Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
End-to-end single-step decoding on DeepSeek-R1-Distill-LLaMA-8B 32K Context
Loading...
23.4
Latency (ms)
LessIsMore
23.2
24.55
25.9
27.25
Aug 9, 2025
Latency (ms)
Updated 1mo ago
Evaluation Results
Method
Method
Links
Latency (ms)
LessIsMore
Token Budget=2K, Servi...
2025.08
23.4
Quest
Token Budget=2K, Servi...
2025.08
24.4
TidalDecode
Token Budget=2K, Servi...
2025.08
24.7
Full Attention
Token Budget=2K, Servi...
2025.08
28.4
Feedback
Search any
task
Search any
task