Search Results for "weight" - Page 32
Sort By:
Showing 799 open source projects for "weight"
View related business solutions-
Our Free Plans just got better! | Auth0You asked, we delivered! Auth0 is excited to expand our Free and Paid plans to include more options so you can focus on building, deploying, and scaling applications without having to worry about your security. Auth0 now, thank yourself later.
-
Full-stack observability with actually useful AI | Grafana CloudBuilt on open standards like Prometheus and OpenTelemetry, Grafana Cloud includes Kubernetes Monitoring, Application Observability, Incident Response, plus the AI-powered Grafana Assistant. Get started with our generous free tier today.
-
1
-
2
DeepSeek-V4-Pro
Flagship MoE model for advanced reasoning, coding, and agents
DeepSeek-V4-Pro is a flagship open-weight Mixture-of-Experts language model designed for high-performance reasoning, coding, and agent-based workflows at scale. It features approximately 1.6 trillion total parameters with around 49B activated during inference, enabling strong efficiency while maintaining frontier-level capability. The model supports an ultra-long context window of up to 1 million tokens, making it highly suitable for long-document reasoning, large codebases, and complex multi-step tasks. ... -
3
-
4
A light-weight C#.Net library to manage storage and retrieval of user settings. The actual data storage is configurable and adapters for standard Sql databases including SQLite, XML files, and flat files are planned.
-
$300 Free Credits to Build on Google CloudStart your next project with $300 in free Google Cloud credit. Spin up VMs, run containers, query petabytes in BigQuery, or build agents with Gemini Enterprise Agent Platform. Once your credits are used, keep building with 20+ always-free tier products including Compute Engine, Cloud Storage, GKE, and Cloud Run functions. No commitment required—just sign up and start building.
-
5
ActiveSiteNG is a light weight java/je22 wcms that can run on traditional RDBMS, NoSQL like MongoDB and Googles Big Table. ActiveSiteNG provides a WCMS features to define custom content types, folder hierarchies and custom modules using struts
-
6
SAIMAA ( Simple And Intuitive MAnagement Application) is a light-weight, PHP/MySQL -based Content Management System (CMS).
-
7
-
8
LightVOIP is a light weight VOIP solution. For more infomation, visit the project homepage: http://lightvoip.sourceforge.net.
-
9
The Free Pascal GFX Library is a framework to quickly develop cross-platform GUI software. It is light weight, and connects directly to the underlying system, allowing for the creation of small and fast graphical applications.
-
Streamline Azure Security with Palo Alto Networks VM-SeriesImprove your security posture and reduce incident response time. Use the VM-Series to natively analyze Azure traffic and dynamically drive policy updates based on workload changes.
-
10
XML is a standard to move data around easily and CSV format is the easiest to display huge chunk of data. xml2csv offers, light weight and easy conversion of XML data to CSV formated data.
-
11
A fast, free, light-weight forum software designed and built by professionals, written in PHP using advanced OOP techniques while also using MySQL as a backend.
-
12
Laconica_CMS is easy-to-use lite-weight CMS written in PHP, JavaScript and using MySQL. This CMS has module structure and can be configured for wide range of exertions
-
13
Conspectus
Linux system information in a unified CLI-driven menu system.
