Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
LLM Inference Efficiency on Efficient Qwen Competition Scenarios (Short/Medium/Long)
Loading...
6.978
Average Speedup
AFM-k5984d3s (Ours)
0.76088
2.37494
3.989
5.60306
Jul 5, 2026
Average Speedup
Short Latency (ms)
Medium Latency (ms)
Long Latency (ms)
Updated 18d ago
Evaluation Results
Method
Method
Links
Average Speedup
Short Latency (ms)
Medium Latency (ms)
Long Latency (ms)
AFM-k5984d3s (Ours)
Target Model Quantizat...
2026.07
6.978
232
782
2,313
Baseline
Precision=BF16, Optimi...
2026.07
1
2,582
5,441
6,576
Feedback
Search any
task
Search any
task