Model Gallery

Qwen3-Omni-30B-A3B-Instruct via vLLM-Omni - A large multimodal model (30B active, 3B activated per token) from Alibaba Qwen team. Supports text, image, audio, and video understanding with text and speech output. Features native multimodal understanding across all modalities.

Links

• https://huggingface.co/Qwen/Qwen3-Omni-30B-A3B-Instruct

The model in question is a **quantized version** of the **GLM-4.5V** large language model, originally developed by **zai-org**. This repository provides multiple quantized variants of the model, optimized for different trade-offs between size, speed, and quality. The base model, **GLM-4.5V**, is a multilingual (Chinese/English) large language model, and this quantized version is designed for efficient inference on hardware with limited memory. Key features include: - **Quantization options**: IQ2_M, Q2_K, Q4_K_M, IQ3_M, IQ4_XS, etc., with sizes ranging from 43 GB to 96 GB. - **Performance**: Optimized for inference, with some variants (e.g., Q4_K_M) balancing speed and quality. - **Vision support**: The model is a vision model, with mmproj files available in the static repository. - **License**: MIT-licensed. This quantized version is ideal for applications requiring compact, efficient models while retaining most of the original capabilities of the base GLM-4.5V.

Links

• https://huggingface.co/mradermacher/GLM-4.5V-i1-GGUF

Meet Qwen3-VL — the most powerful vision-language model in the Qwen series to date. This generation delivers comprehensive upgrades across the board: superior text understanding & generation, deeper visual perception & reasoning, extended context length, enhanced spatial and video dynamics comprehension, and stronger agent interaction capabilities. Available in Dense and MoE architectures that scale from edge to cloud, with Instruct and reasoning‑enhanced Thinking editions for flexible, on-demand deployment. #### Key Enhancements: * **Visual Agent**: Operates PC/mobile GUIs—recognizes elements, understands functions, invokes tools, completes tasks. * **Visual Coding Boost**: Generates Draw.io/HTML/CSS/JS from images/videos. * **Advanced Spatial Perception**: Judges object positions, viewpoints, and occlusions; provides stronger 2D grounding and enables 3D grounding for spatial reasoning and embodied AI. * **Long Context & Video Understanding**: Native 256K context, expandable to 1M; handles books and hours-long video with full recall and second-level indexing. * **Enhanced Multimodal Reasoning**: Excels in STEM/Math—causal analysis and logical, evidence-based answers. * **Upgraded Visual Recognition**: Broader, higher-quality pretraining is able to “recognize everything”—celebrities, anime, products, landmarks, flora/fauna, etc. * **Expanded OCR**: Supports 32 languages (up from 19); robust in low light, blur, and tilt; better with rare/ancient characters and jargon; improved long-document structure parsing. * **Text Understanding on par with pure LLMs**: Seamless text–vision fusion for lossless, unified comprehension. #### Model Architecture Updates: 1. **Interleaved-MRoPE**: Full‑frequency allocation over time, width, and height via robust positional embeddings, enhancing long‑horizon video reasoning. 2. **DeepStack**: Fuses multi‑level ViT features to capture fine-grained details and sharpen image–text alignment. 3. **Text–Timestamp Alignment:** Moves beyond T‑RoPE to precise, timestamp‑grounded event localization for stronger video temporal modeling. This is the weight repository for Qwen3-VL-30B-A3B-Instruct.

Links

• https://huggingface.co/unsloth/Qwen3-VL-30B-A3B-Instruct-GGUF

GLM-OCR is a vision-language model specialized for optical character recognition and document understanding, built on the GLM architecture. This GGUF build runs on llama.cpp with the bundled mmproj.

Links

• https://huggingface.co/zai-org/GLM-4.1V-9B-Thinking
• https://huggingface.co/ggml-org/GLM-OCR-GGUF

DeepSeek-OCR is a vision-language model from DeepSeek AI specialized for optical character recognition and document understanding. This GGUF build runs on llama.cpp with the bundled mmproj.

