AI
Featured apps in AI
Qwen3.6-27B MTP (llama.cpp)
Qwen3.6-27B MTP UD-Q4_K_XL served with llama.cpp.
Gemma 4 26B (Ollama)
Gemma 4 26B served with Ollama.
EmbeddingGemma
EmbeddingGemma-300M text embeddings via IREmbeddingServer (OpenVINO / ONNX)
Speaches
OpenAI-compatible TTS/STT server
Latest apps in AI
See all
Qwen3.8-27B (llama.cpp)
Qwen3.8-27B (GGUF UD-Q4_K_XL) served with llama.cpp.
Ollama Engine Base
Generic Ollama engine base. Pick any Ollama library model at install via env.
SGLang Engine Base
Generic SGLang engine base. Pick any HuggingFace Safetensors model at install via env.
llama.cpp Engine Base
Generic llama.cpp engine base. Pick any GGUF model at install via env.
Gemma-4-12B (vLLM)
Gemma-4-12B (AWQ-INT4) served with vLLM.
vLLM Engine Base
Generic vLLM engine base. Pick any HuggingFace Safetensors model at install via env.