OpenThinker-Agent-v1-SFT is an agent model obtained through supervised fine-tuning (SFT) based on Qwen/Qwen3-8B. It is the first-stage model of the complete training process (SFT + RL) of OpenThinker-Agent-v1, specifically optimized for agent tasks (such as terminal operations and code repair).

Natural Language ProcessingTransformersOther

OpenThinker - Agent - v1 is an open - source intelligent agent model that is subsequently trained based on Qwen3 - 8B. It is designed for terminal operations and software engineering tasks. It is first trained on a high - quality supervised fine - tuning dataset and then further optimized through reinforcement learning. It performs excellently in agent benchmark tests such as Terminal - Bench 2.0 and SWE - Bench.

Natural Language ProcessingTransformersOther

Fara-7B is an efficient small language model specially designed by Microsoft for computer usage scenarios. It has only 7 billion parameters and performs excellently in advanced user tasks such as web operations, competing with larger agent systems.

MultimodalGguf

This is the quantized version of kldzj's GPT-OSS-120B-Heretic-v2 model, which is quantized using the imatrix technology of llama.cpp. The model significantly reduces the storage and computing resource requirements through quantization technology while maintaining good model performance, facilitating deployment and operation on various devices.

Natural Language ProcessingGguf

This project provides the GGUF format file of the Qwen3-4B-Thinking-2507 model. It is a large language model with 4B parameters and chain of thought reasoning ability, supporting multiple quantization versions for easy deployment and operation on various hardware.

Natural Language ProcessingGguf

Supertonic-TTS-ONNX is a text-to-speech conversion model based on the ONNX format, capable of converting English text into natural and fluent speech. This model is developed based on the Supertone/supertonic basic model and is optimized for the Transformers.js library, supporting efficient operation in the browser environment.

Audio ProcessingTransformersEnglish

This is a quantized version of the kldzj/gpt-oss-120b-heretic model, quantized using llamacpp. It offers a variety of quantization types, including special formats such as BF16, Q8_0, and MXFP4_MOE, significantly improving the model's operating efficiency.

Natural Language ProcessingGguf

VibeThinker-1.5B-GGUF is the GGUF quantized version of the WeiboAI/VibeThinker-1.5B model, quantized by MaziyarPanahi. This model is a text generation model with 1.5B parameters, supporting multiple quantization levels (from 2-bit to 8-bit), which facilitates efficient operation on various hardware.

Natural Language ProcessingGguf

This is a statically quantized version of the adith-ds/emotion-classifier-v2 model, offering various GGUF quantization formats suitable for emotion classification tasks. The model is optimized for efficient operation in different hardware environments.

Natural Language ProcessingTransformersEnglish

This model is an MLX format model converted from summykai/gemma3-27b-abliterated-dpo using version 0.28.3 of mlx-lm. It is a 27B parameter Gemma 3 large language model fine-tuned with DPO (Direct Preference Optimization), optimized for efficient operation on Apple Silicon (MLX framework).

Natural Language ProcessingTransformersEnglish

NV-Reason-CXR-3B GGUF is a quantized version of the NVIDIA NV-Reason-CXR-3B vision-language model, optimized for edge device deployment. This is a model with 3 billion parameters, focusing on chest X-ray analysis. It has been converted to the GGUF format and quantized for efficient operation on mobile devices, desktops, and embedded systems.

MultimodalGgufEnglish

This project is the MXFP4_MOE quantized version of the Kanana 1.5-15.7B-A3B instruction model, which can improve the model's operating efficiency in specific scenarios. This model is optimized based on kakaocorp/kanana-1.5-15.7b-a3b-instruct, using a mixture-of-experts architecture and MXFP4 quantization technology.

Natural Language ProcessingGguf

This is a 6-bit quantized version converted from the Kimi-Linear-48B-A3B-Instruct model, optimized for the Apple MLX framework. The model retains the powerful instruction-following ability of the original model, while significantly reducing storage and computational requirements through quantization technology, making it suitable for efficient operation on Apple hardware.

Natural Language ProcessingMlx

This is a llama.cpp quantized version based on the TheDrummer/Rivermind-24B-v1 model. It uses imatrix technology for optimized quantization and provides multiple quantization levels to adapt to different hardware configurations, enabling efficient operation in various environments.

Natural Language ProcessingGguf

This is a quantized version of the Qwen3-VL-2B-Instruct model. The llama.cpp tool and the imatrix method are used to generate model files with multiple quantization levels, which are convenient for efficient operation in different hardware environments. This model is a multimodal vision-language model with 2B parameters, supporting the interaction between images and text.

MultimodalGguf

This project quantizes the MiniMax-M2 model of MiniMaxAI. Using the llama.cpp tool, it provides model files of multiple quantization types for users with different needs, facilitating the efficient operation of the model under different hardware conditions.

Natural Language ProcessingGguf

MiniMax-M2-6bit is the MLX format conversion version of the MiniMaxAI/MiniMax-M2 model, converted using mlx-lm 0.28.4, and supports efficient operation on Apple Silicon devices.

Natural Language ProcessingMlx

EXAONE-4.0-1.2B is a text generation model developed by LG AI Research. It is based on the EXAONE-4.0-1.2B base model and fine-tuned using the tatsu-lab/alpaca dataset, supporting text generation tasks in both English and Korean. The model has been converted to the GGUF format for easy local deployment and operation.

Natural Language ProcessingGgufMultiple Languages

This is a quantized version based on Qwen3-Coder-REAP-25B-A3B, specifically optimized for Mac devices. It uses the Deckard (qx) formula for quantization, with 6-bit quantization for the embedding layer, heads, and selective attention paths, and 5-bit quantization for the rest, with a group size of 32. It achieves more efficient operation while maintaining a quality close to q8 quantization.

Natural Language ProcessingMlxEnglish

This is a quantized version of Ilya626's Cydonia_Vistral model in GGUF format. Multiple quantization types are generated using the imatrix option of llama.cpp, supporting efficient operation under different hardware configurations.

Natural Language ProcessingGguf