model-reference

What problem does it solve?

This Skill removes the guesswork in choosing AI models by giving you a quick, structured reference for capabilities, benchmarks, recommended sampling settings, memory needs, and pricing across major LLM/VLM and generation families.

Core Features & Use Cases

• Model-family quick lookup: Jump straight to model families (e.g., Qwen, DeepSeek, Llama, Kimi) and see where to find deeper reference notes.
• Recommended parameters & practical guidance: Pull suggested temperature/top_p/top_k guidance and task modes (reasoning, coding, creative) to reduce trial-and-error.
• Pricing and resource sizing: Use the reference overview to estimate cost and VRAM/precision memory requirements; consult per-family references for details.
• Cross-model comparisons: Use the overview and topic reference files to compare model characteristics and common configuration patterns.

Quick Start

Ask an AI: "Use the model-reference skill to recommend sampling parameters for a reasoning task and estimate memory needs for a selected model family, then point me to the relevant references file for more details."