Expired85% confidenceFactTime unknown
In the BugFind code bug-finding test, Qwen3.6 27B Q4 precision scored 87 points, higher than Q6's 80 points, exhibiting a quantization reversal phenomenon.
1
Sources
85%
Confidence
Medium-term (~90 days)
Relevance
6/1/2026
First Seen
Valid until: 8/30/2026(expired)
Sources
Related Entities
Related Claims
UnverifiedThe original Qwen3.6 27B Q4 scored 97 in the tool-calling test, demonstrating that distillation does not always improve performance.79% similarUnverifiedThe Qwen3.6 27B version achieved an accuracy of 95.7% on the Simple QA test.76% similarUnverifiedQwen3.6 27B Q4 quantized version scored 650 points, ranking fourth.74% similarUnverifiedQwen3 27B achieved a 100% pass rate in the 256K long-context memory retrieval test (needle in a haystack), with all 15 runs being accurate.73% similarUnverifiedIn actual testing using the Qwen3 27B Q4 quantized dense model, the generation speed with thinking mode disabled is approximately 58–60 tokens/s.73% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/17937API
curl https://kongchang.com/api/v1/knowledge/claims/17937MCP
get_claim(id=17937)