Best local models for Ollama

13B class • 8.5 GB minimum

Native Ollama package verified on the official library page.

34B class • 15.5 GB minimum

Official Ollama library entry with a native tag and published downloads.

70B class • 40.0 GB minimum

Official Ollama package for the 70B instruct tag.

3B class • 2.5 GB minimum

IBM's smallest Granite 4.0 instruct release is a pragmatic US-origin starter for local chat, extraction, and agent scaffolding.

7B class • 5.0 GB minimum

Ai2's 7B instruct release is the clearest Apache-licensed American alternative to Llama when you want a smaller fully open local model.

7B class • 6.5 GB minimum

Meta's 8B instruct release remains the safest broad-compatibility US local model when you want maximum runtime coverage.

13B class • 11.0 GB minimum

Gemma 3 12B stays interesting when you want a smaller multimodal American model, but it is less turnkey than Phi-4-reasoning for plain text work.

34B class • 19.5 GB minimum

OLMo 3.1 32B is the strongest Apache-licensed American 32B-class option, but it asks for more memory than gpt-oss-20b to reach a clean first run.

34B class • 19.5 GB minimum

Granite 4.0 H-Small is a credible American midrange choice for RAG-heavy work, but it is more specialized than the general-purpose winners above it.