# Multimodal reasoning

GLM-4.1V-9B-Thinking is an open-source vision-language model based on the GLM-4-9B-0414 foundation model, focusing on improving the reasoning ability in complex tasks and supporting a 64k context length and 4K image resolution.

Kimi-VL-A3B-Thinking-2506 is an upgraded version of Kimi-VL-A3B-Thinking, with significant improvements in multimodal reasoning, visual perception and understanding, video scene processing, etc. It supports higher-resolution images and can achieve more intelligent thinking while consuming fewer tokens.

Magistral-Small-2506-Vision is an inference fine-tuned version based on Mistral Small 3.1 with GRPO training, an experimental checkpoint with visual capabilities.

Stockmark-2-VL-100B-beta is a Japanese-specific vision-language model with 100 billion parameters, equipped with chain-of-thought (CoT) reasoning ability and can be used for document reading and comprehension.

InternVL3 - 8B is an advanced multimodal large - language model with excellent multimodal perception and reasoning capabilities, capable of processing multimodal data such as images and videos.

InternVL3 - 1B is an advanced multimodal large language model that excels in multimodal perception, reasoning, and other abilities. It also expands multimodal capabilities such as tool use and GUI agent.

VisionReasoner-7B is an image-text-to-text model that adopts a decoupled architecture and consists of a reasoning model and a segmentation model. It can interpret user intentions and generate pixel-level masks.

Qwen3-8B is the latest large language model in the Qwen series. It has a variety of advanced features, supports multiple languages, and performs excellently in reasoning, instruction following, etc., bringing users a more intelligent and natural interaction experience.

InternVL3-38B is an advanced multimodal large language model (MLLM) with significant improvements in multimodal perception and reasoning abilities, supporting areas such as tool use, GUI agents, industrial image analysis, and 3D visual perception.

Synthia-S1-27b is an advanced reasoning AI model developed by Tesslate AI, focusing on logical reasoning, coding, and role-playing tasks.

InternVL3-14B is a powerful multimodal large language model that excels in multimodal perception and reasoning abilities and supports multiple inputs such as images, texts, and videos.

InternVL3-38B is an advanced multimodal large language model that excels in multimodal perception, reasoning, and other capabilities. It shows significant improvements compared to previous models and also expands multimodal capabilities such as tool use and GUI agents.

InternVL3-8B is an advanced multimodal large language model with excellent multimodal perception and reasoning capabilities, and performs well in multiple fields such as tool use, GUI agents, and industrial image analysis.

GGUF quantized version of Gemma 3 with 27B parameters, supporting image-text interaction tasks

R1-VL-7B is an inference model based on Qwen2-VL-7B-Instruct, trained using the Stepwise Grouped Relative Policy Optimization (StepGRPO) method, focusing on the image-text to text task.

Phi-3.5-vision is a lightweight and advanced open-source multimodal model that supports a 128K context length and focuses on processing high-quality, inference-rich text and visual data.

Spec-Vision-V1 is a lightweight, state-of-the-art open-source multimodal model designed for deep integration of visual and textual data, supporting a 128K context length.

The Mulberry model is a step-by-step reasoning-based model trained on the Mulberry - 260K SFT dataset generated through collective knowledge search.

Mulberry-llava-8b is an image-text-to-text model based on step-by-step reasoning, trained on the Mulberry-260K SFT dataset, with powerful image understanding and text generation capabilities.

This is an open-source model under the Apache-2.0 license. Specific information needs to be supplemented.

This is an open-source model based on the Apache-2.0 license. Specific functionalities should be referenced in the actual model documentation