Unverified50% confidenceBenchmarkExact time
The IQ3_S model is about 7 GB larger than IQ3_XXS and has a slightly slower generation speed.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/5/2026
First Seen
Valid until: 1/3/2027
Sources
Related Entities
Related Claims
UnverifiedIQ3_S is a non-uniform 3-bit integer quantization scheme that has greater precision loss compared to standard Q4 quantization but requires less storage space and VRAM.77% similarUnverifiedIQ2_XXS以约2.06位的平均比特率编码权重，IQ3_S约3.44位，Q4_K_M约4.83位73% similarUnverifiedIQ3_S shows a significant overall performance improvement compared to the earlier IQ3_XXS version.73% similarUnverifiedIn the name IQ3_S, the number 3 indicates that each weight uses approximately 3 bits of storage on average, and the suffix S represents a finer grouping strategy at the same bit count.71% similarUnverifiedThe 7900XTX on Windows achieves only approximately 400–479 t/s for the prompt processing (preview) phase with Qwen3 IQ3_XSS quantization.70% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/978729API
curl https://kongchang.com/api/v1/knowledge/claims/978729MCP
get_claim(id=978729)