Unverified50% confidenceBenchmarkExact time
The 35B model achieved a pass rate of 90/90 under the constrained context, while the 4B model achieved 72/90.
1
Sources
50%
Confidence
Long-term
Relevance
10/11/2026
First Seen
Sources
Related Entities
Related Claims
Unverified在35B参数模型中GEMM内核往往占据总计算时间的60-80%73% similarUnverifiedThe output quality of 4-bit quantized models can typically reach more than 95% of that of the original model.70% similarUnverifiedWhen the 35B model switched to a wider context, its pass rate plummeted to 46/90, with 43 responses truncated due to a fixed output budget.70% similarUnverifiedH100内存子系统的动态功耗在大模型推理中占比可达整卡功耗的20%～35%69% similarUnverifiedEach token in the GLM series 744B model activates only approximately 40B parameters, accounting for about 5.4% of the total.67% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1000038API
curl https://kongchang.com/api/v1/knowledge/claims/1000038MCP
get_claim(id=1000038)