Qwen3-14B
Qwen
BenchClub cloud
- Pass rate
- 87%
- 39 of 45 checks
- Speed
- 67.1 tok/s
- decode, short prompt
- At 8k context
- 52.3 tok/s
- decode
- Cloud runs
- 5
- speeds within 1.8%
- Coding13/1587%
- Tool use11/1573%
- Long context15/15100%
- Suite
- [email protected]
- Machine
- NVIDIA L40S · 48 GB
- Engine
- ollama 0.40.14
Headline numbers come only from cloud runs. Runs on members’ own machines are listed below and don’t change them.
LMArena
Not ranked on LMArena
LMArena only ranks the models it serves.
BenchClub runs
Run this modelRun byWhereSpeed
Alex RiveraOct 27, 2026L40S · 48 GBCloud66.0 tok/s
Ben CarterOct 26, 2026RTX 4090 · 24 GB77.5 tok/s
- Li WeiOct 24, 2026L40S · 48 GBCloud67.1 tok/s
- Jana NovákováOct 20, 2026Apple M1 Max · 64 GB28.2 tok/s
- Lucas OliveiraOct 13, 2026RTX 4060 Ti · 16 GB21.0 tok/s
- Kwame MensahOct 12, 2026L40S · 48 GBCloud67.1 tok/s
- Mei TanakaOct 9, 2026L40S · 48 GBCloud67.1 tok/s
- Priya RamanOct 8, 2026RTX 4070 Ti SUPER · 16 GBNot counted
- Lucas OliveiraOct 6, 2026RTX 4060 Ti · 16 GB22.9 tok/s
- Kwame MensahSep 15, 2026Apple M2 Pro · 32 GB13.4 tok/s
PassedFailedNot supported