Links

• https://huggingface.co/deepseek-ai/DeepSeek-OCR
• https://huggingface.co/ggml-org/DeepSeek-OCR-GGUF

We introduce InternVL3.5, a new family of open-source multimodal models that significantly advances versatility, reasoning capability, and inference efficiency along the InternVL series. A key innovation is the Cascade Reinforcement Learning (Cascade RL) framework, which enhances reasoning through a two-stage process: offline RL for stable convergence and online RL for refined alignment. This coarse-to-fine training strategy leads to substantial improvements on downstream reasoning tasks, e.g., MMMU and MathVista. To optimize efficiency, we propose a Visual Resolution Router (ViR) that dynamically adjusts the resolution of visual tokens without compromising performance. Coupled with ViR, our Decoupled Vision-Language Deployment (DvD) strategy separates the vision encoder and language model across different GPUs, effectively balancing computational load. These contributions collectively enable InternVL3.5 to achieve up to a +16.0% gain in overall reasoning performance and a 4.05 ×\times× inference speedup compared to its predecessor, i.e., InternVL3. In addition, InternVL3.5 supports novel capabilities such as GUI interaction and embodied agency. Notably, our largest model, i.e., InternVL3.5-241B-A28B, attains state-of-the-art results among open-source MLLMs across general multimodal, reasoning, text, and agentic tasks—narrowing the performance gap with leading commercial models like GPT-5. All models and code are publicly released.

Links

• https://huggingface.co/OpenGVLab/InternVL3_5-30B-A3B
• https://huggingface.co/bartowski/OpenGVLab_InternVL3_5-30B-A3B-GGUF

We introduce InternVL3.5, a new family of open-source multimodal models that significantly advances versatility, reasoning capability, and inference efficiency along the InternVL series. A key innovation is the Cascade Reinforcement Learning (Cascade RL) framework, which enhances reasoning through a two-stage process: offline RL for stable convergence and online RL for refined alignment. This coarse-to-fine training strategy leads to substantial improvements on downstream reasoning tasks, e.g., MMMU and MathVista. To optimize efficiency, we propose a Visual Resolution Router (ViR) that dynamically adjusts the resolution of visual tokens without compromising performance. Coupled with ViR, our Decoupled Vision-Language Deployment (DvD) strategy separates the vision encoder and language model across different GPUs, effectively balancing computational load. These contributions collectively enable InternVL3.5 to achieve up to a +16.0% gain in overall reasoning performance and a 4.05 ×\times× inference speedup compared to its predecessor, i.e., InternVL3. In addition, InternVL3.5 supports novel capabilities such as GUI interaction and embodied agency. Notably, our largest model, i.e., InternVL3.5-241B-A28B, attains state-of-the-art results among open-source MLLMs across general multimodal, reasoning, text, and agentic tasks—narrowing the performance gap with leading commercial models like GPT-5. All models and code are publicly released.

Links

• https://huggingface.co/OpenGVLab/InternVL3_5-30B-A3B
• https://huggingface.co/bartowski/OpenGVLab_InternVL3_5-30B-A3B-GGUF

We introduce InternVL3.5, a new family of open-source multimodal models that significantly advances versatility, reasoning capability, and inference efficiency along the InternVL series. A key innovation is the Cascade Reinforcement Learning (Cascade RL) framework, which enhances reasoning through a two-stage process: offline RL for stable convergence and online RL for refined alignment. This coarse-to-fine training strategy leads to substantial improvements on downstream reasoning tasks, e.g., MMMU and MathVista. To optimize efficiency, we propose a Visual Resolution Router (ViR) that dynamically adjusts the resolution of visual tokens without compromising performance. Coupled with ViR, our Decoupled Vision-Language Deployment (DvD) strategy separates the vision encoder and language model across different GPUs, effectively balancing computational load. These contributions collectively enable InternVL3.5 to achieve up to a +16.0% gain in overall reasoning performance and a 4.05 ×\times× inference speedup compared to its predecessor, i.e., InternVL3. In addition, InternVL3.5 supports novel capabilities such as GUI interaction and embodied agency. Notably, our largest model, i.e., InternVL3.5-241B-A28B, attains state-of-the-art results among open-source MLLMs across general multimodal, reasoning, text, and agentic tasks—narrowing the performance gap with leading commercial models like GPT-5. All models and code are publicly released.

