Unverified50% confidenceFactExact time
The final model has only 367K parameters, with the program and weights totaling about 435 KB, enough to fit on a floppy disk and load entirely into DOS memory.
1
Sources
50%
Confidence
Long-term
Relevance
11/15/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedWhen the model loads, it first allocates a full-precision shell of approximately 1.29 GB and then reads in 643 MB of full weights, with peak memory potentially reaching approximately 3,400 MB.75% similarVerifiedA 7B-parameter model requires only approximately 4 GB of VRAM to run after 4-bit quantization.74% similarUnverifiedWhen running a 35B-level MoE model locally, weight storage in FP16 requires roughly tens of GB.73% similarUnverifiedMeta's LLaMA 2 70B model still requires approximately 35 GB of VRAM to fully load even with 4-bit quantization.73% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1172079API
curl https://kongchang.com/api/v1/knowledge/claims/1172079MCP
get_claim(id=1172079)