▮ aihublocal.com
configsaiorankingsagentsrunnersweb uimultimodal
☕Support
Buy Me a Coffee

© 2026 ▮ aihublocal.com — no cloud · no telemetry · MIT

// your local AI station

No servers needed.
A 125B model on your own PC.

LLM Runner AIO installs Open WebUI, llama.cpp, SearXNG and the Strata gateway for you. Hardware detected, models downloaded, ports opened — automatically.

⬇ llm-runner-aiov2.1.exe — 2.28 GB121 model rankings →
$ run.bat
✓ GPU detected  : RTX 5080 · 15.9 GB VRAM
✓ Profile       : 16 GB preset
✓ Model        : qwen3.8-27B + DFlash2 draft
✓ llama.cpp     : localhost:1234
✓ Open WebUI    : localhost:3000
✓ Strata        : localhost:1235 (OpenAI+Anthropic)
ready. ▊
121+
ranked models
v2.1
AIO version
7
bundled services
100%
open source

// what's included

LLM Runner AIO

One-click setup, hardware detection, GUI Model Manager and the full VRAM preset matrix.

Model Rankings

121 GGUF models compared by intelligence index, parameters, context window and speed.

LLM Configs

Ready-made chat / vision / coding configurations matched to your hardware profile.

LLM Runners

17 runners from Ollama to Strata; OS · platform · capability comparison table.

LLM Web UI

Open WebUI, LibreChat, LobeChat... self-hosted interfaces with GitHub star counts.

Multimodal

Wan2GP, ComfyUI and local image / video / audio generation services.

© 2026 aihublocal.comno cloud · no telemetry · MIT