List your company

ResearchFormerly WizWand

Language Modeling Inference

Benchmarks

DatasetSOTA methodMetricTrendResultsLast updated

Qwen2.5-7B 256K context length

26.3Decode Latency (ms/token)

4

Mar 24, 2026

Qwen2.5-7B 128K context length

18.4Decode Latency (ms/token)

4

Mar 24, 2026

Qwen2.5-7B 64K context length

13.6Decode Latency (ms/token)

4

Mar 24, 2026

Qwen2.5-7B 32K context length

10.3Decoding Latency (ms/token)

4

Mar 24, 2026

Qwen2.5-7B 16K context length

8.4Decode Latency (ms/token)

4

Mar 24, 2026

Qwen2.5-7B 8K context length

7.1Decode Latency (ms/token)

4

Mar 24, 2026

Qwen2.5-7B 4K context length

6.2Decode Latency (ms/token)

4

Mar 24, 2026