Models

25 open-weight models and what they need to run

Small models9 of 25

10B parameters or fewer. Most capable first.Show all models

Coding Run locally Reasoning Vision Agents & tool use Fast models Small models Permissive licenses

Qwen2.5-Math 7B
Compact model for maths and reasoning.
Qwen Team (Alibaba Cloud)
- ~6 GB to run · fits most laptops
- Runs well on most reference systems
- Permissive license · Free to use, including commercially
View model →
Qwen2.5 7B
Compact general-purpose model for coding and tool use.
Qwen Team (Alibaba Cloud)
- ~6 GB to run · fits most laptops
- Runs well on most reference systems
- Permissive license · Free to use, including commercially
View model →
Llama 3.1 8B
Compact general-purpose model for coding and tool use.
Meta
- ~6 GB to run · fits most laptops
- Runs well on most reference systems
- Permissive license · Free to use, including commercially
View model →
Gemma 2 9B
Compact model for everyday chat.
Google DeepMind
- ~9 GB to run · fits a 16 GB graphics card
- Runs well on most reference systems
- Restricted license · Weights are downloadable; the license limits some uses
View model →
Mistral 7B
Compact chat model that can call tools.
Mistral AI
- ~6 GB to run · fits most laptops
- Runs well on most reference systems
- Permissive license · Free to use, including commercially
View model →
Qwen3 0.6B
Compact model for everyday chat.
Qwen Team (Alibaba Cloud)
- Permissive license · Free to use, including commercially
View model →
Qwen3 1.7B
Compact model for everyday chat.
Qwen Team (Alibaba Cloud)
- Permissive license · Free to use, including commercially
View model →
Qwen3 4B
Compact model for everyday chat.
Qwen Team (Alibaba Cloud)
- Permissive license · Free to use, including commercially
View model →
Qwen3 8B
Compact model for everyday chat.
Qwen Team (Alibaba Cloud)
- Permissive license · Free to use, including commercially
View model →

Parameters, context length, capability profiles and side-by-side comparison are in the Technical view.