Verified65% confidenceFactExact time
1.58-bit refers to each weight occupying an average of log₂(3) ≈ 1.58 bits, because ternary weights (−1, 0, +1) have 3 possible states.
3
Sources
65%
Confidence
Long-term
Relevance
7/17/2026
First Seen
Sources
Related Claims
Unverified三个状态的信息熵为log₂(3)≈1.58比特，因此三元量化也被称为1.58-bit量化77% similarUnverifiedTernary quantization restricts neural network weights to three discrete values (typically -1, 0, and +1), requiring theoretically only about 1.58 bits of storage per weight.69% similarUnverifiedThe model has 1.91M parameters, and after int8 quantization the weights occupy 1.97 MB, which is 49.8% of the Ryzen 5 3400G's 4 MB L3 cache.64% similarUnverifiedBonsai uses ternary quantization, compressing each weight to one of three values—-1, 0, or +1—with a shared scaling factor per 128 weights, requiring approximately 1.7 bits per weight, roughly 9 times smaller than 16-bit full precision.64% similarUnverified1-bit量化（BitNet）将每个权重压缩为单个比特，仅表示+1或-163% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/544057API
curl https://kongchang.com/api/v1/knowledge/claims/544057MCP
get_claim(id=544057)