Peregrine uses your hardware profile to choose the right inference setup.
✅ Detected {{ wizard.hardware.gpus.length }} local GPU(s):
{{ wizard.hardware.gpus.join(', ') }}
No local NVIDIA GPUs detected. CPU or Orchard mode recommended.
Ollama
{{ ollamaRunning ? 'running' : 'not detected' }}
SearXNG
{{ searxngRunning ? 'running' : 'not detected' }}
Ollama not running — start it on the host before continuing, or choose Remote or Orchard mode.
See Settings → Services after setup to manage services.
Available nodes:
{{ gpu.node }}
{{ gpu.name }}
{{ Math.round(gpu.vram_free_mb / 1024 * 10) / 10 }} /
{{ Math.round(gpu.vram_total_mb / 1024 * 10) / 10 }} GB free
🔒
Orchard inference requires a Paid license or higher.
You can select this profile now; it will activate once your license is verified.
⚠️ No local GPUs detected — a GPU profile may not work. Choose CPU
or Orchard if you have access to the cluster.