedWithin the Qwen3 series there is a MoE model with a total parameter count of 2.4T and approximately 95B activated parameters, and downloading the model files requires approximately 5TB of storage space.63% similarUnverifiedall-MiniLM-L6-v2 将文本压缩成 384 维稠密向量，模型体积约 80MB，底层基于 BERT 精简变体 MiniLM 通过知识蒸馏训练62% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/973432API
curl https://kongchang.com/api/v1/knowledge/claims/973432MCP
get_claim(id=973432)