Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Inference Efficiency on KV Cache Efficiency
Loading...
1,966
SKV Count
L2-7B (Base)
-12.08
501.46
1,015
1,528.54
Jul 15, 2025
SKV Count
RS
TTFT
RT
Updated 3d ago
Evaluation Results
Method
Method
Links
SKV Count
RS
TTFT
RT
L2-7B (Base)
Model=L2-7B, dqk=128,...
2025.07
1,966
-
668
-
KV-Latent Train (L2-7B)
Model=L2-7B, dqk=64, d...
2025.07
983
50
573
17
KV-Latent Distill (L2-7B)
Model=L2-7B, dqk=64, d...
2025.07
983
50
573
17
L3-8B (Base)
Model=L3-8B, dqk=128,...
2025.07
491
-
670
-
KV-Latent Train (L3-8B)
Model=L3-8B, dqk=64, d...
2025.07
245
50
622
8
KV-Latent Distill (L3-8B)
Model=L3-8B, dqk=64, d...
2025.07
245
50
622
8
KV-Latent Train (L3-8B, d=16)
Model=L3-8B, dqk=16, d...
2025.07
64
87
595
13
Feedback
Search any
task
Search any
task