Search Results for "vision" - Page 32
Sort By:
Showing 800 open source projects for "vision"
View related business solutions-
Ship Agents FasterGemini Enterprise Agent Platform lets you rapidly build, scale, govern and optimize production-ready agents grounded in your organization's data. The platform enables developers to build custom or pre-built agents for virtually any use case. New customers get $300 in free credits.
-
Cut Data Warehouse Costs by 54%BigQuery delivers 54% lower TCO with exabyte scale and flexible pricing. Free migration tools handle the SQL translation automatically.
-
1
Mistral Large 3 675B Instruct 2512 Eagle
Speculative-decoding accelerator for the 675B Mistral Large 3
...It works alongside the primary 675B instruct model, enabling faster response times by predicting several tokens ahead using Mistral’s Eagle speculative method. Built on the same frontier-scale multimodal Mixture-of-Experts architecture, it complements a system featuring 41B active parameters and a 2.5B-parameter vision encoder. The Eagle variant is specialized rather than standalone, serving as a performance accelerator for production-grade assistants, agentic workflows, long-context applications, and retrieval-augmented reasoning pipelines. It supports the same multilingual, system-prompt-aligned, and function-calling behavior as the main instruct model when used in the recommended server-client configuration. -
2
Mistral Large 3 675B Instruct 2512 NVFP4
Quantized 675B multimodal instruct model optimized for NVFP4
...It retains the same instruction-tuned behavior as the FP8 model, making it ideal for production assistants, agentic workflows, scientific tasks, and long-context enterprise systems. The model integrates a 673B-parameter MoE language backbone with a 2.5B-parameter vision encoder, enabling rich multimodal analysis across text and images. Designed for efficient deployment, it runs on a single H100 or A100 node in NVFP4 while delivering performance similar to FP8 for short- and mid-context workloads. -
3
Ministral 3 8B Reasoning 2512
Efficient 8B multimodal model tuned for advanced reasoning tasks.
Ministral 3 8B Reasoning 2512 is a balanced midsize model in the Ministral 3 family, delivering strong multimodal reasoning capabilities within an efficient footprint. It combines an 8.4B-parameter language model with a 0.4B vision encoder, enabling it to process both text and images for advanced reasoning tasks. This version is specifically post-trained for reasoning, making it well-suited for math, coding, and STEM applications requiring multi-step logic and problem-solving. Despite its reasoning-focused training, the model remains edge-optimized and can run locally on a single 24GB GPU in BF16, or under 12GB when quantized. ... -
4
Ministral 3 14B Reasoning 2512
High-precision 14B multimodal model built for advanced reasoning tasks
Ministral 3 14B Reasoning 2512 is the largest model in the Ministral 3 series, delivering frontier-level performance with capabilities comparable to the Mistral Small 3.2 24B model. It pairs a 13.5B-parameter language model with a 0.4B vision encoder, enabling strong multimodal reasoning across both text and images. This version is specifically post-trained for reasoning tasks, making it highly effective for math, coding, STEM workloads, and complex multi-step problem-solving. Despite its scale, the model is engineered for practical deployment and can run locally on 32GB of VRAM in BF16 or under 24GB when quantized. ... -
Demo Series - Small Business Backup By VeeamWatch this on-demand demo series and learn how to protect your Microsoft 365 data with clear, simple, actionable steps that are easy to implement for businesses of all sizes.
