Unverified50% confidenceFactExact time
The average quantization bit width of IQ4_XS is approximately 4.25 bits.
1
Sources
50%
Confidence
Long-term
Relevance
9/25/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedIQ4_XS量化文件大小15.57GB，pp2048为95.4 tok/s，tg128为10.9 tok/s78% similarUnverifiedTaking the Q4_0 format as an example, every 32 FP32 weights are packed into one quantization block containing one scale factor and 32 4-bit integers, averaging approximately 4.5 bits per parameter, reducing memory usage to approximately 1/8 of the original.70% similarUnverifiedEach of Qwen3-27B's 16 full-attention layers has 4 KV heads and a head dimension of 256, occupying 64 KB per token at 16-bit precision.68% similarUnverifiedA 70B model can be compressed to approximately 35GB at INT4 precision.68% similarUnverifiedIQ2_XS can compress a model to close to 2 bits/weight, enabling a 70B model that would otherwise require 48 GB of VRAM to fit into a 24 GB consumer-grade GPU67% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/949598API
curl https://kongchang.com/api/v1/knowledge/claims/949598MCP
get_claim(id=949598)