Unverified50% confidenceFactExact time

以 LLaMA-2 70B 为例，每次完整推理需从存储加载约 140GB 权重数据，以 5GB/s 的 SSD 读速估算仅数据加载时间就约需 28 秒

1

Sources

50%

Confidence

Long-term

Relevance

7/19/2026

First Seen

Sources

AirLLM: How a 4GB GPU Can Run a 70B Model — Core Principles and Use Cases

Related Claims

UnverifiedIf the quantized model weights are 150 GB, reading the weights once at a bandwidth of 273 GB/s takes approximately 0.55 seconds, giving a theoretical single-token generation speed of approximately 1.8 tokens/s (excluding computation latency and cross-node communication overhead).80% similar

Cite This Claim

Stable URI

https://kongchang.com/claim/564366

API

curl https://kongchang.com/api/v1/knowledge/claims/564366

MCP

get_claim(id=564366)