Unverified50% confidenceBenchmarkExact time
On the COCO dataset, RTMPose-L achieves an AP of 72.3% while reaching inference speeds of hundreds of FPS.
1
Sources
50%
Confidence
Long-term
Relevance
8/8/2026
First Seen
Sources
SAM3+RTMPose零微调解析1950年代工厂影像：基础模型泛化能力实测
Related Claims
UnverifiedRTX 4090相比RTX 3060在推理场景下的实际吞吐量提升约3-4倍65% similarUnverifiedOn the RTX 5090, Muse Glimmer's generation speed increases from 75 tokens per second to 233 tokens per second, a speedup of approximately 3.1×.63% similarUnverifiedOn high-performance laptops, quantized Gemma models can achieve token generation speeds of 20–50 tokens per second; pure CPU inference is approximately 5–15 tokens/second, and INT4 quantization on NVIDIA RTX 4060/4070 can boost inference speed by 3–5 times.63% similarUnverifiedMeta Llama 3的405B参数版本以BF16精度加载需约810GB内存，量化至INT4精度需约200GB61% similarUnverifiedLLaMA-2 70B 总参数约 700 亿均匀分布于 80 层，每层约 8.75 亿参数，FP16 精度下单层约占 1.75GB 显存61% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/709549API
curl https://kongchang.com/api/v1/knowledge/claims/709549MCP
get_claim(id=709549)