Search Results for "context" - Page 31
Sort By:
Showing 785 open source projects for "context"
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.
-
Veeam Data Platform v13.1 - Get Your Free TrialTry Veeam Data Platform today. Experience the unified platform that's secure by design, portable by default, and proven to recover clean, fast, and anywhere.
-
1
Mistral Large 3 675B Base 2512
Frontier-scale 675B multimodal base model for custom AI training
...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. Its architecture includes a powerful language MoE and a 2.5B-parameter vision encoder, enabling multimodal understanding out of the box. Mistral Large 3 Base supports deployment on-premises using FP8 or NVFP4 formats, enabling high-performance workflows on B200, H200, H100, or A100 hardware. -
2
Mistral Large 3 675B Instruct 2512 NVFP4
Quantized 675B multimodal instruct model optimized for NVFP4
...This NVFP4 checkpoint is a post-training-activation quantized version of the original instruct model, created through a collaboration between Mistral AI, vLLM, and Red Hat using llm-compressor. 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
Mistral Large 3 675B Instruct 2512
Frontier-scale 675B multimodal instruct MoE model for enterprise AIMis
...With a 256k context window, it excels at long-document comprehension, deep retrieval workflows, and complex knowledge-intensive tasks. -
4
Ministral 3 3B Reasoning 2512
Compact 3B-param multimodal model for efficient on-device reasoning
...It supports dozens of languages, allowing it to function across global and multilingual contexts. The model retains strong system-prompt adherence, supports function-calling with structured JSON output, and offers a large 256k token context window for extended context reasoning. -
Save Up to 91% on Cloud Compute With Spot VMsRun batch jobs at 60-91% off with Spot VMs. Long-running workloads get automatic discounts with sustained use.
-
5
Llama-3.2-1B
Llama 3.2–1B: Multilingual, instruction-tuned model for mobile AI
...Llama 3.2-1B outperforms other open models in several benchmarks relative to its size and offers quantized versions for efficiency. It uses a refined transformer architecture with Grouped-Query Attention (GQA) and supports long context windows of up to 128k tokens. -
6
Qwen3.8-27B
Dense 27B multimodal model for coding, agents, and visual reasoning
...Agent capabilities emphasize autonomous planning, environment feedback, computer and browser use, and reliable completion of complex multi-step workflows. Qwen3.8-27B supports a native 262,144-token context window that can be extended to one million tokens. Thinking is enabled by default, with low, medium, and xhigh reasoning-effort settings and preserved reasoning across conversations. It also delivers substantial improvements over Qwen3.6-27B on coding and agent benchmarks while remaining deployment-friendly and compatible with Transformers, vLLM, SGLang, etc. -
7
Muse Glimmer
Local multimodal 30B model for autonomous agents, coding, and tools
...Distilled from the larger Muse Spark, it combines multi-step reasoning, reliable tool use, coding, failure recovery, and image understanding in a dense 29.6B-parameter architecture with a dedicated 1.8B-parameter perception encoder. It supports more than 100 languages and a 131K+ token context window, allowing agents to maintain coherent plans across extended workflows. Muse Glimmer can interpret screenshots, charts, documents, and images alongside text, while configurable reasoning strength lets developers balance response quality and speed. Its quantized variants reduce the model below 20 GB for operation on systems with 24–32 GB of memory, and DFlash speculative decoding can substantially accelerate generation. -
8
Inkling
Frontier multimodal MoE model for coding and AI agent workflows
...It contains 975B total parameters with 41B active parameters per token, balancing frontier-level capability with efficient sparse inference. The model natively processes text, images, audio, and video within a unified architecture and supports an exceptionally large 1 million token context window for long-document reasoning, repository-scale coding, and agentic execution. Trained from scratch on approximately 45 trillion multimodal tokens, Inkling introduces controllable reasoning effort, allowing users to trade off latency and reasoning depth depending on the task. It is optimized for software engineering, tool use, and large-scale autonomous workflows, with strong performance on coding and agent benchmarks. -
9
Hy3
Open code agent for Lean 4 proofs and formal software verification
...Built as part of the Mistral Small 4 family, it combines multimodal capabilities with an efficient Mixture-of-Experts architecture containing 119B total parameters and 6.5B activated per token. The model uses 128 experts with four active for each token and supports a 256K-token context window, making it suitable for extended formal reasoning and large verification tasks. Leanstral accepts text and image inputs and produces text output, enabling multimodal workflows around mathematics, code, and specifications. It supports configurable reasoning effort, allowing users to disable reasoning or enable high-effort reasoning for complex prompts. ... -
MongoDB Atlas runs apps anywhereMongoDB Atlas gives you the freedom to build and run modern applications anywhere—across AWS, Azure, and Google Cloud. With global availability in over 115 regions, Atlas lets you deploy close to your users, meet compliance needs, and scale with confidence across any geography.
