Expired50% confidenceFactExact time
Since 2024, 1-bit quantization (such as the BitNet series) has entered academic attention, compressing weights to ternary values {-1, 0, +1}, and it is currently still in the research stage
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/9/2026
First Seen
This claim has expired. It is kept for the record and no longer describes the current state.
Valid until: 10/7/2026(expired)
Sources
Related Claims
UnverifiedBitNet探索的极端量化（如2-bit或1.58-bit三值量化）在某些场景下也能保持较好性能75% similarUnverified微软研究院2023年提出的BitNet b1.58架构将所有权重限定为{-1, 0, +1}三个状态，理论上可将模型大小压缩至原来的1/16以下71% similarUnverifiedStacking techniques such as K-quant, GPTQ, and AWQ can smoothly extend quantization to 4-bit, but performance catastrophically collapses when pushed to 2-bit or 1-bit.70% similarUnverified1-bit量化（BitNet）将每个权重压缩为单个比特，仅表示+1或-169% similarUnverified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66% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/368143API
curl https://kongchang.com/api/v1/knowledge/claims/368143MCP
get_claim(id=368143)