Llama 2 7B

User benchmarks Llama-2 7B at 62 t/s generation and 1084 t/s prompt processing on an NVIDIA GTX 1080 Ti 11GB. Setup is the CUDA build of llama.cpp with Q4_0 GGUF weights, run via llama-bench with -ngl 100. Figures are pp512 and tg128, a plain single-stream run with no speculative decoding.