Unverified50% confidenceFactExact time
SupaVoxel's export menu offers two options: a compressed GLB of 11,165,408 bytes and an uncompressed GLB of 82,060,632 bytes at original size.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/12/2026
First Seen
Valid until: 1/10/2027
Sources
Related Entities
Related Claims
UnverifiedThe HGN format's PLE module uses FP8 quantization at approximately 47.7 GB, while the GGUF format quantizes PLE to Q4 via unsloth at only 26.8 GB, but the overall file is larger and occupies approximately 10 GB of additional VRAM62% similarVerified4-bit quantization in GGUF format can compress model weights from 32-bit floating point to 4-bit integers, reducing model size by approximately 8 times.59% similarUnverifiedOllama通过GGUF格式的4-bit/8-bit量化可将70B模型压缩至在16GB显存的消费级GPU甚至Apple Silicon芯片上运行58% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1007555API
curl https://kongchang.com/api/v1/knowledge/claims/1007555MCP
get_claim(id=1007555)