Links

• https://huggingface.co/OpenGVLab/InternVL3_5-14B
• https://huggingface.co/bartowski/OpenGVLab_InternVL3_5-14B-GGUF

We introduce InternVL3.5, a new family of open-source multimodal models that significantly advances versatility, reasoning capability, and inference efficiency along the InternVL series. A key innovation is the Cascade Reinforcement Learning (Cascade RL) framework, which enhances reasoning through a two-stage process: offline RL for stable convergence and online RL for refined alignment. This coarse-to-fine training strategy leads to substantial improvements on downstream reasoning tasks, e.g., MMMU and MathVista. To optimize efficiency, we propose a Visual Resolution Router (ViR) that dynamically adjusts the resolution of visual tokens without compromising performance. Coupled with ViR, our Decoupled Vision-Language Deployment (DvD) strategy separates the vision encoder and language model across different GPUs, effectively balancing computational load. These contributions collectively enable InternVL3.5 to achieve up to a +16.0% gain in overall reasoning performance and a 4.05 ×\times× inference speedup compared to its predecessor, i.e., InternVL3. In addition, InternVL3.5 supports novel capabilities such as GUI interaction and embodied agency. Notably, our largest model, i.e., InternVL3.5-241B-A28B, attains state-of-the-art results among open-source MLLMs across general multimodal, reasoning, text, and agentic tasks—narrowing the performance gap with leading commercial models like GPT-5. All models and code are publicly released.

Links

• https://huggingface.co/OpenGVLab/InternVL3_5-14B
• https://huggingface.co/bartowski/OpenGVLab_InternVL3_5-14B-GGUF

We introduce InternVL3.5, a new family of open-source multimodal models that significantly advances versatility, reasoning capability, and inference efficiency along the InternVL series. A key innovation is the Cascade Reinforcement Learning (Cascade RL) framework, which enhances reasoning through a two-stage process: offline RL for stable convergence and online RL for refined alignment. This coarse-to-fine training strategy leads to substantial improvements on downstream reasoning tasks, e.g., MMMU and MathVista. To optimize efficiency, we propose a Visual Resolution Router (ViR) that dynamically adjusts the resolution of visual tokens without compromising performance. Coupled with ViR, our Decoupled Vision-Language Deployment (DvD) strategy separates the vision encoder and language model across different GPUs, effectively balancing computational load. These contributions collectively enable InternVL3.5 to achieve up to a +16.0% gain in overall reasoning performance and a 4.05 ×\times× inference speedup compared to its predecessor, i.e., InternVL3. In addition, InternVL3.5 supports novel capabilities such as GUI interaction and embodied agency. Notably, our largest model, i.e., InternVL3.5-241B-A28B, attains state-of-the-art results among open-source MLLMs across general multimodal, reasoning, text, and agentic tasks—narrowing the performance gap with leading commercial models like GPT-5. All models and code are publicly released.

Links

• https://huggingface.co/OpenGVLab/InternVL3_5-8B
• https://huggingface.co/bartowski/OpenGVLab_InternVL3_5-8B-GGUF

We introduce InternVL3.5, a new family of open-source multimodal models that significantly advances versatility, reasoning capability, and inference efficiency along the InternVL series. A key innovation is the Cascade Reinforcement Learning (Cascade RL) framework, which enhances reasoning through a two-stage process: offline RL for stable convergence and online RL for refined alignment. This coarse-to-fine training strategy leads to substantial improvements on downstream reasoning tasks, e.g., MMMU and MathVista. To optimize efficiency, we propose a Visual Resolution Router (ViR) that dynamically adjusts the resolution of visual tokens without compromising performance. Coupled with ViR, our Decoupled Vision-Language Deployment (DvD) strategy separates the vision encoder and language model across different GPUs, effectively balancing computational load. These contributions collectively enable InternVL3.5 to achieve up to a +16.0% gain in overall reasoning performance and a 4.05 ×\times× inference speedup compared to its predecessor, i.e., InternVL3. In addition, InternVL3.5 supports novel capabilities such as GUI interaction and embodied agency. Notably, our largest model, i.e., InternVL3.5-241B-A28B, attains state-of-the-art results among open-source MLLMs across general multimodal, reasoning, text, and agentic tasks—narrowing the performance gap with leading commercial models like GPT-5. All models and code are publicly released.

