Choosing a local Qwen model for Hermes Agent workflows
A local AI setup is being planned with Ollama plus or OpenClaw, and the main choice is between and Qwen 3.5 35B. The machine has an RX 9070 XT with 16 GB of VRAM, a Ryzen 7 7700 processor, and 32 GB of . The model would mainly handle reasoning, RAG, and coordination across AI agents.
Audio work would be handled by Whisper, and image analysis would be handled by a separate . The practical question is whether the 35B model is worth the extra resources for long and reasoning, or whether the 27B model or another option would be a better fit.
Key points
- The setup uses Ollama with or OpenClaw.
- The model choice is between and Qwen 3.5 35B.
- The hardware includes 16 GB of VRAM, 32 GB of , and a Ryzen 7 7700 processor.
- The target tasks are reasoning, RAG, and coordinating AI agents.
- The main decision is whether 35B gives enough real benefit to justify its higher resource needs.