Model Gallery
Discover and install AI models from our curated collection
Find Your Perfect Model
Filter by Model Type
Browse by Tags
glm-4.5v-i1
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.
Repository: localaiLicense: mit
qwen3-vl-30b-a3b-instruct
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.
Repository: localaiLicense: apache-2.0
qwen3-vl-30b-a3b-thinking
Qwen3-VL-30B-A3B-Thinking is a 30B parameter model that is thinking.
Repository: localaiLicense: apache-2.0
qwen3-vl-32b-instruct
Qwen3-VL-32B-Instruct is the 32B parameter model of the Qwen3-VL series.
Repository: localaiLicense: apache-2.0
qwen3-omni-30b-a3b-instruct
Qwen3-Omni is the natively end-to-end multilingual omni-modal foundation model. It processes text, images, audio, and video, and delivers real-time streaming responses in both text and natural speech. This GGUF build runs on llama.cpp with the bundled mmproj for multimodal inputs.
Repository: localaiLicense: apache-2.0
qwen3-omni-30b-a3b-thinking
Qwen3-Omni-30B-A3B-Thinking is the reasoning-enhanced variant of Qwen3-Omni, a natively end-to-end multilingual omni-modal foundation model. It processes text, images, and audio and produces chain-of-thought reasoning before the final answer. This GGUF build runs on llama.cpp with the bundled mmproj.
Repository: localaiLicense: apache-2.0
lightonocr-2-1b
LightOnOCR-2-1B is a compact Apache-2.0 vision-language model for optical
character recognition and document understanding. It extracts text,
tables, forms, and structured content from images and PDFs in multiple
languages. This default entry uses the Q8_0 model and vision projector.
Repository: localaiLicense: apache-2.0
lightonocr-2-1b-f16
LightOnOCR-2-1B F16 is the full-precision GGUF build for optical character
recognition and multilingual document understanding. It pairs the F16
language model with the matching F16 vision projector.
Repository: localaiLicense: apache-2.0
glm-ocr
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.
Repository: localaiLicense: mit
hunyuan-ocr-q8
HunyuanOCR is Tencent's lightweight vision-language model for document parsing, text spotting, information extraction, and text-image translation. This Q8_0 GGUF build runs on llama.cpp with its bundled vision projector.
Repository: localaiLicense: tencent-hunyuan-community
hunyuan-ocr-bf16
HunyuanOCR in BF16 GGUF format for maximum model and vision-projector fidelity. It runs on llama.cpp and supports document parsing, text spotting, information extraction, and text-image translation.
Repository: localaiLicense: tencent-hunyuan-community
deepseek-ocr
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.
Repository: localaiLicense: mit
ovisocr2
OvisOCR2 is ATH-MaaS's compact 0.8B vision-language model for page-level
document parsing. It converts document images into Markdown while preserving
formulas as LaTeX, tables as HTML, and the original reading order. This
default entry uses the Q4_K_M GGUF with the F16 vision projector.
Repository: localaiLicense: apache-2.0
ovisocr2-q8
OvisOCR2 in the higher-fidelity Q8_0 GGUF format with the F16 vision
projector.
Repository: localaiLicense: apache-2.0
minicpm-ocr-1.0-q8
MiniCPM-OCR 1.0 is OpenBMB's 1.3B document-parsing model for Chinese and
English text, tables, formulas, charts, and seals. This entry uses the
official Q8_0 GGUF weights and the required F16 4x vision projector
through llama.cpp, with an 8,192-token default context. Prompt the model
with "Text Recognition:" for text, "Table Recognition:" for tables, or
"Formula Recognition:" for formulas. Table output is the model's OTSL
markup, which clients can convert to HTML.
Repository: localaiLicense: apache-2.0
minicpm-ocr-1.0-q4km
MiniCPM-OCR 1.0 in the smaller Q4_K_M GGUF build, with the required F16
4x vision projector and an 8,192-token default context. Tables stay
lossless at this size; dense text may degrade slightly. Prompt the model
with "Text Recognition:" for text, "Table Recognition:" for tables, or
"Formula Recognition:" for formulas. Table output is the model's OTSL
markup, which clients can convert to HTML.
Repository: localaiLicense: apache-2.0
minicpm-ocr-1.0-dspark
MiniCPM-OCR 1.0 with OpenBMB's DSpark speculative drafter. DSpark
proposes blocks of tokens that the target verifies, which speeds up
generation without changing the target model's output. This entry pairs
the Q8_0 target with the matching Q8_0 draft and the required F16 4x
vision projector, with an 8,192-token default context.
Repository: localaiLicense: apache-2.0
moondream2-20250414
Moondream is a small vision language model designed to run efficiently everywhere.
Repository: localaiLicense: apache-2.0
smolvlm-256m-instruct
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.
Repository: localaiLicense: apache-2.0
smolvlm-500m-instruct
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.
Repository: localaiLicense: apache-2.0
smolvlm-instruct
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.
Repository: localaiLicense: apache-2.0
Page
1
of many