https://ramdi.fr/tags/llama-cpp/Recent content in Llama-Cpp on Noureddine RAMDIHugoenSat, 23 May 2026 20:41:27 +0000https://ramdi.fr/post/ai-llm/local-llm-tokens-per-second-benchmark/Tue, 28 Apr 2026 00:00:00 +0000https://ramdi.fr/post/ai-llm/local-llm-tokens-per-second-benchmark/Part 2 of 4: a benchmark journal across nixpkgs llama.cpp, upstream master, and ik_llama.cpp on Qwen3.6-27B. Six hours, four backends, all converging at 66 tok/s — and the physical reason why.https://ramdi.fr/post/ai-llm/local-llm-speculative-decoding-hybrid-ssm/Tue, 28 Apr 2026 00:00:00 +0000https://ramdi.fr/post/ai-llm/local-llm-speculative-decoding-hybrid-ssm/Part 3 of 4: a deep-dive into why speculative decoding silently breaks (or runs anti-economically) on hybrid attention+SSM architectures like Qwen3.6, Mamba-2, and RWKV — and what would need to change upstream to fix it.https://ramdi.fr/post/ai-llm/local-llm-nixos-llama-server-module/Tue, 28 Apr 2026 00:00:00 +0000https://ramdi.fr/post/ai-llm/local-llm-nixos-llama-server-module/Part 4 of 4: the actual NixOS module, llama-pull helper, claude-code-router wiring, and one-line workflow for switching models. Five Nix files for a complete, isolated, rollback-able local LLM service.