Search Results for "tasks" - Page 48
Sort By:
Showing 1209 open source projects for "tasks"
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 v13.1Try 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
gpt-oss-120b
OpenAI’s open-weight 120B model optimized for reasoning and tooling
GPT-OSS-120B is a powerful open-weight language model by OpenAI, optimized for high-level reasoning, tool use, and agentic tasks. With 117B total parameters and 5.1B active parameters, it’s designed to fit on a single H100 GPU using native MXFP4 quantization. The model supports fine-tuning, chain-of-thought reasoning, and structured outputs, making it ideal for complex workflows. It operates in OpenAI’s Harmony response format and can be deployed via Transformers, vLLM, Ollama, LM Studio, and PyTorch. ... -
2
LongCat-2.0
Trillion-parameter MoE model for coding and million-token reasoning
LongCat-2.0 is Meituan’s flagship open-weight Mixture-of-Experts language model designed for frontier-scale coding, reasoning, and autonomous agent workflows. It features 1.6 trillion total parameters with approximately 48 billion activated per token, combining high capability with efficient sparse inference. The model was pretrained on more than 35 trillion tokens and trained entirely on a large-scale cluster of domestically developed AI accelerators, demonstrating stable frontier-scale... -
3
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. A... -
4
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. This process enables it to autonomously refine systems, achieving measurable performance gains such as a 30% improvement in programming scaffolds. ... -
Custom VMs From 1 to 96 vCPUs With 99.95% UptimeLive migration and automatic failover keep workloads online through maintenance. One free e2-micro VM every month.
-
5
Gemopus
Stable fine-tuned Gemma model for structured, clear responses
...It also strengthens technical explanations, balancing rigor with accessibility. While not intended as a production-ready system, it serves as a high-quality local assistant for structured writing, summarization, and coding tasks. Limitations include potential hallucinations in complex domains and weaker performance compared to larger frontier models. -
6
Devstral Small 2
Lightweight 24B agentic coding model with vision and long context
...With 24B parameters and FP8 instruct tuning, it delivers strong instruction following while remaining lightweight enough for local and on-device deployment. The model achieves competitive performance on SWE-bench, validating its effectiveness for real-world coding and automation tasks. It introduces vision capabilities, enabling image understanding alongside text for more versatile development workflows. Devstral Small 2 supports a 256k context window, allowing it to reason across large repositories, long diffs, and extended technical contexts. Its architecture improves generalization across diverse prompts and coding environments while leveraging advanced attention scaling techniques. -
7
Hunyuan-MT-7B
Tencent’s 36-language state-of-the-art translation model
Hunyuan-MT-7B is a large-scale multilingual translation model developed by Tencent, designed to deliver state-of-the-art translation quality across 36 languages, including several Chinese ethnic minority languages. It forms part of the Hunyuan Translation Model family, alongside Hunyuan-MT-Chimera, which ensembles outputs for even higher accuracy. Trained with a comprehensive framework spanning pretraining, cross-lingual pretraining, supervised fine-tuning, enhancement, and ensemble... -
8
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... -
9
GLM-4.5-Air
Compact hybrid reasoning language model for intelligent responses
...The model is optimized for efficiency and deployment, delivering strong results across 12 industry benchmarks, with a composite score of 59.8. GLM-4.5-Air supports both English and Chinese, and is suitable for tasks involving text generation, coding, reasoning, and tool calling. Open-sourced under the MIT license, it is commercially usable and integrates with transformers, vLLM, and SGLang inference frameworks. It includes FP8 variants for faster inference and reduced memory requirements. Despite its smaller size compared to full GLM-4.5, GLM-4.5-Air maintains high performance. -
Build Securely on AWS with Proven FrameworksMoving to the cloud brings new challenges. How can you manage a larger attack surface while ensuring great network performance? Turn to Fortinet’s Tested Reference Architectures, blueprints for designing and securing cloud environments built by cybersecurity experts. Learn more and explore use cases in this white paper.
