CPP

Apples to Apples: MLX vs. Llama.cpp for Gemma 4 12B on an M1 16GB
5 points | 1 comments

Show HN: Run Llama.cpp In-Process from Java with Project Panama FFM
5 points | 0 comments

Show HN: Will It Fit? – Opinionated Normal People Llama.cpp VRAM Estimator
4 points | 1 comments

LlamaStash – Zero-overhead, terminal-native llama.cpp launcher
3 points | 0 comments

ik_llama.cpp – llama.cpp fork with better CPU performance
3 points | 0 comments

Show HN: TurboPrefill – Multi-GPU prefill acceleration for llama.cpp
2 points | 0 comments

LlamaStash: a zero-overhead, terminal-native llama.cpp launcher
2 points | 0 comments