Unverified50% confidenceFactExact time
Engram dedicates one quarter of the entire checkpoint's capacity to n-gram memory, reaching a scale of 197B parameters.
1
Sources
50%
Confidence
Long-term
Relevance
9/15/2026
First Seen
Sources
Related Entities
Related Claims
VerifiedUsing float16 precision as a baseline, each parameter occupies approximately 2 bytes, meaning a 7B model requires approximately 14GB of VRAM/memory, and a 70B model requires approximately 140GB.75% similarUnverifiedAn agentic host requires at least 96 GB of unified memory as the entry-level threshold.73% similarUnverifiedThe model weights alone of a 175-billion-parameter model (in BF16 precision) require 350 GB of storage, and the Adam optimizer must maintain two sets of states—first-order moments and second-order moments—totaling more than 1 TB.72% similarUnverifiedA unified memory pool of 128GB means that quantized models at the 70-billion-parameter scale or larger can be run locally.72% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/921481API
curl https://kongchang.com/api/v1/knowledge/claims/921481MCP
get_claim(id=921481)