This is the FP8 quantized version of the Meta Llama-3.1-8B-Instruct model. By performing FP8 quantization on weights and activation values, it significantly reduces the disk size and GPU memory requirements while maintaining good model performance.

Natural Language ProcessingSafetensors

This is a quantized version of Qwen3-VL-235B-A22B-Instruct. By quantizing the weights and activation values to the FP8 data type, it effectively reduces the disk size and GPU memory requirement by approximately 50%. It supports text, image, and video inputs and outputs text, suitable for various natural language processing and multimodal tasks.

MultimodalSafetensors

This is the INT8 quantized version of the Devstral-Small-2507 model. By quantizing the weights and activation values to 8-bit integers, it significantly reduces the GPU memory and disk space requirements by approximately 50% while maintaining good performance on coding tasks.

Natural Language ProcessingSafetensorsEnglish

This is a version of the Google Gemma 3N E4B IT model with FP8 dynamic quantization. By quantizing the weights and activation values to the FP8 data type, the inference efficiency is significantly improved while maintaining the performance of the original model. It supports multimodal inputs (text, images, audio, videos) and text outputs.

MultimodalSafetensorsMultiple Languages

The FP8 quantized version of the SmolLM3-3B model developed by RedHatAI. By quantizing weights and activation values to the FP8 data type, it significantly reduces GPU memory requirements and disk space usage while improving computational throughput.

Natural Language ProcessingSafetensorsMultiple Languages

Mi:dm 2.0 is a Korea-centered AI model developed by KT, which deeply internalizes the unique values and cognitive frameworks of Korean society and provides efficient text generation services.

Natural Language ProcessingTransformersMultiple Languages

Mi:dm 2.0 is an 'AI centered around South Korea' model developed using KT's proprietary technology, which deeply internalizes the unique values, cognitive frameworks, and common-sense reasoning of South Korean society.

Natural Language ProcessingTransformersMultiple Languages

Mi:dm 2.0 is an AI model centered around South Korea, developed by KT using its proprietary technology. This model has deeply internalized the unique values, cognitive frameworks, and common-sense reasoning of South Korean society. It can not only process and generate Korean content but also reflect a profound understanding of South Korean social and cultural norms and values.

Natural Language ProcessingTransformersMultiple Languages

This is a regression model based on the DistilBERT architecture that can predict the Big Five personality traits (openness, conscientiousness, extraversion, agreeableness, and neuroticism) from English free text, with outputs as continuous values between 0.0 and 1.0.

Natural Language ProcessingTransformersEnglish

Motif 2.6B is a language model with 2.6 billion parameters, trained from scratch on AMD Instinct™ MI250 GPUs, aiming to build AI that aligns with human values, is useful, and reliable.

Natural Language ProcessingSafetensorsMultiple Languages

Fanar-1-9B-Instruct is a powerful Arabic-English large language model developed by the Qatar Computing Research Institute (QCRI). It supports Modern Standard Arabic and multiple Arabic dialects, and is aligned with Islamic values and Arab culture.

Natural Language ProcessingTransformersMultiple Languages

Qwen3-14B-FP8-dynamic is an optimized large language model. By quantizing activation values and weights to the FP8 data type, it effectively reduces GPU memory requirements and improves computational throughput.

Natural Language ProcessingTransformers

CARA is an advanced language model fine-tuned based on Mistral-Small-24B-Instruct-2501, specifically designed for handling emotional and relational scenarios, offering functions such as emotional coaching, conflict resolution, and values clarification.

Natural Language ProcessingTransformers

This is an AI model for online content moderation, aiming to identify and process content that does not comply with laws, regulations, and the core socialist values, and maintain a healthy and orderly online environment.

Natural Language ProcessingTransformersEnglish

A distilled version of the genmoai mochi-1 model transformer, composed of 42 modules (original version has 48 modules), achieving lightweight through iterative removal of modules with the smallest MSE values

MultimodalDiffusersEnglish

A Korean language model fine-tuned based on the LlaMA3.2 1B model through the SFT method. It is trained with Korean data from 53 domains and can understand Korean social values and culture. It supports various natural language processing tasks such as text generation and question answering.

Natural Language ProcessingTransformersKorean

A Korean - specialized language model based on LlaMA3.1, which understands Korean social values and culture and is suitable for diverse Korean scenarios.

Natural Language ProcessingSafetensorsKorean

Teuken-7B-instruct-research-v0.4 is a 7-billion-parameter multilingual large language model fine-tuned for instructions, supporting 24 official EU languages, with a focus on European values and multilingual task scenarios.

Natural Language ProcessingTransformersMultiple Languages

OCR model optimized for printed digits and timestamp-like numerical values, achieving CER=0 recognition accuracy on single-line image test sets

Computer VisionTransformersEnglish

ZoeDepth is a depth estimation model fine-tuned on NYU and KITTI datasets, capable of estimating depth values in actual metric units.

Computer VisionTransformers