CLI Coding Agent

Confirm your environment

Description: Verify the OS version and GPU are visible before installing anything.

cat /etc/os-release | head -n 2
nvidia-smi

Expected output should show Ubuntu 24.04.3 LTS (DGX OS 7.3.1 base) and a detected GPU.

Install or update Ollama

Description: Install Ollama or ensure it is recent enough to support ollama launch.

curl -fsSL https://ollama.com/install.sh | sh
ollama --version

If Ollama is already installed, just verify the version:

ollama --version

Expected output should show Ollama v0.15 or newer.

Pull Qwen3.6

Description: Download the Qwen3.6 model weights to your Spark node.

ollama pull qwen3.6

Optional variants if you want different memory footprints or precision:

ollama pull qwen3.6:35b-a3b-nvfp4   # NVIDIA FP4 build tuned for Blackwell (~22GB)
ollama pull qwen3.6:35b-a3b-q8_0    # Higher-quality 8-bit quant (~39GB)
ollama pull qwen3.6:35b-a3b-bf16    # Full precision (~71GB)

Expected output should show qwen3.6 in ollama list.

Test local inference (optional)

Description: Run a quick prompt to confirm the model loads.

ollama run qwen3.6

Try a prompt like:

Write a short README checklist for a Python project.

Expected output should show the model responding. When you are done, type /bye or press Ctrl+D to exit before continuing.

Launch OpenCode with Ollama

Description: Use Ollama's built-in launch method to start OpenCode against your local model. No opencode.json provider configuration is required.

ollama launch opencode --model qwen3.6

If you want to pre-configure OpenCode without launching immediately:

ollama launch opencode --config

Expected output should show OpenCode starting with Ollama preselected as the provider and Qwen3.6 as the model. Qwen3.6 ships with a 256K context window by default.

Complete a small coding task

Description: Create a tiny repo and let OpenCode implement a function and tests.

mkdir -p ~/cli-agent-demo
cd ~/cli-agent-demo

printf 'def add(a, b):\n    """Return the sum of a and b."""\n    pass\n' > math_utils.py
printf 'import math_utils\n\n\ndef test_add():\n    assert math_utils.add(1, 2) == 3\n' > test_math_utils.py

If you do not already have pytest installed:

python3 -m venv .venv
source .venv/bin/activate
python3 -m pip install -U pytest

In OpenCode:

Please implement add() in math_utils.py and make sure the test passes.

Run the test:

python3 -m pytest -q

Expected output should show the test passing. When you are done, run deactivate to exit the virtual environment.

Cleanup and rollback

Description: Remove the model and stop services if you no longer need them.

To stop the service:

sudo systemctl stop ollama

ollama rm qwen3.6

Next steps

• Try the qwen3.6:35b-a3b-nvfp4 or bf16 variants for different quality/VRAM tradeoffs
• Use OpenCode on multi-file changes or test-generation tasks
• Explore the full 256K context window on larger codebases