llama
Llama
Meta Llama is the king of Open Weights models. Llama 4 (2025) pushes 405B+ parameters, rivaling closed models like GPT-5.
When to Use
- Privacy: Run it on your own VPC (AWS Bedrock, Azure, or self-hosted).
- Fine-Tuning: It is the default base model for fine-tuning on domain data.
- Cost: Inference on Groq/Together AI is significantly cheaper than GPT.
Core Concepts
Models
- 405B: Frontier intelligence. Requires massive GPU clusters (or API).
- 70B: The workhorse. Smart enough for most tasks.
- 8B: Runs on a laptop (MacBook M3).
Quantization
More from g1joshi/agent-skills
template
Expert [skill-name] assistance covering [feature 1], [feature 2], and [feature 3]. Use when [working with X], [debugging Y], or [implementing Z].
34mariadb
MariaDB MySQL-compatible database with Galera clustering. Use for MySQL-compatible database needs.
6claude
Anthropic Claude AI models for analysis and coding. Use for AI assistants.
5javascript
JavaScript ES6+ programming including async/await, DOM manipulation, modules, and Node.js. Use for .js files and web development.
4typescript
TypeScript static typing with interfaces, generics, decorators, and type inference. Use for .ts files.
4python
Python programming with type hints, async/await, decorators, and package management. Use for .py files and data science.
4