Unverified50% confidenceBenchmarkExact time
Peak memory usage is approximately 117 GB when running at full load with a 1M context.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
9/10/2026
First Seen
Valid until: 12/9/2026
Sources
Related Entities
Related Claims
UnverifiedThe KV Cache of a 70B-parameter model with 128K context support can require hundreds of gigabytes of VRAM at full load, exceeding the 80GB VRAM capacity of a single H100.72% similarUnverified128GB DDR5 memory can fully load all weights of a 70B-class model, but at a speed of approximately 2–5 tokens/s.71% similarUnverifiedFor 1 million tokens, the KV Cache alone can consume hundreds of GB of VRAM at FP16 precision, far exceeding the 80 GB capacity limit of a single A100/H100.71% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/891414API
curl https://kongchang.com/api/v1/knowledge/claims/891414MCP
get_claim(id=891414)