Mistral NeMo 12B

Good fit for

People comparing a 12B text-only model with smaller chat models or larger vision models.

Why consider it

The exact runtime entry documents the joint Mistral/NVIDIA model, a conversational template and up to 128K context.

Main limitations

An established older release, not a current flagship claim. Its 7.1GB package does not establish a RAM requirement. Function calling needs a surrounding tool application. No image input or hosted research capability is assigned.

Cost and access

No subscription or per-token hosted fee for local inference within permitted uses. Hardware, electricity and setup are separate. Apache 2.0 is included in the runtime package.

Getting started

Install a current compatible Ollama version, review the exact license and run: ollama run mistral-nemo:12b. API refers to the local runtime endpoint, not a hosted API included with the weights.