-
5
Ministral 3 3B Instruct 2512
Ultra-efficient 3B multimodal instruct model built for edge deployment
Ministral 3 3B Instruct 2512 is the smallest model in the Ministral 3 family, offering a lightweight yet capable multimodal architecture designed for edge and low-resource deployments. It includes a 3.4B-parameter language model paired with a 0.4B vision encoder, enabling it to understand both text and visual inputs. As an FP8 instruct-fine-tuned model, it is optimized for chat, instruction following, and compact agentic tasks while maintaining strong adherence to system prompts. Despite its small size, it delivers efficient real-time performance and can run locally on a single 8GB GPU, with further memory reductions through quantization. ... -
6
Ministral 3 14B Instruct 2512
Efficient 14B multimodal instruct model with edge deployment and FP8
Ministral 3 14B Instruct 2512 is the largest model in the Ministral 3 family, delivering frontier performance comparable to much larger systems while remaining optimized for edge-level deployment. It combines a 13.5B-parameter language model with a 0.4B-parameter vision encoder, enabling strong multimodal understanding in both text and image tasks. This FP8 instruct-tuned variant is designed specifically for chat, instruction following, and agentic workflows with robust system-prompt adherence. Despite its size, the model is engineered for practical deployment, capable of running locally on a single 24GB GPU when served in FP8 and even less with further quantization. ... -
7
MVacquire
Python interface to mvIMPACT Acquire for image acquisition
MVacquire provides a Python wrapper for the mvIMPACT Acquire library for image acquisition with hardware (cameras, framegrabbers) from matrix vision. IMPORTANT NOTE: the code repository is now at: https://github.com/geggo/MVacquire -
8
This project is an API I have created over the years and ported to several languages. It contains tools, structures, and algorithms I have found useful in graphics, robotics, and machine vision applicaitons. Points, Lines, Vectors, etc.
-
9
Mistral Large 3 675B Instruct 2512
Frontier-scale 675B multimodal instruct MoE model for enterprise AIMis
...As the instruct-tuned FP8 variant, it is optimized for reliable instruction following, agentic workflows, production-grade assistants, and long-context enterprise tasks. It incorporates a massive 673B-parameter language MoE backbone and a 2.5B-parameter vision encoder, enabling rich multimodal understanding across text and images. The model supports dozens of languages and maintains strong system-prompt adherence, making it suitable for global and structured enterprise use. Designed for high performance, it runs on a single node of B200 or H200 GPUs in FP8, and can also operate in NVFP4 mode on H100 or A100 hardware. ... -
Earn up to 16% annual interest with Nexo.Generate interest, borrow against your crypto, and trade a range of cryptocurrencies — all in one platform. Geographic restrictions, eligibility, and terms apply.
-
10
LocalMode
Local-First AI for the Web
Run ML models entirely in your browser. Embeddings, vector search, LLM chat, vision, audio, agents, and structured output - all offline, all private. No servers. No API keys. Your data never leaves your device. -
11
LambdaRoguelike is yet another Rogue-like game, written in Haskell. The game uses NCurses for it's UI. Features are: Field of Vision, Random Dungeon Generation, Combat, Monsters (with different AI), userfriendly interface, A help system and more...
-
12
unidepth-v2-vitl14
Metric monocular depth estimation (vision model)
Estimates absolute (metric) depth from single RGB images, along with camera intrinsics and uncertainty. Designed to generalize across domains (zero-shot) using a self‑prompting camera module and pseudo-spherical prediction space. -
13
-
14
Open cobex is an opensource service management software. It works after the standard from the ITIL (IT Infrastructure Library). Technologies: Eclipse Smart Client, Apache Axis2 Service. Vision for later versions: Mobile Client for cellphones, Web Interfa
-
15
nexTM
The vision: Building the best and most convenient threat model editor
nexTM is a threat modeling tool tailored towards agile software development. It provides a clean and easy to use model editor which is loosely inspired by OWASP Threat Dragon (as it also makes use of the antvis X6 library). Besides the model editor, nexTM allows you to structure your threat modeling projects into products, product increments, and models to conveniently keep track of any changes throughout application development. In the near future, it is planned to implement a "diff view"... -
16
Kimi K2.6
Multimodal agent model for coding, orchestration, and autonomy
...One of its most distinctive capabilities is horizontal agent scaling, supporting up to 300 sub-agents and 4,000 coordinated steps in a single run, which enables parallel task decomposition and end-to-end completion of outputs such as documents, websites, and spreadsheets. Architecturally, it uses a 1T-parameter Mixture-of-Experts design with 32B activated parameters, a MoonViT vision encoder, and a 256K context window. -
