← Model library
text
Mistral Small 24B
Mistral · Family Mistral
Mistral Small 24B is a low-latency chat model that deploys in minutes with lightweight serving stacks like Ollama. Ideal for edge deployments and experimental workloads.
Key Features
- ✓ One-command setup with Ollama
- ✓ Low latency
- ✓ Apache 2.0
Use Cases
- → Rapid prototyping
- → Edge/branch deployments
- → High-volume lightweight tasks