Expired85% confidenceFactTime unknown
The Llama 3.1 405B version requires approximately 640 GB of VRAM to fully load and run.
1
Sources
85%
Confidence
Medium-term (~90 days)
Relevance
6/1/2026
First Seen
Valid until: 8/30/2026(expired)
Sources
Related Entities
Related Claims
UnverifiedLlama 3 8B模型（80亿参数）运行约需7GB显存76% similarUnverifiedThe 4-bit quantized GGUF format version of llama.cpp enables the Llama 3.1 70B model to run on an Apple M2 Ultra with 64GB unified memory at an inference speed of approximately 20–30 tokens/second.69% similarUnverifiedGLM-5.2's model weights exceed 1.5 TB in download size, and even the 1-bit quantized compressed version requires approximately 200 GB of VRAM to run.68% similarUnverifiedLLaMA-3 70B权重约140GB，推理时每生成一个Token都需要完整遍历一次权重68% similarUnverifiedThe T30 Lite is equipped with 8 GB of RAM and 512 GB of storage.66% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/18065API
curl https://kongchang.com/api/v1/knowledge/claims/18065MCP
get_claim(id=18065)