Qwen3.6 35B (3B active)

User reports inconsistent output from local models Gemma 4 and Qwen 3.6 35B A3B compared to frontier models, for a dictation and SOAP scribe. Setup is a Core Ultra 9 with 128 GB RAM and an RTX 5090, running Proxmox with AnythingLLM and Ollama on llama.cpp. The system prompt is a 25-30k token markdown file.