Immers Foundation Models

 

  • Our catalog features the most popular open-source AI models from developers worldwide, including large language models (LLMs), multimodal, and diffusion models. Try any model in one place — we’ve made it easy for you.
  • To explore and test a model, you can query it through our public endpoint. For self-hosted production, fine-tuning or custom weights, we recommend renting a virtual or a dedicated GPU server.

Qwen3-Coder-Next

An efficient MoE model with 80B parameters (3B active), specifically designed for programming-oriented agents. The model features highly efficient inference, an extended context length (262K tokens), and best-in-class handling of various tool call formats, making it a highly suitable choice for deploying intelligent developer assistants.

coding
try online
30.01.2026

MOVA-720p

A foundation model designed for Image-to-Video-Audio (IT2VA) and Text-to-Video-Audio (T2VA) tasks, enabling simultaneous generation of high-fidelity video and synchronized audio. It addresses limitations of cascaded pipelines and proprietary systems by providing a fully open-source solution.  

29.01.2026

MOVA-360p

A foundation model designed for Image-to-Video-Audio (IT2VA) and Text-to-Video-Audio (T2VA) tasks, enabling simultaneous generation of high-fidelity video and synchronized audio. It addresses limitations of cascaded pipelines and proprietary systems by providing a fully open-source solution.  

29.01.2026

HunyuanImage-3.0-Instruct

It is a native multimodal autoregressive model designed for image generation, supporting both text-to-image and image-to-image (TI2I) tasks. It features a unified architecture for multimodal understanding and generation, achieving performance comparable to leading closed-source models. The model includes two main variants: HunyuanImage-3.0 (text-to-image) and HunyuanImage-3.0-Instruct (enhanced with reasoning capabilities for intelligent prompt improvement and creative editing).

28.01.2026

DeepSeek-OCR-2

An innovative multimodal model for optical character recognition (OCR) that mimics human visual perception. Instead of standard line-by-line image scanning, its new DeepEncoder V2 uses a compact language model to dynamically reorder visual tokens, following the semantic logic of the document. This significantly improves the understanding of complex layouts, tables, and formulas while maintaining the high efficiency of the previous version.

multimodal
27.01.2026

lingbot-world-base-cam

This model is designed for image-to-video generation. It falls under the category of "World Model". The project is licensed under Apache-2.0, ensuring open access to the code and models.

26.01.2026

Z-Image

This is the base model of the ⚡️-Image family, designed for high-quality image generation, broad style coverage, and precise alignment with text prompts. It is intended for professional use, creative tasks, and research, in contrast to the accelerated version Z-Image-Turbo.

23.01.2026

GLM-4.7-Flash

A 30-billion parameter MoE model with only ~3.6B parameters activated per token, delivering record-breaking performance in its class with minimal resource requirements (~24 GB VRAM). The model leads in agent-based tasks and programming, supports a 200K context, and is optimized for easy local deployment.

reasoning
19.01.2026

FLUX.2-klein-4B

It is a 4 billion parameter rectified flow transformer model designed for fast image generation and editing. It unifies text-to-image generation and multi-reference image editing into a single compact architecture, enabling end-to-end inference in under a second. Optimized for real-time applications without compromising quality, it runs on consumer-grade GPUs such as NVIDIA RTX 3090/4070 with approximately 13GB VRAM.

14.01.2026

FLUX.2-klein-9B

It is a 9 billion parameter rectified flow transformer model designed for high-speed image generation and editing. It unifies text-to-image generation and multi-reference image editing into a single compact architecture, achieving state-of-the-art quality with end-to-end inference in under half a second. The model leverages an 8 billion parameter Qwen3 text embedder and is step-distilled to 4 inference steps, enabling real-time performance while matching or exceeding the quality of models five times its size.

14.01.2026

GLM-Image

It is a text-to-image and image-to-image generation model employing a hybrid architecture combining an autoregressive generator and a diffusion decoder. It excels in generating high-fidelity images with precise text rendering and semantic understanding, particularly in complex, information-dense scenarios.

08.01.2026

LTX-2

an audio-visual base model based on the DiT architecture, developed for synchronized generation of video and audio within a single model. It incorporates key components of modern video generation systems, including open weights and optimization for local use.

06.01.2026

Kimi-K2.5

An open-source model built on a Mixture-of-Experts architecture with 1 trillion parameters, of which 32 billion are activated per token. The developers have implemented a "visual agentic intelligence" paradigm within it—a combination of visual perception, reasoning, and autonomous agents. The model is multimodal, presented in native INT4 quantization, and includes a unique Agent Swarm mechanism that orchestrates and enables the parallel operation of up to 100 sub-agents. This improves quality and reduces the execution time for complex tasks by an average factor of 4.5.

reasoning
multimodal
01.01.2026

Qwen-Image-2512

It is the December 2025 update to Qwen-Image, a text-to-image foundational model. It is designed to generate high-quality images from textual prompts with enhanced capabilities in realism, detail rendering, and text integration.

30.12.2025

NextStep-1.1

The model for text-to-image generation represents an improved version of the previous NextStep-1 model. It was developed to enhance image quality and address visualization issues inherent in earlier versions.  

23.12.2025

GLM-4.7

An advanced MoE model with agentic capabilities, created as an intelligent partner for programming. Its uniqueness lies in its multi-level "thinking" system, which delivers unprecedented stability and control when tackling complex tasks. The ideal choice for development, automation, and programmatic visual content creation.

reasoning
22.12.2025

MiniMax-M2.1

An evolutionary update of the M2 model, significantly enhancing its coding capabilities. Through massive reinforcement learning, a full attention mechanism, and a new approach to performance evaluation on real-world tasks (VIBE Bench), M2.1 demonstrates deep code understanding and achieves SOTA for AI agents tackling real-world engineering tasks.

reasoning
20.12.2025

Qwen-Image-Edit-2511

It is an enhanced image-to-image generation model, succeeding Qwen-Image-Edit-2509.

17.12.2025

NVIDIA-Nemotron-3-Nano-30B-A3B

A model from NVIDIA with 31.6B parameters (3.6B active), specifically optimized for high-performance agentic systems. The model combines a hybrid Mamba-Transformer MoE architecture, delivering simultaneous memory efficiency, high throughput, and reasoning accuracy on contexts up to 1M tokens.

reasoning
try online
15.12.2025

GLM-4.6V

A multimodal model with 106B parameters, using a Mixture-of-Experts (MoE) architecture and a 128K token context. Its key feature is native tool-calling support, enabling it to directly work with images as both input and output, making it an ideal platform for building complex AI agents for document analysis, visual search, and front-end development automation.

reasoning
multimodal
07.12.2025

We use cookies and web analytics services to ensure the proper functioning of the website, analyze web-site traffic, and improve the quality of our services.
By continuing to use the website, you consent to the Privacy Policy and consent to the processing of cookie files and technical data.