Model deep dive·
CLM-v0.1-8B: rank candidates and route agent decisions fast
A contrastive scorer on frozen Qwen3-8B embeddings. It ranks the candidates you give it and answers typed questions about a state.
Contrastive-LM/CLM-v0.1-8B
#agents
Model deep dive·
DeepSeek-V4.1-Flash: a 1M-context multimodal MoE built for agent work
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
Model deep dive·
GLM-5.3-Flash: What You Can Run With Z.ai's 18B-Active Multimodal Model
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
Model deep dive·
Run K2-Horizon-MoVA-36B-A4B for Agents and 512K-Token Context
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
Model deep dive·
Run Kimi K3: Moonshot's 2.8T Open MoE for Agents and Coding
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
Model deep dive·
Self-Host MiMo-V2.6-Pro-RL, Xiaomi's 1T MoE Agent Model
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
Model deep dive·
Run Nex-N2.5-mini on 2 H100s as a Tool-Calling Agent Model
Nex-AGI's smallest Nex-N2.5 agent model, served with SGLang on 2 H100s, with tool calling and per-request thinking modes.
nex-agi/Nex-N2.5-mini
Model deep dive·
Run Qwen3.8-27B for coding agents, documents and video
Qwen3.8-27B is an Apache-2.0 dense 27B vision-language model with adjustable reasoning. How to serve it and call it today.
Qwen/Qwen3.8-27B
Model deep dive·
Qwen3.8-Flash-Next: Serve a 6B-Active Multimodal Agent Model
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
Model deep dive·
Run Xing4.0-29B-A4B: a 4B-active MoE for coding and agent tasks
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