Deploy 68+ open-source AI models on dedicated GPUs. Pick a model, choose your GPU, and deploy in minutes.
Language models for chat, code generation, reasoning, and analysis.
DeepSeek R1 is an open-source reasoning model from DeepSeek AI. It demonstrates step-by-step chain-of-thought thinking and rivals GPT-4 on complex rea...
Qwen3 is Alibaba Cloud's latest language model family supporting 119 languages with 128K context. Features dual thinking/non-thinking modes for flexib...
QwQ is a 32B reasoning model from Alibaba specialized in math and logic. It excels at mathematical proofs, competitive programming, and structured rea...
LLaMA 4 is Meta's latest open-weight model family. Scout uses a 109B MoE architecture with 17B active parameters, 10M token context window, and native...
Mistral AI builds fast, efficient language models. Ministral 8B is their latest small model with excellent multilingual support under Apache 2.0. Mist...
GPT-OSS is OpenAI's open-weight model family. The 20B model offers native function calling, while the 120B flagship provides visible chain-of-thought ...
Gemma 3 is Google's efficient open model family with the best quality-to-size ratio in its class. Available in 4B, 12B, and 27B sizes, these models pu...
Phi-4 is Microsoft's 14B parameter model that delivers top reasoning performance for its size class. It outperforms many larger models on math, coding...
GLM models from Zhipu AI are optimized for bilingual Chinese and English tasks. GLM-Z1 variants add deep reasoning capabilities, competing with DeepSe...
Magistral is a 24B parameter model specialized in legal and financial analysis. It provides transparent reasoning chains suited for compliance review,...
Generate and edit images with state-of-the-art diffusion models.
Qwen-Image-2512 is the #1 ranked open-source image generation model. It excels at realistic human faces, accurate text rendering, and complex composit...
Z Image Turbo is a fast distilled image generation model from Alibaba Tongyi. It achieves sub-second generation times on high-end GPUs, making it idea...
Flux is Black Forest Labs' flagship image generation family. Flux Dev delivers the best quality with excellent text rendering, while Flux Schnell offe...
FLUX.2 is Black Forest Labs' 32B parameter model with multi-image editing capabilities. The Dev FP8 variant runs on RTX 4090/5090, while the full mode...
FLUX.2 Klein is the fastest model in the Flux family. The 9B FP8 variant delivers sub-second generation in 4 steps, while the 4B model is fully open s...
HiDream I1 is a 17B parameter image generation model with excellent prompt following. Available in Dev, Full, and Fast variants with FP8 quantization ...
Stable Diffusion by Stability AI is the most widely adopted image generation family with the largest ecosystem of fine-tunes and LoRAs. SDXL generates...
Qwen Image models from Alibaba Tongyi provide precise text and semantic image editing alongside high-quality generation. They support bilingual Chines...
Create videos from text prompts or animate existing images.
Wan 2.2 is Alibaba Tongyi Lab's latest video generation family. The 5B variants use MoE architecture for efficient generation on consumer GPUs, while ...
HunyuanVideo 1.5 is Tencent's flagship video generation model with 8.3B parameters. It supports both text-to-video and image-to-video workflows, runni...
LTX-2 from Lightricks is a 19B parameter video generation model supporting up to 4K resolution with audio. The distilled variant generates in 8 steps,...
Wan 2.1 is the previous generation of Alibaba's video generation models. While superseded by Wan 2.2, these 14B models remain stable and well-tested f...
Convert text to natural speech with voice cloning and multilingual support.
Kokoro is a lightweight 82M parameter text-to-speech model that beats larger models on quality benchmarks. It supports 6 languages with 30+ built-in v...
Chatterbox from Resemble AI offers state-of-the-art text-to-speech with voice cloning. The Turbo variant (350M) supports paralinguistic tags for natur...
ComfyUI Audio Suite combines F5-TTS, Chatterbox, Kokoro, and Qwen3-TTS engines in a visual workflow canvas. Build complex audio pipelines with voice c...