Unverified50% confidenceBenchmarkExact time
The TIES method fluctuates in accuracy by 6.7 percentage points at the 4B scale, whereas selection by loss effect fluctuates by only 0.7 percentage points.
1
Sources
50%
Confidence
Long-term
Relevance
11/5/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedLetting the judge also see the formal artifact loses 1.4 to 4.5 percentage points of performance.77% similarVerifiedINT8 quantization loses approximately 0.5% accuracy while halving VRAM usage; INT4 quantization compresses VRAM to 1/4 of the original with an accuracy loss of approximately 1–3%.77% similarVerified4-bit quantization reduces model size to 1/8 of the original at the cost of approximately 1–3% accuracy loss.75% similarVerifiedFor models with more than 30B parameters, the performance loss caused by 4-bit quantization typically results in a 1–3% drop on benchmarks, but the impact is more significant for smaller models.75% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1137827API
curl https://kongchang.com/api/v1/knowledge/claims/1137827MCP
get_claim(id=1137827)