Qwen3 1.7B Base DPO Tulu3 Decontaminated Masked Alternatives

Qwen3-1.7B-Base-SFT-Tulu3-decontaminated-masked is an open-source base language model for text generation tasks. It is designed for developers and researchers working on NLP projects, offering open weights and compatibility with Python and CLI tools for flexible integration.

Qwen2.5-1.5B-DPO-Tulu3-decontaminated-masked is an open source language model for text generation and research. It is distributed with open weights and supports local inference and Docker deployment for AI development.

Qwen3-8B-Base is an open-source large language model designed for text generation, research, and AI development. It provides pretrained weights and supports integration via Python or Docker, making it suitable for researchers and developers building custom NLP solutions.

Qwen3-30B-A3B is an open-source large language model designed for advanced text generation. Distributed under the Apache 2.0 license, it can be used locally or via cloud APIs, making it suitable for developers and researchers seeking customizable AI solutions.

Qwen3.5-2B is an open-source multimodal language model checkpoint supporting both text and image inputs. It is designed for developers and researchers who require advanced transformer models for natural language and vision tasks, with efficient local inference.

Qwen3.6-27B is a large-scale open-source language model for advanced NLP tasks. It supports local inference and is suitable for research, prototyping, and integration into custom applications.

Qwen-3.6-27B-AstroWolf is an open-source large language model checkpoint designed for advanced text generation. It is suitable for developers and researchers seeking to leverage state-of-the-art transformer models for natural language processing tasks. The model can be run locally or in self-hosted environments.

Qwen3.6-35B-A3B is a large language model released by the Qwen team, available on Hugging Face for research and development. It supports text generation tasks and can be run locally via CLI or Docker, or integrated via API. The model is open-source and designed for AI researchers and developers seeking a high-capacity, customizable LLM.

Qwen3.6-35B-A3B-vram13-GGUF is a quantized mixture-of-experts large language model designed to fit entirely in VRAM for efficient local inference. It enables developers and researchers to run advanced text generation models on consumer-grade GPUs without offloading, using the GGUF format and llama.cpp compatibility.

Qwen3.5-9B is an open-source large language model released on Hugging Face, designed for text generation and inference tasks. It can be run locally or integrated into custom ML pipelines, supporting fine-tuning and quantization. Ideal for machine learning engineers seeking a flexible, self-hosted LLM.

Qwen3.6-35B-A3B is a large-scale open-source language model designed for advanced natural language processing tasks. It supports local inference and is suitable for research, prototyping, and integration into custom NLP applications.

Qwen3.6-27B-V4 is a large checkpoint of the Qwen3.6 model, designed for advanced text generation and instruction-following. Distributed via Hugging Face, it is intended for researchers and developers to use in local inference and experimentation.

Qwen3-8B-Base-TauSFT-Tau is an open-source AI language model hosted on Hugging Face. It is designed for natural language processing tasks and can be integrated into Python projects or used via CLI for research and development purposes. The model is distributed with open weights for customization and experimentation.

qwen3.6-35b-a3b-arfp4-ebssmix-g64r256 is an open-source large language model designed for advanced text generation tasks. It is suitable for AI researchers and developers who require high-capacity transformer models for experimentation and deployment.

Qwen3.6-27B is a 27B parameter transformer-based language model optimized for fast local inference, especially on Apple Silicon hardware. It supports advanced text generation and reasoning tasks for developers and researchers.

Qwen3.5-2B-Base is a 2B parameter transformer model supporting both text and image generation. It is optimized for local inference and serves as a base for research, completion-style prompting, or further fine-tuning.

Qwen3.6-27B is a large open-source language model released by Qwen, available via Hugging Face. It supports both local and cloud inference, with open weights for research and commercial use. Developers can install it using pip or Docker and integrate it into their AI workflows.

Qwen3.6-27B-FP8 is an open-source large language model distributed via Hugging Face. It supports FP8 quantization for efficient local inference and is suitable for research and development purposes. The model is accessible to AI researchers and developers.

Qwen3-1.7B-AutoRound-W4A16-RTN is an open-source large language model hosted on Hugging Face, designed for text generation and inference. It enables developers and researchers to access, fine-tune, and deploy the model for various NLP tasks. The model is accessible via API and CLI and supports self-hosted deployment.

Qwen3.6-35B-A3B-MLX-VQ-2.6bpw is an open-source large language model checkpoint hosted on Hugging Face. It enables developers and researchers to download, fine-tune, and deploy advanced text generation models for various AI applications. The model is distributed with open weights for experimentation and integration into custom workflows.

Qwen3.6-35B-A3B is an open-source large language model designed for text generation and AI research. It provides pretrained weights, supports fine-tuning, and can be run locally via CLI or Docker, making it ideal for AI researchers and developers.

Qwen3.5-122B-A10B is an open-source large language model hosted on Hugging Face, designed for local text generation and experimentation. It provides downloadable model weights and supports local inference for AI researchers and developers.

Qwen3-TTS-12Hz-1.7B-Base is an open-source text-to-speech model that converts text into natural-sounding audio. Distributed as a Python package, it is designed for AI developers and researchers seeking customizable TTS solutions.

Qwen3-1.7B-GGUF is an open-source checkpoint of the Qwen3 language model in GGUF format, designed for local inference and text generation. It is suitable for developers and researchers who want to integrate or experiment with large language models in their own environments.

Qwen3.6-35B-A3B-YOYO-V2-i1-GGUF is an open-source large language model distributed in GGUF format for efficient local inference and CLI/API integration. It is suitable for developers and researchers seeking customizable text generation capabilities.

Qwen3.6-35B-A3B-GGUF is an open-source, quantized large language model distributed in GGUF format for local inference and research. It enables developers and researchers to run advanced language models on their own hardware, supporting experimentation and customization. The model is freely available for use and modification.

Qwen3.6-35B-A3B-MLX-VQ-3.4bpw is an open-source large language model available on Hugging Face, designed for natural language processing tasks. It supports local inference and can be integrated via API or CLI for research and development purposes. The model is suitable for AI researchers and developers seeking customizable LLMs.

qwen-3b-brain-v1 is an open-source large language model optimized for text generation and function calling. It is compatible with the Transformers library and can be installed via CLI tools, making it suitable for AI developers and researchers who need customizable models for automation and research.

Qwen3.5-0.8B-MTP-GGUF is an open-source language model designed for text generation and research. It supports local inference, is installable via multiple package managers, and is suitable for developers seeking a lightweight, customizable LLM for experimentation.

Qwen3.5-0.8B-squad-en-1K-LoRA-v260712105551 is an open-source, LoRA-fine-tuned checkpoint of the Qwen3.5 language model, optimized for NLP tasks such as question answering. Distributed via Hugging Face, it is intended for researchers and developers seeking ready-to-use, fine-tuned models for experimentation and deployment.

Qwen3.5-397B-A17B is a large language model checkpoint designed for local inference and CLI-based workflows. It enables developers and researchers to run advanced language models on their own hardware for experimentation and application development.