Skip to content
llm-speed

Requested LLM benchmark runs

Pick a model and hardware to request a measured run, or vote for one below. We rent NVIDIA cards and run the most-requested pairs first, within budget. Apple Silicon and other hardware need a community run, so those requests count too: anyone with that machine can submit their own. Vote counts are requests, not benchmark results.

Request a run

No measured run yet for these pairs. Vote for the one you want; the most-requested runs go first. See all requests.

Codestral-22B-v0.1 on A100 40GB0 votes

We never sell or share your email. Privacy

We can rent this card · Submit your own

Top requests

  1. Qwen3.8-27B on RTX 4070 Ti SUPER1 vote
    We can rent this card · Submit your own
  2. Gemma 4 12B IT QAT on M4 Pro1 vote
    Needs a community run · Submit your own
  3. Qwen3.8-27B on M4 Pro1 vote
    Needs a community run · Submit your own