Tutorials
Step-by-step setup and configuration notes: commands, parameters, failure modes and acceptance checks, written to be followed.
How to read these tutorials
Every step lists a copyable command and a pass/fail check. Failures are kept, with the environment and versions at the time. Numbers come from the recorded run; check vendor docs for updates.
Tutorial index
Claude Code with a Local llama.cpp Model: It Works, but Half of 32K Context Is Gone
llama-server ships an Anthropic-compatible endpoint, so Claude Code can talk to a local model by changing one URL. It ran on our 6GB laptop, but its ~16K-token system prompt triggers "Prompt is too long" on small-context models.
Read articleCodex CLI with a Local Model: Config, and 12 \"expected i32\" Errors
Point Codex CLI at llama-server with a custom model_provider. On LFM2.5-24B it passed 12/12, but made 12 tool-argument type errors and recovered by retrying. The first bug-fix run took 599 s.
Read articleBuild llama.cpp with CUDA on a Windows Laptop via WSL2 (RTX 3060)
Build llama.cpp with CUDA 12.8 in WSL2 on a Windows 11 laptop to get llama-server and llama-bench. Every 6GB test on this site uses this setup, and three settings are the easiest to get wrong.
Read articleMoE in llama.cpp: Putting All Experts on the CPU Was 4x Faster (-ncmoe Tuning)
On a 6GB laptop, Qwen3.6-35B-A3B generates 5.2 t/s with experts on the GPU and 21.5 t/s with all experts in system RAM, using half the VRAM. That isn't a rule, though. LFM2.5-24B peaks in the middle.
Read articleOne Command to Turn llama-server into a Local OpenAI / Anthropic API (6GB Settings)
llama-server speaks both OpenAI- and Anthropic-compatible APIs, so pi, Codex and Claude Code can all connect to it. These are the exact flags we used to run agents on a 6GB laptop, and what each one does.
Read articleSlow Hugging Face Downloads? Parallel Range Chunks, Tested
Downloading 16.6 GB of Qwen-Image 2.1 weights, both curl and the official client stalled. Switching to 16 parallel 32 MiB Range chunks reached ~15.8 MiB/s during the main model's chunk phase, and both files finished in 36 minutes with official SHA256 checks passing.
Read articleDeploying LingBot-World 1.3B natively on Windows: 13 frames of image-to-video on a 6 GB laptop
From nothing to a finished clip: environment checks, cloning the patched branch, aria2 multi-connection downloads, the CUDA gate, 13 weight checksums, and finally a 832×464, 13-frame image-to-video run. Commands are copy-paste ready and every step states how to tell it worked; the flash-attn problem that stops upstream on Windows is covered at the end.
Read article