Unverified50% confidenceBenchmarkExact time
A model with approximately 27B parameters achieved a score of 52 running on a laptop, demonstrating that high-quality models are penetrating edge and lightweight devices.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
9/1/2026
First Seen
Valid until: 11/30/2026
Sources
Related Entities
Related Claims
UnverifiedThe MiniCPM series achieves performance close to 7B and even 13B models on multiple benchmarks with a parameter count at the 2B–4B level69% similarUnverified研究表明当模型参数规模达到3B以上时，1.58-bit模型在多项基准测试中表现可接近甚至匹配同等规模的全精度模型68% similarUnverified对于7B至13B参数级别的模型，4-bit量化后的输出质量与全精度版本差异很小66% similarUnverifiedFrom the dimension of instruction following, the 27B local model performs closer to the user's original intent than the flagship Opus, but this may simply be because the boundary of its inferential capability is more conservative.66% similarUnverified在27B混合架构、4B稠密模型、36B MoE三类模型上以8k上下文测试，Prefill阶段性能无变化，Decode阶段打补丁后快约1.4%65% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/839302API
curl https://kongchang.com/api/v1/knowledge/claims/839302MCP
get_claim(id=839302)