Unverified50% confidenceFactExact time
Sub-1-bit compression means that the average amount of information occupied per parameter is compressed to less than 1 bit.
1
Sources
50%
Confidence
Long-term
Relevance
10/8/2026
First Seen
Sources
Related Entities
Related Claims
Unverified1-bit LLM 的核心思路是将模型权重压缩到每个参数仅约1比特的水平73% similarUnverified2-bit-per-weight quantization compresses each neural network weight to be represented by only 4 discrete values, reducing storage size to 1/8 to 1/16 of the original, at the cost of precision loss.72% similarUnverified1-bit量化（BitNet）将每个权重压缩为单个比特，仅表示+1或-171% similarVerified4-bit quantization compresses each parameter to 0.5 bytes, theoretically compressing 140GB down to approximately 35–40GB.70% similarUnverifiedApple's native 1-bit model compression technology can compress model size to approximately 1/14, reduce memory usage by more than 90%, and improve inference speed by approximately 8 times.70% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/988384API
curl https://kongchang.com/api/v1/knowledge/claims/988384MCP
get_claim(id=988384)