Tested system prompts, chat templates, tool-calling formats, and sampler defaults for every local LLM in the directory. Local models are pickier about prompt structure than cloud models — what works on Claude or GPT-5 often fails on Llama or Qwen. This is the catalog of what actually works, per model, with source attribution.
Cloud models (GPT-5, Claude, Gemini Pro) are massive and forgiving. They tolerate vague system prompts, recover gracefully from schema-violating tool calls, and adapt to whatever format you throw at them. Local open-weight models — even good ones — don’t. Llama 3 70B will follow Llama 3 chat-template tokens correctly and drop coherence the moment you feed it ChatML. Qwen 3 expects its own /think toggle; DeepSeek R1 silently degrades if you add a system prompt at all.
Three things change every time you switch model family:
<|begin_of_text|> / <|start_header_id|>. Qwen and Phi-4 use ChatML’s <|im_start|>. Gemma uses <start_of_turn> with no native system role. Mistral uses [INST]...[/INST]. Wrong template = the model loses 20-50% of its instruction-following quality.<tool_call>{...}</tool_call> blocks. Llama 3 emits raw JSON in the assistant turn. Mistral is OpenAI compatible. Same-shape input, three different output formats.temperature 0.7, top_p 0.8, top_k 20. Mistral 3.2 wants 0.15 / 1.0 for tool calls. Phi-4 expects 0.7 / 0.95. Use the wrong defaults and you get either repetition loops or incoherent outputs.Every kit below lists what the vendor model card actually specifies for that model. Where we’ve verified the behavior on our own hardware, the badge flips from blue “From model card” to green “Tested by runlocalai” with date and rig.
Every kit on this page is sourced either from the vendor’s official model card (blue badge) or verified on our own hardware (green badge). We refuse to invent system prompts or fabricate quirks. If you want a model added, tell us which one — popular requests move up the seed queue. The full model directory lives at /models; models without a kit yet just render the base spec page.