This repo contains the official website for llm.cpp, a dependency-free language model implementation written in C++. No PyTorch, no Python, no frameworks — just plain C++ with a fully manual backward pass.
The site is a single self-contained index.html file with all assets (fonts via Google CDN, hardware photos embedded as base64) baked in.
Optimized for any hardware - from your laptop CPU to a datacenter cluster.
 Apple Silicon M1–M4 · Metal |
 M Pro 19-core GPU · Metal |
 M Max 40-core GPU · Metal |
 M Ultra 76-core GPU · Metal |
 H100 SXM5 · NVLink · 80 GB HBM3 |
 A100 SXM4 · 80 GB HBM2e |
 B200 Blackwell · 192 GB HBM3e |
 T4 CUDA · Cloud · Colab |
 RTX 5090 CUDA · 32 GB GDDR7 |
 RTX 4090 CUDA · 24 GB GDDR6X |
 Jetson Orin NVIDIA · Edge AI |
 DGX Spark NVIDIA · GB10 |
 Radeon RX ROCm · RDNA3 |
 MI300X ROCm · 192 GB HBM3 |
 CPU (x86-64) OpenMP · AVX · Zero install |
- GitHub repo: https://github.com/LMGNU/llm.cpp
- Technical notes: https://eamon2009.github.io/LLMs/
- Releases: https://github.com/LMGNU/llm.cpp/releases
- License: GPL-3.0
By LMGNU · Eamon Sippy