Unverified50% confidenceBenchmarkExact time
The reference model Supra-50M has 51.8M parameters, is 103.6 MB in bf16, 56.2 MB after 8-bit quantization, perplexity degrades from 165 to 193 when reduced to int4, and collapses entirely when compressed to ternary.
1
Sources
50%
Confidence
Long-term
Relevance
9/15/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedA 70B model can be compressed to approximately 35GB at INT4 precision.74% similarUnverified13B–14B class models (4-bit quantization) see speeds drop to 2–5 tokens per second under this configuration73% similarUnverifiedA 2.4-trillion-parameter model requires approximately 9.6 TB of VRAM in FP32, about 4.8 TB in BF16, about 2.4 TB in INT8, and about 1.2 TB in INT4.72% similarVerifiedA 70B-parameter FP16 model requires approximately 140 GB of video memory, approximately 70 GB after INT8 quantization, and approximately 35–40 GB after INT4 quantization.71% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/922671API
curl https://kongchang.com/api/v1/knowledge/claims/922671MCP
get_claim(id=922671)