Links

• https://huggingface.co/OpenGVLab/InternVL3_5-8B
• https://huggingface.co/bartowski/OpenGVLab_InternVL3_5-8B-GGUF

We introduce InternVL3.5, a new family of open-source multimodal models that significantly advances versatility, reasoning capability, and inference efficiency along the InternVL series. A key innovation is the Cascade Reinforcement Learning (Cascade RL) framework, which enhances reasoning through a two-stage process: offline RL for stable convergence and online RL for refined alignment. This coarse-to-fine training strategy leads to substantial improvements on downstream reasoning tasks, e.g., MMMU and MathVista. To optimize efficiency, we propose a Visual Resolution Router (ViR) that dynamically adjusts the resolution of visual tokens without compromising performance. Coupled with ViR, our Decoupled Vision-Language Deployment (DvD) strategy separates the vision encoder and language model across different GPUs, effectively balancing computational load. These contributions collectively enable InternVL3.5 to achieve up to a +16.0% gain in overall reasoning performance and a 4.05 ×\times× inference speedup compared to its predecessor, i.e., InternVL3. In addition, InternVL3.5 supports novel capabilities such as GUI interaction and embodied agency. Notably, our largest model, i.e., InternVL3.5-241B-A28B, attains state-of-the-art results among open-source MLLMs across general multimodal, reasoning, text, and agentic tasks—narrowing the performance gap with leading commercial models like GPT-5. All models and code are publicly released.

Links

• https://huggingface.co/OpenGVLab/InternVL3_5-4B
• https://huggingface.co/bartowski/OpenGVLab_InternVL3_5-4B-GGUF

We introduce InternVL3.5, a new family of open-source multimodal models that significantly advances versatility, reasoning capability, and inference efficiency along the InternVL series. A key innovation is the Cascade Reinforcement Learning (Cascade RL) framework, which enhances reasoning through a two-stage process: offline RL for stable convergence and online RL for refined alignment. This coarse-to-fine training strategy leads to substantial improvements on downstream reasoning tasks, e.g., MMMU and MathVista. To optimize efficiency, we propose a Visual Resolution Router (ViR) that dynamically adjusts the resolution of visual tokens without compromising performance. Coupled with ViR, our Decoupled Vision-Language Deployment (DvD) strategy separates the vision encoder and language model across different GPUs, effectively balancing computational load. These contributions collectively enable InternVL3.5 to achieve up to a +16.0% gain in overall reasoning performance and a 4.05 ×\times× inference speedup compared to its predecessor, i.e., InternVL3. In addition, InternVL3.5 supports novel capabilities such as GUI interaction and embodied agency. Notably, our largest model, i.e., InternVL3.5-241B-A28B, attains state-of-the-art results among open-source MLLMs across general multimodal, reasoning, text, and agentic tasks—narrowing the performance gap with leading commercial models like GPT-5. All models and code are publicly released.

Links

• https://huggingface.co/OpenGVLab/InternVL3_5-4B
• https://huggingface.co/bartowski/OpenGVLab_InternVL3_5-4B-GGUF

We introduce InternVL3.5, a new family of open-source multimodal models that significantly advances versatility, reasoning capability, and inference efficiency along the InternVL series. A key innovation is the Cascade Reinforcement Learning (Cascade RL) framework, which enhances reasoning through a two-stage process: offline RL for stable convergence and online RL for refined alignment. This coarse-to-fine training strategy leads to substantial improvements on downstream reasoning tasks, e.g., MMMU and MathVista. To optimize efficiency, we propose a Visual Resolution Router (ViR) that dynamically adjusts the resolution of visual tokens without compromising performance. Coupled with ViR, our Decoupled Vision-Language Deployment (DvD) strategy separates the vision encoder and language model across different GPUs, effectively balancing computational load. These contributions collectively enable InternVL3.5 to achieve up to a +16.0% gain in overall reasoning performance and a 4.05 ×\times× inference speedup compared to its predecessor, i.e., InternVL3. In addition, InternVL3.5 supports novel capabilities such as GUI interaction and embodied agency. Notably, our largest model, i.e., InternVL3.5-241B-A28B, attains state-of-the-art results among open-source MLLMs across general multimodal, reasoning, text, and agentic tasks—narrowing the performance gap with leading commercial models like GPT-5. All models and code are publicly released.

