Unverified50% confidenceFactExact time
In addition to the model itself, running a large model requires reserving 1–2 GB of VRAM for the KV Cache (key-value cache).
1
Sources
50%
Confidence
Long-term
Relevance
7/22/2026
First Seen
Sources
Ollama本地部署大模型：Windows完整安装教程
Related Claims
UnverifiedWhen models with hundreds of billions of parameters process a 128K context window, KV Cache can occupy tens of gigabytes of VRAM.73% similarUnverifiedIn long-context scenarios (such as models with a 128K token window), the GPU memory occupied by the KV Cache may exceed that of the model weights themselves.73% similarUnverifiedFor a model with 70B parameters, the KV Cache for an 8K context may occupy several additional gigabytes of VRAM72% similarUnverifiedFor a typical 7B model with 32 layers and 32 attention heads, storing the KV Cache for each token requires approximately 0.5 MB of VRAM, so generating 1,000 tokens requires an additional ~500 MB of VRAM72% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/590878API
curl https://kongchang.com/api/v1/knowledge/claims/590878MCP
get_claim(id=590878)