LoreonLabsPlatform
DocsHome
  • Overview

Intelligence

  • Markets
  • Builders
  • Research
  • Ecosystems
  • Launchpads
  • Search
Ecosystems

HTML

selfhostllm

A web-based calculator for estimating GPU memory requirements and maximum concurrent requests for self-hosted LLM inference.

HTMLEmergingcalculatorgpullmselfhost
GitHubWebsite
Stars
46
Forks
5
Contributors
2
Last push
5d ago

Recent commits

Latest commits.

  • add Gemma 4, Qwen 3.6, StepFun models; correct GLM-4.7/5/5.1 specs
    f9ef51aEran Sandler5d ago
  • update recent model catalog
    9080733Eran Sandler27d ago
  • add RTX 50 and RTX PRO GPU options
    102bfaeEran Sandler27d ago
  • Merge pull request #1 from Mr-claw/add-latest-GPU-spec
    c8ea7a2Eran Sandler27d ago
  • Expand context window presets across GPU, Mac, and PC pages
    fb2f474Eran Sandler4mo ago
Add integrated autocomplete selectors and refresh model/device catalogs
d5d5453Eran Sandler4mo ago
  • Add H200 and B200 GPU
    7d72059Mr-claw5mo ago
  • Add AI2 OLMo 2 and OLMo 3 models to all calculators
    2d51392Eran Sandler6mo ago

    • Top contributors

    Builders behind this project.

    erans
    33 commits
    Mr-claw
    1 commits