Explore AI
Tool use and automation
Models that call functions, browse and run multi-step tasks. Small models fail at this quietly.
Models that call functions, browse and run multi-step tasks. Small models fail at this quietly.
What we would try first
- Qwen3 32B 24 GB at Q4 The best quality you can run on a single consumer card. Noticeably better at coding and multi-step tasks than any 8B model.
- GPT-OSS 120B 64 GB at Q4 Needs roughly 64–80 GB. Where the arithmetic stops favouring ownership: rent a GPU for the hours you need it.
- Qwen3 8B 8 GB at Q4 The default answer for most people with 16 GB or a 12 GB card. Start here, and only look elsewhere if it fails at something specific.