OpenAI-gpt-oss-20b

By machine

Each machine's best run of this model. Higher is better: fast, and correct.

1. 27/44
   M4 Max 128 GBApple silicon · 27/44 tasks · 76k tokens · 1 run by uwu
   Not on the leaderboard: it was posted under an earlier version of the task suite.

Open a machine's page from any run, or the hardware leaderboard, to compare it with others.

Latest runs

1. 27/44
   M4 Max 128 GB111 tok/s · 76k tokens · llama.cpp · uwu · 1 day ago
2. 42/44
   Other109 tok/s · 81k tokens · llama-swap · uwu · 5 days ago
3. 41/44
   Other96.8 tok/s · 148k tokens · llama-swap · uwu · 5 days ago