llama-server for Underdog

llama.cpp's llama-server, built unmodified by Underdog to run GGUF models such as Underdog Saluki 27B on Apple silicon Macs (macOS 14.0 and later). The Underdog app downloads it with the model and checks this SHA-256 before it runs it.


Source	https://github.com/ggml-org/llama.cpp at `bd4eeaa047006cb1fe71999fbd11134b5836e167`
Build	llama-server-0.6.0-bd4eeaa_macos14.0-arm64_r1: static, arm64, Metal, no web UI
Signed	Developer ID, hardened runtime, notarized
SHA-256	`6fd3c37124cae4710f0cfbbc627177bbc9bfc248dff904549ee0b0d8bc87996f`

Licences: LlamaCppThirdPartyNotices.txt (MIT).

Downloads last month: -; Downloads are not tracked for this model. How to track

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support