Unverified50% confidenceFactExact time
For a model with exactly 8 billion parameters, the idealized weight payload is about 14.90 GiB at 16 bits, about 7.45 GiB at 8 bits, and about 3.73 GiB at 4 bits.
1
Sources
50%
Confidence
Long-term
Relevance
10/18/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedFull fine-tuning of a 70B model with the AdamW optimizer requires about 1,129 GB of VRAM (70.55 billion parameters × 16 bytes per parameter).71% similarUnverifiedOn NVIDIA L4, the bf16 model (6.32 GiB) has a theoretical memory-bandwidth ceiling of about 47 tokens/s, while the int4 model (2.85 GiB) has a theoretical ceiling of about 105 tokens/s, with measured peak reaching 131.9 tokens/s.70% similarUnverified27.18 MiB is approximately equal to 22.7 million bytes; if stored at 8 bits, this corresponds to about 22.7 million parameters, accounting for only 0.28% of an 8B model.70% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1057298API
curl https://kongchang.com/api/v1/knowledge/claims/1057298MCP
get_claim(id=1057298)