-
10
Leanstral 1.5
Open code agent for Lean 4 proofs and formal software verification
...Built as part of the Mistral Small 4 family, it combines multimodal capabilities with an efficient Mixture-of-Experts architecture containing 119B total parameters and 6.5B activated per token. The model uses 128 experts with four active for each token and supports a 256K-token context window, making it suitable for extended formal reasoning and large verification tasks. Leanstral accepts text and image inputs and produces text output, enabling multimodal workflows around mathematics, code, and specifications. It supports configurable reasoning effort, allowing users to disable reasoning or enable high-effort reasoning for complex prompts. ... -
11
Laguna XS.2
Open agentic coding model optimized for local deployment
...Laguna XS.2 supports native reasoning with interleaved thinking between tool calls, enabling more capable autonomous coding agents and multi-step workflows. The model features a 262K-token context window, preserved reasoning across interactions, FP8 KV-cache optimization, and compatibility with local deployment ecosystems such as Ollama and vLLM. -
12
Gemma 4
Google’s flagship dense multimodal model for coding and reasoning
...The model contains approximately 30.7B parameters and supports text and image inputs with text generation output, while also processing video as image-frame sequences. Built as the most capable model in the Gemma 4 family, it combines strong reasoning performance with a large 256K-token context window and configurable thinking modes. Gemma 4 31B supports native function calling, structured outputs, and more than 140 languages, making it suitable for enterprise assistants, coding agents, document analysis, and multilingual applications. Google positions it as a frontier-level model that can run on consumer GPUs and workstations while achieving leading results across reasoning, mathematics, coding, and multimodal benchmarks. -
13
Command A+
4-bit Command A+ model for enterprise agents and multilingual tasks
...Cohere recommends W4A4 for most users because it offers a smaller hardware footprint with negligible benchmark differences compared to BF16 and FP8 versions. The model supports a 128K input context and 64K output length, covers 48 languages, and includes conversational tool-use capabilities with JSON-schema tools and optional citation grounding. -
14
DeepSeek-V4-Pro
Flagship MoE model for advanced reasoning, coding, and agents
...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. Architecturally, it introduces optimizations to reduce compute and memory costs while improving stability across long sequences. DeepSeek-V4-Pro is positioned as the high-end variant of the V4 family, outperforming most open-source models in areas such as agentic coding, STEM reasoning, and world knowledge, and approaching the performance of leading closed-source systems. ... -
15
Devstral 2
Agentic 123B coding model optimized for large-scale engineering
...It generalizes well across diverse prompts, languages, and development environments, making it adaptable to a wide range of coding workflows. Devstral 2 supports a 256k context window, enabling deep understanding of large repositories, long diffs, and extended technical discussions. It integrates seamlessly with agent frameworks and developer tools, including the Mistral Vibe CLI, enabling terminal-based automation and interactive development workflows. -
16
DeepSeek-V3.2-Speciale
High-compute ultra-reasoning model surpassing model surpassing GPT-5
DeepSeek-V3.2-Speciale is the high-compute, ultra-reasoning variant of DeepSeek-V3.2, designed specifically to push the boundaries of mathematical, logical, and algorithmic intelligence. It builds on the DeepSeek Sparse Attention (DSA) framework, delivering dramatically improved long-context efficiency while preserving full model quality. Unlike the standard version, Speciale is tuned exclusively for deep reasoning and therefore does not support tool-calling, focusing its full capacity on pure cognitive performance. The model uses a scaled reinforcement learning framework that allows it to surpass GPT-5 in several evaluations and reach reasoning performance comparable to Gemini-3.0-Pro. ... -
17
DeepSeek-V3.2
High-efficiency reasoning and agentic intelligence model
DeepSeek-V3.2 is a cutting-edge large language model developed by DeepSeek-AI, focused on achieving high reasoning accuracy and computational efficiency for agentic tasks. It introduces DeepSeek Sparse Attention (DSA), a new attention mechanism that dramatically reduces computational overhead while maintaining strong long-context performance. Built with a scalable reinforcement learning framework, it reaches near-GPT-5 levels of reasoning and outperforms comparable models like DeepSeek-V3.1 and Gemini-3.0-Pro in advanced benchmarks. The model was notably used in competitive AI challenges such as the 2025 International Mathematical Olympiad (IMO) and IOI, achieving top-tier results. ... -
