Models
25 open-weight models and what they need to runAgents & tool use9 of 25
Models that support tool calling, best at following instructions first.Show all models
Llama 3.3 70B
Chat model that can call tools. Among the strongest open models at following instructions.
Meta- ~37 GB to run · needs a 64 GB Mac or two graphics cards
- Runs well on many reference systems
- Restricted license · Weights are downloadable; the license limits some uses
- ~6 GB to run · fits most laptops
- Runs well on most reference systems
- Permissive license · Free to use, including commercially
- ~6 GB to run · fits most laptops
- Runs well on most reference systems
- Permissive license · Free to use, including commercially
- ~10 GB to run · fits a 16 GB graphics card
- Runs well on most reference systems
- Permissive license · Free to use, including commercially
- ~6 GB to run · fits most laptops
- Runs well on most reference systems
- Permissive license · Free to use, including commercially
Qwen3 30B-A3B
Efficient general-purpose model for coding, reasoning and tool use.
Qwen Team (Alibaba Cloud)- ~18 GB to run · fits a 24 GB graphics card
- Runs well on most reference systems
- Permissive license · Free to use, including commercially
- ~15 GB to run · fits a 16 GB graphics card
- Runs well on most reference systems
- Permissive license · Free to use, including commercially
Qwen2.5 32B
General-purpose model for coding, reasoning and tool use. Among the strongest open models at reasoning.
Qwen Team (Alibaba Cloud)- ~21 GB to run · fits a 24 GB graphics card
- Runs well on most reference systems
- Permissive license · Free to use, including commercially
- ~42 GB to run · needs a 64 GB Mac or two graphics cards
- Runs well on many reference systems
- Restricted license · Weights are downloadable; the license limits some uses
Parameters, context length, capability profiles and side-by-side comparison are in the Technical view.