Unverified50% confidenceFactExact time
The follow-up paper "The Era of 1-bit LLMs (BitNet b1.58)" found that pure 1-bit requires very large scale to match full-precision quality, so it introduced a zero state, with weights becoming -1, 0 or +1.
1
Sources
50%
Confidence
Long-term
Relevance
10/17/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedBitNet b1.58 uses ternary quantization, where each weight takes one of three values—-1, 0, or +1—amounting to approximately 1.58 bits (log₂3).73% similarUnverifiedBitNet 1.58b quantization uses ternary weights {-1, 0, +1} in PCEI's 24-layer network, reducing parameter memory by about 4 times compared with FP16 precision, and at inference time integer addition can replace floating-point multiplication.66% similarUnverifiedNTK scaling cannot slow down the fastest frequency pair, because θ₀ = base⁰ = 1, which stays the same no matter how the base is adjusted.61% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1053592API
curl https://kongchang.com/api/v1/knowledge/claims/1053592MCP
get_claim(id=1053592)