Llama 3.2 3B on Ollama. A smaller, fast, tool-capable Meta model. Good fit for boxes with limited RAM that still need tool calling.
Every EasyEnv recipe spins up in seconds on a real Linux VM-not a stripped-down sandbox. The Ollama Llama 3.2 3B recipe is provisioned by an open Ansible role, so the machine that boots for you is reproducible, inspectable, and matches what you would get in production.
$ easyenv workspace create --recipe ollama_llama3_2_3b --name ollama_llama3_2_3b-demo
Provisioning Ollama Llama 3.2 3B...
Workspace ready in ~45s
$ easyenv workspace ssh ollama_llama3_2_3b-demo
Connected. You're on the machine.Stop guessing from resumes. Drop candidates into a real Ollama Llama 3.2 3B workspace, watch them debug, deploy and operate it, score the result automatically, and replay the session. We also evaluate how they work with AI.
Builds and deploys AI applications, integrates LLMs into products, and manages self-hosted AI infrastructure
PostgreSQLDevelops and deploys machine learning models and AI systems for production environments
Builds and maintains data pipelines, ETL processes, and data infrastructure for analytics
Develops backend services, APIs, and scripts using Python frameworks like Django, Flask, or FastAPI
VS CodeSelf-hosted LLM inference with Ollama and OpenWebUI for private AI workloads
Self-hosted AI document assistant powered by AnythingLLM and Ollama
Automated AI workflows combining LLMs with n8n orchestration and PostgreSQL
Machine learning and data science environment
