# Llama

> Meta Llama open-source LLM family. Use for local AI.

- **Type:** Skill
- **Install:** `agentstack add skill-g1joshi-agent-skills-llama`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [G1Joshi](https://agentstack.voostack.com/s/g1joshi)
- **Installs:** 0
- **Category:** [Developer Tools](https://agentstack.voostack.com/c/developer-tools)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [G1Joshi](https://github.com/G1Joshi)
- **Source:** https://github.com/G1Joshi/Agent-Skills/tree/main/skills/ai-ml/llama
- **Website:** https://skills.sh/g1joshi/agent-skills

## Install

```sh
agentstack add skill-g1joshi-agent-skills-llama
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# 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

Running models at 4-bit or 8-bit precision to fit in VRAM with minimal quality loss (GGUF, EXL2).

### Llama Stack

Standardized tooling for building agentic apps on Llama.

## Best Practices (2025)

**Do**:

- **Use via API**: Groq (LPU) runs Llama Instantaneously (>1000 tok/s).
- **Fine-Tune 8B**: For specific tasks (classification, SQL generation), a fine-tuned 8B beats a generic 70B.

**Don't**:

- **Don't self-host 405B**: Unless you have 8xH100s. Use an API provider.

## References

- [Llama Website](https://www.llama.com/)

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [G1Joshi](https://github.com/G1Joshi)
- **Source:** [G1Joshi/Agent-Skills](https://github.com/G1Joshi/Agent-Skills)
- **License:** MIT
- **Homepage:** https://skills.sh/g1joshi/agent-skills

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-g1joshi-agent-skills-llama
- Seller: https://agentstack.voostack.com/s/g1joshi
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.