← All Models

Llama 4 Maverick

400B MoE (17B active) Min 256GB VRAM Full 803GB VRAM chatresearchcreative

Meta's larger multimodal Llama 4 model, best suited to cloud or datacenter GPUs.

Run with Ollama

ollama run llama4:maverick

Which GPUs can run this?

Check my GPU →
📚 Learn to fine-tune Llama 4 Maverick — Pluralsight