resyn

Qwen3.8-27B-Fast

3 runs on 1 machine by 1 person · best score 2,256 on M4 Max 128 GB.

Run it

By machine

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

  1. 2,256
    M4 Max 128 GBApple silicon · llama.cpp llama-swap (version not exposed) · resyn-bench 2 · 24.8 tok/s · 49/50 tasks · 100k tokens · 2 runs by uwu

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

Latest runs

  1. 42/44
    M4 Max 128 GB24.8 tok/s · 58k tokens · llama.cpp · uwu · 22 hours ago
  2. 49/50
    M4 Max 128 GB23.4 tok/s · 100k tokens · llama.cpp · uwu · 2 days ago
  3. 44/44
    Other24.3 tok/s · 54k tokens · llama-swap · uwu · 5 days ago

Who ran it

Follow it

Atom feed of new runs of this model, for a feed reader.

Comments on this model are below the runs.

Comments

Sign in or create an account to comment.