Unverified50% confidenceFactExact time
When running a 35B-level MoE model locally, weight storage in FP16 requires roughly tens of GB.
1
Sources
50%
Confidence
Long-term
Relevance
10/29/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedInferencing a 1T-parameter MoE model requires hundreds of gigabytes of VRAM even with BF16 half-precision storage, far exceeding the capacity limit of consumer-grade GPUs.78% similarUnverifiedThe main model file of this model has a disk size of approximately 21GB, but ComfyUI loads and unloads weights on demand between VRAM and memory, so the weights are not all pushed into the GPU at runtime.74% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1110194API
curl https://kongchang.com/api/v1/knowledge/claims/1110194MCP
get_claim(id=1110194)