| Symptom | Cause | Fix |
|---|---|---|
ollama: command not found | Ollama not installed or PATH not updated | Rerun curl -fsSL https://ollama.com/install.sh | sh and open a new shell |
ollama launch reports unknown command | Ollama is older than v0.15 | Update Ollama: curl -fsSL https://ollama.com/install.sh | sh |
| Model load fails with version error or HTTP 412 | Ollama version is too old for the model | Update Ollama: curl -fsSL https://ollama.com/install.sh | sh |
model not found when launching an agent | Model was not pulled | Run ollama pull qwen3.6 and retry |
connection refused to localhost:11434 | Ollama service not running | Start with ollama serve or sudo systemctl start ollama |
ollama launch <agent> exits immediately | Agent integration failed to initialize | Re-run ollama launch <agent>; if it persists, check journalctl -u ollama |
| Slow responses or OOM errors | Model variant too large for GPU memory | Switch to qwen3.6:35b-a3b-nvfp4 or close other GPU workloads |
python3 -m pip install -U pytest reports externally-managed-environment | Ubuntu 24.04 protects the system Python environment | Create and activate a virtual environment first: python3 -m venv .venv && source .venv/bin/activate |
ollama pull reports that a model tag is a sharded GGUF | The selected model tag is not supported by Ollama | Use the Qwen3.6 commands in Step 3 instead of sharded GGUF tags |
ollama run fails with CUDA error: context is destroyed on a multi-GPU system | Ollama is initializing across a mixed-GPU topology | Pin Ollama to one GPU. For a foreground test, run CUDA_VISIBLE_DEVICES=0 ollama serve; for a system service, add Environment="CUDA_VISIBLE_DEVICES=0" to an Ollama systemd drop-in and restart Ollama |
| A direct Claude Code setup using an Anthropic-compatible Ollama endpoint produces prose but does not edit files | Some model/server combinations do not emit tool calls reliably | Use ollama launch claude with Qwen3.6 as shown in this playbook |
NOTE
DGX Spark uses a Unified Memory Architecture (UMA), which enables dynamic memory sharing between the GPU and CPU. If you see memory pressure, flush the buffer cache with:
sudo sh -c 'sync; echo 3 > /proc/sys/vm/drop_caches'