Unverified50% confidenceBenchmarkExact time
In the t2va task benchmark at 448×448 resolution with 362 frames, Sage baseline sampling took 12.65 s (17.46 fps), Sol+Spectrum was fastest at 9.64 s (20.96 fps), and Sage+Spectrum was 10.36 s (20.18 fps).
1
Sources
50%
Confidence
Long-term
Relevance
9/11/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedAt FP16 half-precision computation, the RTX 4090 has a theoretical performance of approximately 330 TFLOPS, while the M2 Ultra's GPU delivers approximately 27.2 TFLOPS.69% similarUnverifiedA 2B model requires approximately 4–10 TFLOPs of computation per inference, taking 10–50 milliseconds on an A100 GPU, while a 70B model requires 140–350 TFLOPs and can take up to several seconds.69% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/909202API
curl https://kongchang.com/api/v1/knowledge/claims/909202MCP
get_claim(id=909202)