← All Models

DeepSeek V4 Flash

284B MoE (13B active) Min 40GB VRAM Full 80GB VRAM codingresearchreasoningagentic

DeepSeek's 2026 preview frontier model. In Ollama it is cloud-only as of May 2026, with a 284B MoE architecture, 13B active parameters per token, and a 1M-token context window.

Run with Ollama

ollama run deepseek-v4-flash:cloud

Which GPUs can run this?

Check my GPU →
📚 Learn to fine-tune DeepSeek V4 Flash — Pluralsight