qwen3 coder 30B with ollama server via continue. Big box Win11 Ryzen9-7900,128GB-DDR5,8TB,5090. Use for all of the above. Works pretty well for simple coding tasks. Haven't given it much in the way of smoke tests yet. It's quite snappy, but of course the limitation is context size if I run it solely on GPU. Haven't plugged OSS into the pipeline yet. Wanted to use code specific model.