Unverified50% confidenceBenchmarkExact time
After 200 steps, the maximum discrepancy between the corresponding weights of the two runs reaches 0.237.
1
Sources
50%
Confidence
Long-term
Relevance
10/12/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedIn tests on 2,456 held-out prompts, increasing the sampling steps from 20 to 50 improved FID only from 27.0 to 26.6 (a gain of 0.4), while removing the shift caused FID to rise from 27.0 to 27.3 and FD-DINOv2 to rise from 218 to 228.71% similarUnverifiedThe model's peak decoding speed on the test platform is approximately 274 tokens/second.64% similarUnverifiedIn a model comparison test, qwen2.5:3b correctly understood pace, produced 0 hallucinated place names, had a length error of 0.3%, peak memory of 259 MB, and took 106 seconds.64% similarUnverifiedThe 26-billion-parameter Gemma (MoE) achieved a measured speed of nearly 31 tokens/second, about one-third faster than GPT-OSS 20B.63% similarUnverifiedPerplexity Decider V1.1 27B topped the evaluation with a score of 80/82, a median latency of 0.445 seconds, and zero flips across 26 reversal tests.63% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1001668API
curl https://kongchang.com/api/v1/knowledge/claims/1001668MCP
get_claim(id=1001668)