Unverified50% confidenceBenchmarkExact time
By default, after generating one image, the SDXL checkpoint, CLIP text encoder, and VAE remain resident in VRAM, occupying about 8GB; after calling /free, VRAM falls back to a baseline of about 2.2GB.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/14/2026
First Seen
Valid until: 1/12/2027
Sources
Related Entities
Related Claims
UnverifiedSDXL 基础模型仅加载就需要 6-8GB 显存66% similarUnverifiedRunning mainstream image generation models (such as SDXL) requires at least 8GB of VRAM65% similarUnverifiedIn DOS games, programs set display modes via INT 10h interrupts, draw pixels by writing directly to the 0xA000 segment video memory address, perform file operations via INT 21h, and are subject to a conventional memory limit of 640 KB64% similarUnverifiedWhen the author ran Qwen-Image-2.1 at 1024×1024 resolution on the same Mac, the process footprint never exceeded 18.5 GB, but swap grew by 3.5 GB during the denoising stage and by 9.6 GB during the VAE decoding stage, and finally the memory guard actively terminated the run before writing out the image.64% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1025789API
curl https://kongchang.com/api/v1/knowledge/claims/1025789MCP
get_claim(id=1025789)