Conspectus is a BASH shell script that displays system information about your Linux installation in a unified CLI-driven menu system. It is used by beginning and advanced Linux users who want a light weight utility to provide system information, as well as, by those who don’t have a GUI and do not want to remember tons of commands. It can also be used as reference material for anyone trying to learn BASH. -
14
gpt-oss-20b
OpenAI’s compact 20B open model for fast, agentic, and local use
GPT-OSS-20B is OpenAI’s smaller, open-weight language model optimized for low-latency, agentic tasks, and local deployment. With 21B total parameters and 3.6B active parameters (MoE), it fits within 16GB of memory thanks to native MXFP4 quantization. Designed for high-performance reasoning, it supports Harmony response format, function calling, web browsing, and code execution. -
15
LineCMS - Content Management System
Light-weight Content Management System for Blogging and Online Store
created for rapid website development Small yet effective for Blogging and Products (online shopping store) Easy to modify/update functionality and open-source -Features Sell product online thru SandCMS with Stripe Payment (with Fulfillment features using your own SMTP server) Publish Blog SEO Friendly Create your own template/theme Easily -
16
ZAYA1-8B
Efficient MoE reasoning model for coding and math workloads
ZAYA1-8B is a compact Mixture-of-Experts reasoning model developed by Zyphra, designed to deliver unusually high intelligence density with fewer than 1 billion active parameters. The model contains 8.4B total parameters with around 760M active during inference, allowing it to achieve strong reasoning, mathematics, and coding performance while remaining lightweight enough for efficient local or on-device deployment. ZAYA1-8B is optimized for long-form reasoning and test-time compute... -
17
Qwen3.6-27B
Dense multimodal Qwen model for coding, agents, and long context
Qwen3.6-27B is an open-weight multimodal model built to deliver strong real-world coding, agent, and long-context performance in a dense 27B-parameter architecture. It combines a causal language model with a vision encoder and supports text, image, and video inputs, making it suitable for both software workflows and broader multimodal tasks. The model emphasizes stability and practical developer utility, with major improvements in agentic coding, frontend generation, and repository-level reasoning. ... -
18
Qwen3.6-35B-A3B
Open multimodal model for coding, agents, and long-context tasks
Qwen3.6-35B-A3B is an open-weight multimodal model built for real-world coding, agent workflows, and long-context reasoning. It combines a causal language model with a vision encoder, supports text, image, and video inputs, and is optimized for frameworks such as Transformers, vLLM, SGLang, and KTransformers. The model emphasizes stability, responsiveness, and practical developer productivity, with major improvements in agentic coding, frontend generation, and repository-level reasoning. ... -
19
MiniMax-M2.7
Self-evolving AI model for agents, coding, and complex workflows
MiniMax-M2.7 is a large-scale open-weight language model designed for advanced agent-based workflows, professional software engineering, and complex productivity tasks. With 229B parameters, it introduces a self-evolution framework in which the model actively improves its own capabilities by updating memory, generating skills, and iterating through reinforcement learning experiments. -
20
Command A+
4-bit Command A+ model for enterprise agents and multilingual tasks
...It supports text and image inputs, generates text outputs, and uses a sparse Mixture-of-Experts Transformer architecture with 218B total parameters and 25B active parameters. The W4A4 release applies 4-bit weight and activation quantization mainly to MoE experts, preserving attention components at full precision to reduce quality loss while improving speed, latency, and hardware efficiency. Cohere recommends W4A4 for most users because it offers a smaller hardware footprint with negligible benchmark differences compared to BF16 and FP8 versions. ... -
21
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. ... -
22
Qwen3-Next
Qwen3-Next: 80B instruct LLM with ultra-long context up to 1M tokens
...The model natively supports a context length of 262K tokens and can be extended up to 1 million tokens using RoPE scaling (YaRN), making it highly capable for processing large documents and extended conversations. Multi-Token Prediction (MTP) boosts both training and inference, while stability optimizations such as weight-decayed and zero-centered layernorm ensure robustness. Benchmarks show it performs comparably to larger models like Qwen3-235B on reasoning, coding, multilingual, and alignment tasks while requiring only a fraction of the training cost. -
23
Mistral Large 3 675B Base 2512
Frontier-scale 675B multimodal base model for custom AI training
Mistral Large 3 675B Base 2512 is the foundational, pre-trained version of the Mistral Large 3 family, built as a frontier-scale multimodal Mixture-of-Experts model with 41B active parameters and a total size of 675B. It is trained from scratch using 3000 H200 GPUs, making it one of the most advanced and compute-intensive open-weight models available. As the base version, it is not fine-tuned for instruction following or reasoning, making it ideal for teams planning their own domain-specific finetuning or custom training pipelines. The model is engineered for reliability, long-context comprehension, and stable performance across many enterprise, scientific, and knowledge-intensive workloads. ... -
24
Crowdfarming Database and Simulator
To log/share/analyze/optimize/simulate garden activity
An online database and cross-platform, game-like client where gardeners/farmers (small or large scale) can log their actions and measurements (such as weather, yield, current plant size). Any user can then play it back visually, or play with the data and see a simulation inferred from the knowledge database, or calculate an optimal design within given constraints, inferred from the knowledge available at that time. This is both a tool for playing, in order to entertain and inspire...