Unverified50% confidenceFactExact time
SDXL can now render within a 4 GiB VRAM budget, and has been tested on T4 and L4.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
11/3/2026
First Seen
Valid until: 2/1/2027
Sources
Related Entities
Related Claims
UnverifiedCFG=4–4.5 is the recommended starting range for many Flux and SD3 series models, while SDXL-type models commonly use 5–8.61% similarUnverifiedThe Agent's default self-hosted configuration uses the Qwen3.6-35B-A3B model with 4-bit quantization deployed via sglang.61% similarUnverifiedThe FLUX.2 [dev] version is a 32B parameter model capable of outputting 4-megapixel images; the [klein] 4B version can perform inference on consumer-grade hardware such as the NVIDIA RTX 3090.60% similarUnverifiedvLLM and SGLang had previously completed adaptation for the text-only version of V4-Flash.59% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1131475API
curl https://kongchang.com/api/v1/knowledge/claims/1131475MCP
get_claim(id=1131475)