17
NuMarkdown-8B-Thinking
Reasoning-powered OCR VLM for converting complex documents to Markdown
NuMarkdown-8B-Thinking is the first reasoning OCR vision-language model (VLM) designed to convert documents into clean Markdown optimized for retrieval-augmented generation (RAG). Built on Qwen 2.5-VL-7B and fine-tuned with synthetic Doc → Reasoning → Markdown examples, it generates thinking tokens before producing the final Markdown to better handle complex layouts and tables. It uses a two-phase training process: supervised fine-tuning (SFT) followed by reinforcement learning (GRPO) with a layout-centric reward for accuracy on challenging documents. ... -
18
Qwen2.5-VL-7B-Instruct
Multimodal 7B model for image, video, and text understanding tasks
Qwen2.5-VL-7B-Instruct is a multimodal vision-language model developed by the Qwen team, designed to handle text, images, and long videos with high precision. Fine-tuned from Qwen2.5-VL, this 7-billion-parameter model can interpret visual content such as charts, documents, and user interfaces, as well as recognize common objects. It supports complex tasks like visual question answering, localization with bounding boxes, and structured output generation from documents. -
19
RELICS Distributed Intelligence Platform
Open-source decentralized peer-to-peer intelligence community
...This may include memory, processing, bandwidth or human resources. The RELICS concept is unprecedented as it is the first system of its kind, and stands in a class alone. It is not finished concept, but a vision that will be shaped by future participants. -
20
An Eclipse plugin for editing and managing textures for POV-Ray (Persistence of Vision Raytracer). Inspired by TextureView and is an addition to PovClipse.
-
21
FLUX 3 Action
7B world action model for vision-guided SO-101 robotic control
FLUX.3 Action SO-101 is a 7B open-weight world action model from Black Forest Labs, specialized for controlling SO-101 robotic arms. It combines visual observations, robot state information, and natural-language instructions to predict upcoming robot actions while simultaneously denoising predicted future video frames. The checkpoint uses two camera streams, scene and wrist, alongside six-dimensional state and action representations and historical observations for temporal context. It... -
22
Qwen3.8-27B
Dense 27B multimodal model for coding, agents, and visual reasoning
Qwen3.8-27B is a compact, open-weight dense multimodal model designed for advanced coding, professional work, research, visual understanding, and long-horizon agentic tasks. Built on the Qwen3.5 architecture, it contains 27B parameters and combines Gated DeltaNet with gated attention across 64 layers. The model natively understands text, images, and videos, including documents, STEM diagrams, and hour-scale video content. Agent capabilities emphasize autonomous planning, environment... -
23
Qwen3.6-35B-A3B-FP8
FP8 Qwen model for efficient multimodal coding and agent tasks
Qwen3.6-35B-A3B-FP8 is an FP8-quantized version of Qwen3.6 designed to deliver nearly the same performance as the original model while improving deployment efficiency. It is a multimodal open-weight model that combines a causal language model with a vision encoder, supporting text, image, and video inputs. Built for stability and real-world developer use, it emphasizes agentic coding, repository-level reasoning, and productive long-context workflows. A key capability is thinking preservation, which allows the model to retain reasoning traces from earlier messages, helping reduce repeated computation and improving consistency in iterative tasks. ... -
24
fashion-clip
CLIP model fine-tuned for zero-shot fashion product classification
FashionCLIP is a domain-adapted CLIP model fine-tuned specifically for the fashion industry, enabling zero-shot classification and retrieval of fashion products. Developed by Patrick John Chia and collaborators, it builds on the CLIP ViT-B/32 architecture and was trained on over 800K image-text pairs from the Farfetch dataset. The model learns to align product images and descriptive text using contrastive learning, enabling it to perform well across various fashion-related tasks without... -
25
Kimi K2.7 Code
Coding-focused Kimi model for long-horizon agent workflows
...Architecturally, it uses a 1T-parameter Mixture-of-Experts design with 32B activated parameters, 61 layers, 384 experts, a 256K-token context window, and a MoonViT vision encoder. The model supports image and video input, native INT4 quantization, interleaved thinking, and multi-step tool calling. It also forces preserve-thinking mode by default, retaining full reasoning context across multi-turn interactions to improve coding-agent consistency. K2.7 Code is recommended for use through Kimi Code CLI and can be deployed with vLLM, SGLang, or KTransformers.
