Run 70B+ LLMs on a single 4GB GPU — no quantization required. Layer-streaming inference for consumer hardware.
[email protected] is safe to use (health: 48/100)
Get this data programmatically — free, no authentication.
curl https://depscope.dev/api/check/pypi/rabbitllmLast updated · 2026-02-28T12:08:30.266798Z