This Gist explains how to run Qwen3.6-35B-A3B on an NVIDIA DGX Spark with a 256 KB context window, which is necessary (in my case) to do anything useful. The memory needed is around 53 GB, leaving plenty of room for loading further tools.
Extension Cline (saoudrizwan.claude-dev) works fine with PhpStorm and Rider (and Visual Studio Code for macOS) using following configuration:
- API provider: OpenAI Compatible
- Base URL: http://{{DGX-SPARK-IP}}:8001/v1
- OpenAI Compatible API Key: placeholder
- Model ID: Qwen/Qwen3.6-35B-A3B
- Model Configuration
- Context Window Size: 262144