Model Recipes
DeepSeek

deepseek-ai/DeepSeek-V3.1

DeepSeek-V3.1 is a hybrid MoE model that supports dynamic switching between thinking and non-thinking modes, with tool calling and function execution.

Hybrid thinking / non-thinking MoE with native FP8 and tool calling

moe671B / 37B163,840 ctxvLLM 0.12.0+text
Guide