Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Time to First Token (TTFT) measurement on Context sequences 32K-256K (vLLM 0.18.0/0.20.0)
Loading...
2.944
TTFT (Dense, s)
Qwen3.5-9B (distilled indexer)
1.02516
13.97733
26.9295
39.88167
Jun 5, 2026
TTFT (Dense, s)
TTFT (Sparse, s)
Speedup
Updated 1mo ago
Evaluation Results
Method
Method
Links
TTFT (Dense, s)
TTFT (Sparse, s)
Speedup
Qwen3.5-9B (distilled indexer)
Indexer=distilled, Har...
2026.06
2.944
2.747
1.07
Qwen3.5-0.8B (distilled indexer)
Indexer=distilled, Har...
2026.06
5.957
4.613
1.29
Qwen3.5-9B (distilled indexer)
Indexer=distilled, Har...
2026.06
6.863
6.024
1.14
Qwen3.5-9B (distilled indexer)
Indexer=distilled, Har...
2026.06
11.78
9.173
1.28
Qwen3.5-9B (distilled indexer)
Indexer=distilled, Har...
2026.06
17.652
12.452
1.42
Qwen3.5-0.8B (distilled indexer)
Indexer=distilled, Har...
2026.06
17.928
10.491
1.71
Qwen3.5-9B (distilled indexer)
Indexer=distilled, Har...
2026.06
50.915
26.322
1.93
Feedback
Search any
task
Search any
task