Unverified50% confidenceFactExact time
INT4 uses uniform quantization, while FP4 retains exponent bits, which can better cover the long-tail distribution in activation values.
1
Sources
50%
Confidence
Long-term
Relevance
10/28/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThe difference between NVFP4 and INT4 is that NVFP4 retains the dynamic range expressiveness of floating-point numbers, making it more friendly to large models with non-uniform weight distributions.76% similarUnverifiedThe M5 Ultra's FP8 and FP4 floating-point compute performance is identical to its BF16 performance, and the gap with the Spark narrows noticeably when dropping to FP4 precision.72% similarVerifiedINT4 quantization can theoretically compress a model's VRAM footprint to one-quarter of FP16, with commonly used tools including GPTQ, AWQ, and GGUF.70% similarUnverifiedThe solution uses BF16 precision uniformly for the KV cache, and MXFP4 quantization for the model weights.70% similarUnverifiedFP16 is the default precision for most models at release.68% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1106498API
curl https://kongchang.com/api/v1/knowledge/claims/1106498MCP
get_claim(id=1106498)