models▌

Foundation Models issues manifest as context window exceeded errors, guardrail violations, slow generation, availability failures, and unexpected output. Core principle 80% of Foundation Models problems stem from misunderstanding model capabilities (3B parameter device-scale model, not world knowledge), context limits (4096 tokens), or availability requirements—not framework bugs.

Use when:

bitsandbytes reduces LLM memory by 50% (8-bit) or 75% (4-bit) with <1% accuracy loss.

Access 100+ language models via inference.sh CLI.

BigCode Evaluation Harness evaluates code generation models across 15+ benchmarks including HumanEval, MBPP, and MultiPL-E (18 languages).

This skill provides access to current trending programming models from OpenRouter's public rankings. It executes a Bun script that fetches, parses, and structures data about the top 9 most-used AI models for programming tasks.

On-device LLM integration for iOS 18+ using Apple's FoundationModels framework with privacy-first text generation and structured output. \n \n Covers text generation, structured output via @Generable macro, custom tool calling, and snapshot streaming—all running locally without cloud dependency \n Requires availability checks before session creation; supports single-turn and multi-turn conversations with optional system instructions \n Guided generation with @Guide constraints (numeric ranges, a

The Foundation Models framework provides access to Apple's on-device Large Language Model (3 billion parameters, 2-bit quantized) with a Swift API. This reference covers every API, all WWDC 2025 code examples, and comprehensive implementation patterns.

Access 100+ language models including Claude, Gemini, Kimi, and GLM via OpenRouter. \n \n Supports Claude Opus 4.5, Sonnet 4.5, and Haiku 4.5 for varying performance and cost tradeoffs, plus Gemini 3 Pro, Kimi K2 Thinking, GLM-4.6, and Intellect 3 \n Auto-select mode picks the most cost-effective model automatically for your use case \n Designed for code generation, reasoning, content creation, data analysis, and building AI agent workflows \n Requires inference.sh CLI ( infsh ) and API authenti