Unverified50% confidenceBenchmarkExact time
THX-01 returns structured answers with calibrated probabilities in a single forward pass; official GPU benchmarks show that a single inference takes approximately 10 milliseconds.
1
Sources
50%
Confidence
Long-term
Relevance
10/12/2026
First Seen
Sources
Related Entities
Related Claims
Unverified参数量在1亿以下的轻量模型经领域数据微调后可达95%以上意图分类准确率，单次推理延迟控制在5-20ms以内70% similarUnverifiedMainstream GPU inference solutions based on the NVIDIA H100 can typically only achieve tens to one or two hundred tokens per second on models of equivalent scale.68% similarVerifiedCalibrated confidence means that when the system gives a score of 0.9, the probability of being correct should be close to 90%.67% similarUnverified在机器学习多种子实验中重复次数通常只有5到10次，样本量极小，正态性假设难以验证，因此 Wilcoxon 检验往往是更保守稳健的选择66% similarUnverifiedA micro CNN may have only thousands to tens of thousands of parameters, with a single inference computation on the order of 1–10 MFLOPs and an inference latency in the millisecond or even sub-millisecond range.66% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1005017API
curl https://kongchang.com/api/v1/knowledge/claims/1005017MCP
get_claim(id=1005017)