Unverified50% confidenceBenchmarkExact time
A UP host running MiniCPM 2B with an RTX 4080S (16GB VRAM) + 64GB RAM configuration achieved an inference speed of approximately 110 tokens/second in real-world testing
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
9/15/2026
First Seen
Valid until: 12/14/2026
Sources
Related Entities
Related Claims
UnverifiedIn real-world testing on an RTX 3060 (6GB VRAM) with 32GB RAM running the pre-quantized Krea2 Turbo, 1024×1024 resolution with 8-step Euler sampling achieved a speed of 1.78 s/it and a total elapsed time of 17.64 seconds.78% similarVerifiedRTX 4090的理论FP16算力为82.6 TFLOPS，显存带宽为1008 GB/s75% similarUnverified原本需要 A100 80GB 才能完成的 70B 参数模型微调任务，在 Unsloth 优化下可以在消费级 RTX 4090（24GB）上运行74% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/923500API
curl https://kongchang.com/api/v1/knowledge/claims/923500MCP
get_claim(id=923500)