Unverified50% confidenceBenchmarkExact time
4Bit量化下模型的基准测试得分通常能保持原始精度的90%-95%
1
Sources
50%
Confidence
Long-term
Relevance
8/27/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedNVFP4量化方案相比BF16基线实现了1.5倍的推理加速，同时在top-1准确率上保留了92%到97%的水平73% similarUnverifiedTop-1% accuracy is a metric for evaluating the output consistency between a quantized model and the original full-precision model, focusing on whether the top 1% of tokens with the highest model confidence are consistent with the full-precision version.71% similarUnverified在GPT-4发布初期，主流模型在GPQA上的准确率约为35-40%，人类领域专家基准线约为65%，随机猜测为25%70% similarUnverified该量化模型相较于BF16全精度版本保留了约77%的准确率69% similarUnverifiedDeveloper Ivan tested version MTP-LX 0.3.5 and achieved a 93.3% accuracy rate on a math benchmark within 5 minutes and 30 seconds.67% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/810111API
curl https://kongchang.com/api/v1/knowledge/claims/810111MCP
get_claim(id=810111)