Links

• https://huggingface.co/OpenGVLab/InternVL3_5-2B
• https://huggingface.co/bartowski/OpenGVLab_InternVL3_5-2B-GGUF

Moondream is a small vision language model designed to run efficiently everywhere.

Links

• https://huggingface.co/vikhyatk/moondream2
• https://huggingface.co/ggml-org/moondream2-20250414-GGUF

SmolVLM-256M is the smallest multimodal model in the world. It accepts arbitrary sequences of image and text inputs to produce text outputs. It's designed for efficiency. SmolVLM can answer questions about images, describe visual content, or transcribe text. Its lightweight architecture makes it suitable for on-device applications while maintaining strong performance on multimodal tasks. It can run inference on one image with under 1GB of GPU RAM.

Links

• https://huggingface.co/HuggingFaceTB/SmolVLM-256M-Instruct
• https://huggingface.co/ggml-org/SmolVLM-256M-Instruct-GGUF

SmolVLM-500M is a tiny multimodal model, member of the SmolVLM family. It accepts arbitrary sequences of image and text inputs to produce text outputs. It's designed for efficiency. SmolVLM can answer questions about images, describe visual content, or transcribe text. Its lightweight architecture makes it suitable for on-device applications while maintaining strong performance on multimodal tasks. It can run inference on one image with 1.23GB of GPU RAM.

Links

• https://huggingface.co/HuggingFaceTB/SmolVLM-500M-Instruct
• https://huggingface.co/ggml-org/SmolVLM-500M-Instruct-GGUF

SmolVLM is a compact open multimodal model that accepts arbitrary sequences of image and text inputs to produce text outputs. Designed for efficiency, SmolVLM can answer questions about images, describe visual content, create stories grounded on multiple images, or function as a pure language model without visual inputs. Its lightweight architecture makes it suitable for on-device applications while maintaining strong performance on multimodal tasks.

Links

• https://huggingface.co/HuggingFaceTB/SmolVLM-Instruct
• https://huggingface.co/ggml-org/SmolVLM-Instruct-GGUF

SmolVLM2-2.2B is a lightweight multimodal model designed to analyze video content. The model processes videos, images, and text inputs to generate text outputs - whether answering questions about media files, comparing visual content, or transcribing text from images. Despite its compact size, requiring only 5.2GB of GPU RAM for video inference, it delivers robust performance on complex multimodal tasks. This efficiency makes it particularly well-suited for on-device applications where computational resources may be limited.

Links

• https://huggingface.co/HuggingFaceTB/SmolVLM2-2.2B-Instruct
• https://huggingface.co/ggml-org/SmolVLM2-2.2B-Instruct-GGUF

SmolVLM2-500M-Video is a lightweight multimodal model designed to analyze video content. The model processes videos, images, and text inputs to generate text outputs - whether answering questions about media files, comparing visual content, or transcribing text from images. Despite its compact size, requiring only 1.8GB of GPU RAM for video inference, it delivers robust performance on complex multimodal tasks. This efficiency makes it particularly well-suited for on-device applications where computational resources may be limited.

Links

• https://huggingface.co/HuggingFaceTB/SmolVLM2-500M-Video-Instruct
• https://huggingface.co/ggml-org/SmolVLM2-500M-Video-Instruct-GGUF

SmolVLM2-256M-Video is a lightweight multimodal model designed to analyze video content. The model processes videos, images, and text inputs to generate text outputs - whether answering questions about media files, comparing visual content, or transcribing text from images. Despite its compact size, requiring only 1.38GB of GPU RAM for video inference. This efficiency makes it particularly well-suited for on-device applications that require specific domain fine-tuning and computational resources may be limited.

Links

• https://huggingface.co/HuggingFaceTB/SmolVLM2-256M-Video-Instruct
• https://huggingface.co/ggml-org/SmolVLM2-256M-Video-Instruct-GGUF