[KongchangAI]
Unverified60% confidenceFactExact time

Running an open-source model at the 70-billion-parameter scale requires at least approximately 140GB of VRAM in FP16 precision, i.e., 8 H100s in parallel.

2
Sources
60%
Confidence
Long-term
Relevance
7/25/2026
First Seen

Sources

DeepSeek 500亿估值融资:开源模型如何逼空OpenAI与Anthropic
bilibiliDeeparchWorks7/10/2026

Related Claims

Cite This Claim

Stable URI
https://kongchang.com/claim/615615
API
curl https://kongchang.com/api/v1/knowledge/claims/615615
MCP
get_claim(id=615615)