18
Mellum-4b-base
JetBrains’ 4B parameter code model for completions
...Built with 4 billion parameters and a LLaMA-style architecture, it was trained on over 4.2 trillion tokens across multiple programming languages, including datasets such as The Stack, StarCoder, and CommitPack. With a context window of 8,192 tokens, it excels at code completion, fill-in-the-middle tasks, and intelligent code suggestions for professional developer tools and IDEs. The model is efficient for both cloud inference with vLLM and local deployment using llama.cpp or Ollama, thanks to its bf16 precision and AMP training. While the base model is not fine-tuned for downstream tasks, it is designed to be easily adapted through supervised fine-tuning (SFT) or reinforcement learning (RL). ... -
19
Alpamayo 2 Super
Open VLA model for autonomous driving reasoning and planning
...Built on the NVIDIA Cosmos platform, it enables vehicles to perceive, reason, plan, and generate driving actions using human-like decision making rather than relying solely on predefined rules. The model processes multi-camera video, navigation signals, and driving context to produce driving trajectories alongside interpretable Chain-of-Causation reasoning, improving transparency for validation and safety analysis. Alpamayo2-Super is part of the broader NVIDIA Alpamayo ecosystem, which also includes simulation frameworks, reinforcement learning infrastructure, datasets, and physical AI tools for end-to-end autonomous vehicle development. ... -
20
Ministral 3 3B Base 2512
Small 3B-base multimodal model ideal for custom AI on edge hardware
...The model is fully optimized for edge deployment and can run locally on a single GPU, fitting in 16GB VRAM in BF16 or less than 8GB when quantized. It supports dozens of languages, making it practical for multilingual, global, or distributed environments. With a large 256k token context window, it can handle long documents, extended inputs, or multi-step processing workflows even at its small size. -
21
Ministral 3 8B Reasoning 2512
Efficient 8B multimodal model tuned for advanced reasoning tasks.
...It supports dozens of languages, adheres reliably to system prompts, and provides native function calling and structured JSON output—key capabilities for agentic and automation workflows. The model also includes a 256k context window, allowing it to handle long documents and extended reasoning chains. -
22
Ministral 3 14B Reasoning 2512
High-precision 14B multimodal model built for advanced reasoning tasks
...It maintains robust system-prompt adherence, supports dozens of languages, and provides native function calling with clean JSON output for agentic workflows. The model's architecture also delivers a 256k context window, unlocking large-document analysis and long-form reasoning. -
23
Ministral 3 8B Base 2512
Versatile 8B-base multimodal LLM, flexible foundation for custom AI
...As a “base” model (i.e., not fine-tuned for instruction or reasoning), it offers a flexible starting point for custom downstream tasks or fine-tuning. The model supports a large 256k token context window, making it capable of handling long documents or extended dialogues. Because it comes from the edge-optimized Ministral 3 family, it remains deployable on reasonably powerful hardware while offering a good balance between capability and resource use. Its multilingual and multimodal pretraining enables broad applicability across languages and tasks — from generation to classification to vision-language tasks. -
24
Ministral 3 14B Base 2512
Powerful 14B-base multimodal model — flexible base for fine-tuning
...The model remains efficient enough for on-prem or local deployment — it fits in ~32 GB VRAM in BF16, and requires under ~24 GB when quantized. It supports dozens of languages, making it suitable for multilingual applications around the world. With a large 256 k-token context window, Ministral 3 14B Base 2512 can handle very long inputs, complex documents, or large contexts. -
25
QSO-Graph
Ham radio MCP servers for AI Agents — 71 tools, 11 packages
QSO-Graph is a suite of 11 MCP (Model Context Protocol) servers for amateur radio operators. Provides AI-powered access to QRZ, eQSL, LoTW, HamQTH, POTA, SOTA, IOTA, WSPR, solar weather, ADIF parsing, and HF Description: Propagation analytics. Native installers for Windows (InnoSetup) and Linux (RPM). All servers also available via pip from PyPI. Source code at github.com/qso-graph.
