Unverified50% confidenceFactExact time
Underdog Saluki 27B is a model obtained by 2-bit quantization of Qwen3.8-27B.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/25/2026
First Seen
Valid until: 1/23/2027
Sources
Related Entities
Related Claims
UnverifiedThe quantization scheme of Underdog Saluki 27B uses ISTA's GSQ-RCO quantization method.75% similarUnverifiedSaluki 27B surpasses the full-precision original model in tool-calling capability68% similarUnverifiedThe 4-bit quantization of Qwen3 27B shows robust performance, with the gap from FP16 baseline on mainstream benchmark tasks remaining within an acceptable range.66% similarUnverifiedIn 120 function-calling tests on Underdog Bench 120—built on Berkeley's BFCL V4 leaderboard—Saluki 27B scored 88, surpassing the full-size original model's score of 84.65% similarUnverifiedThe Qwen series of models is developed by Alibaba's Tongyi Lab, with 4B and 27B representing the parameter scales.65% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1095139API
curl https://kongchang.com/api/v1/knowledge/claims/1095139MCP
get_claim(id=1095139)