Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Long-Context Generation on Qwen3 Context length 10K
Loading...
2.76
Throughput Speedup (α)
SpecPV
2.3752
2.4751
2.575
2.6749
Dec 2, 2025
Throughput Speedup (α)
Draft Accept Length (τ)
Updated 4d ago
Evaluation Results
Method
Method
Links
Throughput Speedup (α)
Draft Accept Length (τ)
SpecPV
Model Size=4B, Partial...
2025.12
2.76
3.39
SpecPV
Model Size=14B, Partia...
2025.12
2.75
2.89
SpecPV
Model Size=14B, Partia...
2025.12
2.74
2.79
SpecPV
Model Size=4B, Partial...
2025.12
2.55
3.37
SpecPV
Model Size=8B, Partial...
2025.12
2.53
2.9
SpecPV
Model Size=4B, Partial...
2025.12
2.46
3.35
EAGLE3-YARN
Model Size=14B
2025.12
2.46
3.03
SpecPV
Model Size=14B, Partia...
2025.12
2.46
2.91
EAGLE3-YARN
Model Size=8B
2025.12
2.44
3.23
SpecPV
Model Size=8B, Partial...
2025.12
2.44
2.98
EAGLE3-YARN
Model Size=4B
2025.12
2.43
3.27
SpecPV
Model Size=8B, Partial...
2025.12
2.39
3.02
Feedback
Search any
task
Search any
task