Unverified50% confidenceBenchmarkExact time
The author's generation setup is an RTX 5070 Ti GPU with 32GB of RAM, 20 sampling steps, approximately 53 seconds per iteration, resolution set to 0.6, aspect ratio 1:1, and no turbo LoRA used.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
9/26/2026
First Seen
Valid until: 12/25/2026
Sources
Related Entities
Related Claims
UnverifiedUsing the ti2v-5b Q5 model at 960x544 resolution, 81 frames, and 20 steps, each step takes only 1.95 seconds, with approximately 3GB of VRAM remaining idle.75% similarUnverified在RTX 3080实测中，用户采用0.2百万像素/608×352分辨率的生成设置73% similarUnverifiedIn an RTX 5060 Ti 16GB + 64GB RAM environment, Qwen3 27B took 1 hour and 10 minutes to generate a responsive personal website, averaging 6.42 tokens per second.73% similarUnverifiedThe test hardware was an RTX 3060 12GB GPU with 16GB of RAM, and the test content was an R2V (reference image to video) task using a maximum of 3 image references.71% similarUnverifiedThe project used two RTX 4090 GPUs each with 48 GB of VRAM to run 8 long-context requests each approaching 256K.71% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/952765API
curl https://kongchang.com/api/v1/knowledge/claims/952765MCP
get_claim(id=952765)