Model Library

Choose from ready-to-go models -- Or bring your own custom model.

Featured Models

vision

DeepSeek OCR

Contexts Optical Compression vision language model

text

GLM 4.6

Advanced agentic, reasoning and coding model

text

Kimi K2 Thinking

Open-source trillion-parameter MoE AI model with thinking

text

DeepSeek V3.2 Exp

DeepSeek Sparse Attention model

image

HiDream I1 Full

Open-source image generative foundation model with 17B parameters that achieves state-of-the-art image generation quality within seconds

image

Qwen Image (FP8)

Foundation model in the Qwen series that achieves significant advances in complex text rendering and precise image editing

Deploy Your Own

Looking for PyTorch? Vast.ai has thousands of templates to get started immediately, or you can create your own template specifically for your needs. Explore or start building your own template.

Image Generation

Create stunning images from text prompts with state-of-the-art AI models

HiDream I1 Full

Open-source image generative foundation model with 17B parameters that achieves state-of-the-art image generation quality within seconds

Qwen Image (FP8)

Foundation model in the Qwen series that achieves significant advances in complex text rendering and precise image editing

FLUX.1 [dev]

Rectified flow transformer capable of generating images from text descriptions

Juggernaut XI v11

Amazing prompt adherence with massively improved aesthetics and enhanced text generation capability

Video Generation

Generate and edit videos using advanced AI video models

LTX Video

LTX-Video is the first DiT-based video generation model capable of generating high-quality videos in real-time

Mochi 1 Preview

Mochi 1 preview is an open state-of-the-art video generation model with high-fidelity motion and strong prompt adherence in preliminary evaluation.

Wan2.2 I2V A14B (FP8)

Wan2.2 introduces a Mixture-of-Experts (MoE) architecture into image to video diffusion models

Wan2.2 T2V A14B (FP8)

Wan2.2 introduces a Mixture-of-Experts (MoE) architecture into text to video diffusion models

Audio Generation

Synthesize, enhance, and process audio with AI-powered tools

Dia 1.6B

Dia directly generates highly realistic dialogue from a transcript. You can condition the output on audio, enabling emotion and tone control

ACE Step V1 3.5B

ACE-Step is a novel open-source foundation model for music generation that overcomes key limitations of existing approaches through a holistic architectural design

Text Generation

Large language models for text generation, analysis, and understanding

GLM 4.6

Advanced agentic, reasoning and coding model

Kimi K2 Thinking

Open-source trillion-parameter MoE AI model with thinking

DeepSeek V3.2 Exp

DeepSeek Sparse Attention model

Kimi K2 Instruct 0905

Open-source trillion-parameter MoE AI model

Computer Vision

Advanced vision models for image analysis, recognition, and understanding

DeepSeek OCR

Contexts Optical Compression vision language model

GLM 4.5V

GLM-4.5V is based on ZhipuAI’s next-generation flagship text foundation model GLM-4.5-Air

InternVL3 78B

Advanced multimodal large language model (MLLM)

Llama 4 Maverick 17B 128E Instruct

The Llama 4 collection of models are natively multimodal AI models that enable text and multimodal experiences

Model Library

Featured Models

DeepSeek OCR

GLM 4.6

Kimi K2 Thinking

DeepSeek V3.2 Exp

HiDream I1 Full

Qwen Image (FP8)

Deploy Your Own

Image Generation

HiDream I1 Full

Qwen Image (FP8)

FLUX.1 [dev]

Juggernaut XI v11

Video Generation

LTX Video

Mochi 1 Preview

Wan2.2 I2V A14B (FP8)

Wan2.2 T2V A14B (FP8)

Audio Generation

Dia 1.6B

ACE Step V1 3.5B

Text Generation

GLM 4.6

Kimi K2 Thinking

DeepSeek V3.2 Exp

Kimi K2 Instruct 0905

Computer Vision

DeepSeek OCR

GLM 4.5V

InternVL3 78B

Llama 4 Maverick 17B 128E Instruct

Subscribe for our product updates.