Unverified50% confidenceSolutionExact time
The 24 GB GPU streams the 34 GB DiT by loading weights through ComfyUI's dynamic VRAM path, actually occupying 23 GB of VRAM, at the cost of consuming 68 GB of host memory
1
Sources
50%
Confidence
Long-term
Relevance
9/12/2026
First Seen
Sources
Related Entities
Related Claims
VerifiedA 35B model requires approximately 70GB of VRAM at FP16 precision, far exceeding the RTX 5090's 32GB capacity, so single-GPU deployment requires quantization.76% similarUnverifiedLess than 24 GB of VRAM supports approximately 4K context, 28–48 GB supports approximately 32K, and more than 48 GB supports approximately 256K.75% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/916659API
curl https://kongchang.com/api/v1/knowledge/claims/916659MCP
get_claim(id=916659)