DeepSeek's 552B MoE activates 8B params on prefill and stores 890 bytes of KV cache per token. What the card says and how to start running it.
deepseek-ai/DeepSeek-V4.1-Flash
Edge0-35B-A3B streams experts from SSD so a 4-bit Qwen3.6-35B-A3B derivative decodes at about 15 tok/s in under 3 GiB of active memory.
Edge0/Edge0-35B-A3B-preview
Z.ai's first natively multimodal GLM-5 model: 320B total / 18B active parameters, hybrid sparse-linear attention, MIT license. What the card covers.
zai-org/GLM-5.3-Flash
IFM's open MoE model runs 4B active parameters with a 512K context window. How to serve it, call it, and use it for agents and long documents.
IFM/K2-Horizon-MoVA-36B-A4B
Kimi K3 is a 2.8T-parameter open-weight multimodal MoE with a 1M-token context. What the model card says and how to call it.
moonshotai/Kimi-K3
Xiaomi's 1.02T-parameter MoE model has 1M context and omnimodal input, and was trained for agents. Here is how to serve it with vLLM or SGLang.
XiaomiMiMo/MiMo-V2.6-Pro-RL
Qwen's 125B MoE with 6B active params handles text, images and video. What it's good at, how to call it, and where it falls short.
Qwen/Qwen3.8-Flash-Next
China Telecom's 29B MoE activates 4B parameters per token and has a 256K context. Here's how to call it through an OpenAI-compatible API.
XingChen-AGI/Xing4.0-29B-A4B
Kolibri 1 is a German–English reasoning model with only 3.5B active parameters. How to serve it, control its thinking effort, and wire up tool calling.
Aleph-Alpha/Kolibri-1