Model Recipes
DeepSeek

deepseek-ai/DeepSeek-V3.2

DeepSeek V3.2 MoE model with MLA attention, sparse attention, and scalable RL for strong reasoning and agent capabilities.

GPT-5-level reasoning with efficient MoE inference

moe671B / 37B163,840 ctxvLLM 0.18.0+text
Guide