FitMyLLM — The data layer for self-hosted AI
www.fitmyllm.com
Independent data for every model, GPU and cloud provider. Estimates calibrated against real measurements, not vendor claims. 449 models, 1,720 GPUs, multi-provider cloud comparisons.

cross-posted from: https://programming.dev/post/51407459

Check what can you use and at what rate of token per seconds would it be… It has examples of many models and quantization levels. Huge resource!

  • comrade | 🇵🇸@lemmy.ml
    1·
    2 days ago

    It recommends Qwen3.5 35B for an Apple A18 8GB… 🙃 also it doesn’t seem to understand how unified memory works