Show HN: Single-File GGUF Inference

A developer released a single-file GGUF inference engine, tested with the Qwen2.5-Coder-0.5B-Instruct-Q3_K_L.gguf model (369 MB), enabling local inference from a single file.

Tested on: Qwen2.5-Coder-0.5B-Instruct-Q3 K L.gguf 369 MB Select a Qwen2.5 GGUF model file to start inference... Engine Console