Unverified50% confidenceBenchmarkExact time
开发者公布在RTX 3050 Laptop（4GB）上微调Llama-3.1-8B的实测结果为训练速度119.6 tok/s，峰值显存3.32 GB
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
8/12/2026
First Seen
Valid until: 11/10/2026
Sources
Related Claims
Unverified实测在RTX 3060（6GB显存）、32GB RAM上运行预量化Krea2 Turbo，1024×1024分辨率8步Euler采样，速度为1.78 s/it，总耗时17.64秒80% similarUnverifiedRTX 5090上Qwen3.6 35B-A3B推理速度达220 token/s，显存占用约23GB73% similarUnverifiedRTX 5090上Qwen3.6 27B模型预填充速度从174提升到253 token/s，显存占用约18GB72% similarUnverifiedRTX 4060生成速度可达GTX 1060的3-5倍72% similarUnverified多机位H.265 10bit 422素材实时预览卡顿的瓶颈往往是硬件解码能力而非显卡算力，RTX40系拥有双NVENC编码器，多路4K导出速度接近翻倍72% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/732848API
curl https://kongchang.com/api/v1/knowledge/claims/732848MCP
get_claim(id=732848)