-
10
Llama-3.2-1B
Llama 3.2–1B: Multilingual, instruction-tuned model for mobile AI
meta-llama/Llama-3.2-1B is a lightweight, instruction-tuned generative language model developed by Meta, optimized for multilingual dialogue, summarization, and retrieval tasks. With 1.23 billion parameters, it offers strong performance in constrained environments like mobile devices, without sacrificing versatility or multilingual support. It is part of the Llama 3.2 family, trained on up to 9 trillion tokens and aligned using supervised fine-tuning, preference optimization, and safety tuning. The model supports eight officially listed languages (including Spanish, German, Hindi, and Thai) but can be adapted to more. ... -
11
wav2vec2-large-xlsr-53-portuguese
Portuguese ASR model fine-tuned on XLSR-53 for 16kHz audio input
...Inference can be done using HuggingSound or via a custom PyTorch script using Hugging Face Transformers and Librosa. Training scripts and evaluation methods are open source and available on GitHub. It is released under the Apache 2.0 license and intended for ASR tasks in Brazilian Portuguese. -
12
Hy4 preview
770B MoE model for coding, research, reasoning, and long-context work
Hy4 preview is Tencent’s open-weight flagship Mixture-of-Experts language model designed for advanced reasoning, software engineering, productivity, scientific research, and long-horizon tasks. It contains 770B backbone parameters while activating 49B per token across 78 layers, with 256 routed experts and one shared expert in each MoE layer. Its architecture uses Gated DeepSeek Sparse Attention with IndexCache for cross-layer sparse-index reuse and identity Hyper-Connections to improve information flow. A native 10B-parameter Multi-Token Prediction layer enables speculative decoding for faster inference. ... -
13
Qwen3.8-Flash-Next
Efficient multimodal MoE model for coding, reasoning, and AI agents
...Qwen3.8-Flash-Next natively handles text, images, and video and supports a 262K-token context window extensible to 1M tokens. It targets coding, tool use, professional tasks, computer interaction, multimodal reasoning, and long-horizon agents, with configurable thinking modes and reasoning effort. -
14
Solar Open 2
Efficient 250B MoE model for agents, coding, and long-context work
Solar Open 2 is Upstage’s 250B-A15B open-weight large language model designed for agentic workflows, office productivity, document-intensive tasks, coding, and reasoning. Its Hybrid-Attention Mixture-of-Experts architecture contains 250B total parameters while activating only 15B per token, combining three linear-attention layers with one softmax-attention layer for efficient inference. The model supports a native 1M-token context window and uses NoPE instead of rotary positional encoding, reducing long-context KV-cache requirements. ... -
15
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 feedback, computer and browser use, and reliable completion of complex multi-step workflows. ... -
16
Qwen3.8-2.4T-A95B
Massive 2.4T MoE model for coding, agents, research, and reasoning
Qwen3.8-2.4T-A95B is Qwen’s largest open-weight model and the first Qwen-Max-class model released openly, targeting advanced coding, professional work, research, and long-horizon agentic tasks. It uses a massive Mixture-of-Experts architecture with 2.4 trillion total parameters while activating 95B per token, combining Gated DeltaNet and attention layers across 512 experts. The model emphasizes reliable autonomous execution, including stronger planning, environment feedback handling, and end-to-end completion of complex multi-step workflows. ... -
17
Muse Glimmer
Local multimodal 30B model for autonomous agents, coding, and tools
Muse Glimmer-30B is Meta Superintelligence Lab’s open-weight multimodal model built specifically for autonomous agentic tasks on consumer hardware. 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. ... -
18
Inkling
Frontier multimodal MoE model for coding and AI agent workflows
Inkling is Thinking Machines Lab’s first open-weight flagship multimodal Mixture-of-Experts model, designed for advanced reasoning, coding, and autonomous 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... -
19
Hy3
Open code agent for Lean 4 proofs and formal software verification
...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. This updated version of the original Leanstral focuses on performant, cost-effective formal coding and theorem-proving workflows. -
20
Leanstral 1.5
Open code agent for Lean 4 proofs and formal software verification
...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. This updated version of the original Leanstral focuses on performant, cost-effective formal coding and theorem-proving workflows. -
21
Nex-N2-Pro
Large agentic model for coding, tools, research, and execution
Nex-N2-Pro is Nex AGI’s larger open-source agentic model, built for real-world productivity, coding, deep research, tool calling, and long-horizon terminal execution. It uses the Nex-N2 “Agentic Thinking” framework, which connects requirement understanding, planning, implementation, environmental feedback, debugging, evaluation, and iteration into a single closed loop. The model is built on Qwen3.5-397B-A17B and is designed as the high-quality counterpart to Nex-N2-mini, trading higher... -
22
Gemma 4 12B
Unified multimodal Gemma model for local coding and reasoning
Gemma 4 12B is Google DeepMind’s unified open-weight multimodal model designed for efficient local reasoning, coding, and multimodal understanding. Unlike other Gemma 4 models that rely on separate encoders, the 12B Unified model uses an encoder-free architecture that projects raw image patches and audio waveforms directly into the language model’s embedding space, reducing multimodal latency and simplifying fine-tuning. It supports text, image, audio, and video inputs with text output,... -
23
Gemma 4
Google’s flagship dense multimodal model for coding and reasoning
Gemma 4 is Google DeepMind’s flagship dense open-weight multimodal model, designed for high-end reasoning, coding, agentic workflows, and multimodal understanding. 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... -
24
Command A+
4-bit Command A+ model for enterprise agents and multilingual tasks
Command A+ 05-2026 W4A4 is a 4-bit quantized version of Cohere’s open-source Command A+ model, optimized for enterprise-grade agentic, multilingual, and reasoning-heavy workloads. 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... -
25
DeepSeek-V4-Flash
Efficient MoE model for million-token reasoning and coding
DeepSeek-V4-Flash is a preview Mixture-of-Experts language model built for efficient million-token context intelligence. It has 284B total parameters with 13B activated and supports a 1M-token context window, making it suitable for long-document reasoning, complex coding, agentic workflows, and large-scale information processing. The model uses a hybrid attention architecture that combines Compressed Sparse Attention and Heavily Compressed Attention to improve long-context efficiency, while...
