CPP

DLLM: Minimal, clean coding agent built directly on llama.cpp without overhead
9 points | 3 comments

Llama-macOS – Agentic and MCP Native macOS Front End for Llama.cpp
6 points | 2 comments

Privibe - LLM Cli Local first+privacy focus+llama.cpp cache branch + Qwen3.x
2 points | 1 comments

Sana.cpp – Nvidia's Sana T2I model in C++, 4.8x faster than PyTorch
2 points | 0 comments

Privibe – LLM CLI Local first+privacy focus+llama.cpp cache branch and Qwen3.x
1 points | 1 comments

Show HN: 1667, a terminal UI for writing fiction with language models
37 points | 93 comments

Show HN: I shrank DeepSeek V4 Flash to 57GB and it wrote a compiler on my Mac
21 points | 3 comments