Unverified50% confidenceFactExact time
The 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.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
9/17/2026
First Seen
Valid until: 12/16/2026
Sources
Related Entities
Related Claims
Unverified1-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% similarVerifiedINT8 quantization can compress model size to 1/2 to 1/4 of the original.65% similarUnverifiedllama.cpp通过INT4/INT8量化将模型权重压缩至原始大小的25%以下62% similarUnverified压缩技术LLMLingua研究表明可在压缩80%内容的情况下保持模型性能基本稳定60% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/930398API
curl https://kongchang.com/api/v1/knowledge/claims/930398MCP
get_claim(id=930398)