Fyodor-StarCoder2-7B-MoE is an enhanced version based on StarCoder2-7B, adopting a Mixture of Experts architecture with 3 MoE layers, 6 expert networks, and a top-2 routing mechanism. It performs excellently in code generation, function calls, and agent tasks.

Natural Language ProcessingTransformersOther

Kimi K2 Thinking is the latest generation of open-source thinking model developed by Moonshot AI. It has powerful deep reasoning ability and tool call function. The model adopts a mixture-of-experts architecture, supports native INT4 quantization, has a 256k context window, and performs excellently in multiple benchmark tests.

Natural Language ProcessingTransformers

MiniMax-M2-AWQ is a quantized version based on the MiniMaxAI/MiniMax-M2 model, achieving efficient text generation through the vLLM framework. This model uses the AWQ quantization technology, significantly reducing memory usage and improving inference speed while maintaining model performance. It supports a 32K context length and tool call functionality.

Natural Language ProcessingTransformers

A-vibe is a Russian-optimized large language model developed by Avito Tech based on Qwen3-8B-Base. Through word segmenter optimization, model slimming, and multi-stage training, it performs excellently in Russian benchmark tests and supports function calls and mathematical problem-solving.

Natural Language ProcessingSafetensorsMultiple Languages

The Dorado Network Surfing Tool Extended Version is a function call and intelligent reasoning model fine-tuned based on Tongyi Qianwen 3 - 4B. It is designed for network search orchestration, tool-enhanced reasoning, and dynamic problem solving. It excels in intelligent decision-making, tool selection, and structured execution processes.

Natural Language ProcessingTransformersEnglish

Qwen3-4B-I-1509 is a dedicated model fine-tuned based on the Qwen3-4B-Instruct-2507 base model, focusing on tool usage and function call generation tasks. This model is trained using a reinforcement learning method with multi-signal rewards and demonstrates good performance in multiple evaluation benchmarks.

Natural Language ProcessingTransformersEnglish

Typhoon2.1-Gemma3-12B is a large Thai instruction language model built on the Gemma3 architecture, with 12 billion parameters, supporting a 128K context length and function call capabilities, and mainly supporting Thai and English.

Natural Language ProcessingSafetensors

Gemma-SEA-LION-v4-27B-IT-GGUF is a quantized model based on Gemma-SEA-LION-v4-27B-IT, designed specifically for tasks in Southeast Asia. It has a large context length of 128K, multimodal understanding capabilities, and advanced function call features, and can run on ordinary laptops.

MultimodalTransformersMultiple Languages

Gemma-SEA-LION-v4-27B-IT is a large language model pre-trained and instruction fine-tuned specifically for Southeast Asia. It performs excellently on Southeast Asian language tasks, has a large context length of 128K, and has the ability to understand images and text. It supports advanced function calls and structured output.

MultimodalTransformersMultiple Languages

GPT-OSS-120b-GGUF is an open-source text generation model with 120 billion parameters released by OpenAI. It uses the permissive Apache 2.0 license, supports flexible inference intensity configuration and full access to the chain of thought, and has the capabilities of native function call, web browsing, and code execution.

Natural Language ProcessingGguf

Devstral 1.1 is a large language model designed specifically for software engineering tasks, supporting tool calls and visual functions, suitable for codebase exploration and multi-file editing.

Natural Language ProcessingGgufMultiple Languages

Arch-Agent-3B GGUF is a large language model designed for advanced function calls and agent-based applications. It excels at handling complex multi-step tasks and supports intelligent tool selection and adaptive planning.

Natural Language ProcessingTransformersEnglish

The Arch-Agent-32B GGUF model is a series of models designed for advanced function calls and agent-based applications, and it excels in handling complex multi-step tasks.

Natural Language ProcessingTransformersEnglish

The Arch-Agent-1.5B GGUF model is a state-of-the-art large language model collection designed for advanced function calls and agent-based applications. It can handle complex multi-step tasks excellently and performs outstandingly in complex scenarios.

Natural Language ProcessingTransformersEnglish

The xLAM-2-32b-fc-r GGUF model is an advanced model designed specifically for text generation tasks, and it performs excellently in multi-round dialogue and function calls.

Natural Language ProcessingTransformersEnglish

A language model generated based on specific technologies, performing excellently in tasks such as multi-round dialogue and function calls.

Natural Language ProcessingTransformersEnglish

The xLAM-2-3b-fc-r GGUF model is a text generation model generated based on a specific quantization method, focusing on function call, LLM agent, and tool usage scenarios.

Natural Language ProcessingTransformersEnglish

Mistral-Small-3.2-24B-Instruct-2506 is a minor version update of Mistral-Small-3.1-24B-Instruct-2503, which improves instruction following, reduces repetitive errors, and enhances function call capabilities, providing more efficient and accurate services.

MultimodalSafetensorsMultiple Languages

Mistral-Small-3.2-24B-Instruct-2506 is an image-text-to-text model that performs excellently in model quantization and shows significant improvements in instruction following, reducing repetition errors, and function calls.

MultimodalGgufMultiple Languages

Mistral-Small-3.2-24B-Instruct-2506 is an image-text-to-text model and an updated version of Mistral-Small-3.1-24B-Instruct-2503, with improvements in instruction following, reducing repetition errors, and function calls.

MultimodalSafetensorsMultiple Languages