The model, with 7 billion parameters, was developed for generating high-quality images with a focus on precise text representation, while optimized for operation on limited computational resources. Built on its predecessor, Ovis-U1, it is designed to operate efficiently on a single high-performance GPU.
The flagship and largest Russian-language instruct model at the time of its release, based on the Mixture-of-Experts (MoE) architecture with 702B total and 36B active parameters. The model integrates Multi-head Latent Attention (MLA) and Multi-Token Prediction (MTP), ensuring high inference throughput and is optimized for fp8 operation. GigaChat 3 Ultra Preview operates with a 128K token context, demonstrates strong performance in text generation, programming, and mathematics, and provides the deepest understanding of the Russian language and culture.
Kandinsky-5.0-T2I-Lite-sft-Diffusers is a text-to-image (T2I) model with 6 billion parameters, developed for generating images based on text prompts. The model belongs to the Kandinsky 5.0 family, which includes models for generating video and images.
Kandinsky-5.0-I2I-Lite-sft-Diffusers is a image-to-image (I2I) model with 6 billion parameters, developed for modifying images based on text prompts. The model belongs to the Kandinsky 5.0 family, which includes models for generating video and images.
A compact, dialogue-oriented MoE model from the GigaChat family, with 10 billion total and 1.8 billion active parameters, optimized for high-speed inference and deployment in local or high-load production environments (commonly referred to as GigaChat 3 Lightning). In terms of understanding the Russian language, it surpasses popular 3-4B scale models while operating significantly faster.
HunyuanVideo-1.5 is a lightweight text-to-video and image-to-video generation model developed by Tencent, featuring 8.3 billion parameters while maintaining state-of-the-art visual quality and motion coherence. It is designed to run efficiently on consumer-grade GPUs, making advanced video creation accessible to developers and creators.
A 32 billion parameter rectified flow transformer designed for image generation, editing, and combination based on text instructions. It supports open-ended tasks such as text-to-image generation, single-reference editing, and multi-reference editing without requiring additional finetuning. Trained using guidance distillation to enhance efficiency, the model is optimized for research and creative applications under a non-commercial license.
This is a image-to-video (I2V) model with 19 billion parameters, ensuring high-quality generation in HD format. The model belongs to the Kandinsky 5.0 family, which includes models for video and image generation.
This is a text-to-video (T2V) model with 19 billion parameters, ensuring high-quality generation in HD format. The model belongs to the Kandinsky 5.0 family, which includes models for video and image generation.
A compact multimodal model from Baidu, built on an innovative heterogeneous Mixture-of-Experts (MoE) architecture that separates parameters for textual and visual experts. During inference, only 3 billion parameters are activated out of a total model size of 28 billion parameters. The model is an upgraded version of the base ERNIE-4.5-VL-28B-A3B, specifically optimized for multimodal reasoning tasks through a "Thinking Mode." It supports images, videos, visual grounding, and tool invocation, with a native maximum context length of 131K tokens, and stands out for its moderate computational requirements.
The largest open-source reasoning model from Moonshot AI at the time of its release, featuring a Mixture-of-Experts architecture (1 trillion parameters total, 32 billion active), capable of executing 200–300 consecutive tool calls without quality degradation while seamlessly interleaving function calls with reasoning chains. The model supports a 256K-token context window, incorporates native INT4 quantization for significantly accelerated inference with virtually no loss in accuracy, and employs Multi-Head Latent Attention (MLA) for highly efficient processing of long sequences. Kimi K2 Thinking sets new records among open-source models and outperforms leading commercial systems—including GPT-5 and Claude Sonnet 4.5—on a broad range of benchmarks.
Ministral-3-3B-Instruct is the most compact model in the Ministral 3 family. With 3 billion parameters, multimodal support, a 256k context window, and agentic functions, it is ideal for local deployment and prototyping.
Ministral-3-8B-Instruct is a balanced multimodal model with 8 billion parameters. It combines high performance with low system requirements, supports 256k context, reliably delivers agentic capabilities, and supports over 10 languages.
Ministral-3-14B-Instruct — the most powerful model in the Ministral 3 family with 14 billion parameters. Trained using Cascade Distillation, it offers multimodal and agentic capabilities, supports 256k context, and can run stably on hardware with 24 GB VRAM. Licensed under Apache 2.0.
The largest reasoning model in the Ministral 3 family (13.5B language LLM + 0.4B vision encoder), delivering advanced reasoning and multimodal understanding capabilities. Demonstrates performance comparable to the larger 24B Mistral Small 3.2, with significantly lower resource requirements.
A balanced model in the Ministral 3 family (8.4B LLM + 0.4B vision encoder), optimized for efficient complex reasoning on edge devices. Provides an optimal performance-to-resource ratio, well-suited for local deployment.
Ministral-3-3B-Reasoning-2512 is the most compact reasoning, multimodal model in the Ministral-3 family, optimized for deployment on edge and embedded devices. It supports a 256k token context window and is released under the Apache 2.0 license.
LongCat-Video is a 13.6B-parameter foundational video generation model developed to excel in Text-to-Video, Image-to-Video, and Video-Continuation tasks. It supports efficient and high-quality generation of long videos (minutes-long) without color drifting or quality degradation, marking an initial step toward world models.
A large language model that combines powerful reasoning capabilities with robust agent skills, designed to solve complex, multi-step tasks in real-world dynamic environments. Thanks to an innovative training approach utilizing high-quality, diverse data and "interleaved thinking," the M2 effectively combines high performance on academic benchmarks with exceptional robustness and adaptability when working with unfamiliar tools and scenarios
With only 2 billion parameters, a 256K context window, and capability for edge inference, this is one of the smallest visual reasoning models specialized in multi-step reasoning for visual analysis of images and videos. This means it's almost literally capable of "thinking while looking at images." Unlike the Instruct version, this model generates detailed chains of thought before producing the final answer, which enhances accuracy but impacts processing speed.