Unverified50% confidenceBenchmarkExact time
An ordinary 2-bit quantized version is approximately 7.3 GB and can only retain approximately 88% of the benchmark score.
1
Sources
50%
Confidence
Long-term
Relevance
10/4/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedTraditional 8-bit quantization can only achieve approximately 2x compression.71% similarUnverifiedA100 80GB通过MIG最多可切分为7个1g.10gb实例（每个约10GB显存），也可切分为2g、3g、4g、7g规格实例70% similarUnverifiedConverting the 8-bit Ngram table to 4-bit can save approximately 100 GB, reducing the model size from approximately 475 GB to approximately 385 GB.70% similarVerified4-bit quantization (such as Q4_K_M) can typically compress the memory footprint of a 3B model from approximately 6GB to approximately 2GB, with a precision loss of less than 2–3%.69% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/973449API
curl https://kongchang.com/api/v1/knowledge/claims/973449MCP
get_claim(id=973449)