Qwen3.5-2B
Qwen
BenchClub cloud
- Pass rate
- 81%
- 29 of 36 checks
- Speed
- 298.1 tok/s
- decode, short prompt
- At 8k context
- 232.5 tok/s
- decode
- Cloud runs
- 4
- speeds within 2.1%
- Coding9/1275%
- Tool use9/1275%
- Long context11/1292%
- 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
- Tom BeckerNov 3, 2026AMD Ryzen 9 7950X · 64 GB32.0 tok/s
Omar FaroukNov 1, 2026RX 7900 XTX · 24 GB212.5 tok/s
- Priya RamanOct 31, 2026Apple M2 Pro · 32 GB89.6 tok/s
- Tom BeckerOct 29, 2026AMD Ryzen 9 7950X · 64 GB33.9 tok/s
- Lucas OliveiraOct 27, 2026RTX 4060 Ti · 16 GBNot counted
- Niko LaineOct 24, 2026L40S · 48 GBCloud296.4 tok/s
- Niko LaineOct 21, 2026L40S · 48 GBCloud299.5 tok/s
- Kwame MensahOct 17, 2026RTX 3090 · 24 GB252.6 tok/s
- Ngozi OkaforOct 11, 2026Apple M1 Max · 64 GB142.6 tok/s
- Jana NovákováOct 6, 2026Apple M1 Max · 64 GB132.0 tok/s
Ben CarterOct 6, 2026L40S · 48 GBCloud296.7 tok/s
- Sofía RuizSep 30, 2026L40S · 48 GBCloud302.7 tok/s
PassedFailedNot supported