GigaAM-v3 is a basic model for Russian automatic speech recognition based on the Conformer architecture, with 220 - 240 million parameters. It is the third-generation model in the GigaAM series, pre-trained on 700,000 hours of Russian speech data using the HuBERT-CTC objective, providing state-of-the-art performance in a wide range of Russian ASR fields.

Audio ProcessingPytorchMultiple Languages

Wraith-8B is the first model in the VANTA Research entity series, fine-tuned based on Meta's Llama 3.1 8B Instruct. This model performs excellently in mathematical reasoning, achieving an accuracy rate of 70% in the GSM8K benchmark test. It also has a unique cosmic intelligence perspective, providing strong support for various application scenarios.

Natural Language ProcessingTransformersEnglish

Apertus is a fully open multilingual language model with a parameter scale of 70B and 8B. It supports over 1000 languages and long context processing. It only uses fully compliant and open training data, and its performance can rival that of closed-source models.

Natural Language ProcessingTransformersOther

Apertus is a fully open multi-language language model with a parameter scale of 70B and 8B. It supports over 1000 languages and long contexts, and only uses fully compliant and open training data. Its performance can be comparable to that of models trained with closed-source data.

Natural Language ProcessingTransformersOther

Apertus is a fully open multilingual large language model developed by Swiss AI. It has parameter scales of 8 billion and 70 billion, supports over 1000 languages and long context processing, and only uses fully compliant open training data. Its performance can rival that of closed-source models.

Natural Language ProcessingTransformersOther

GLM 4.6 is a quantized model optimized for a configuration of 128GB memory + single GPU. It uses the IQ_K quantization method, providing better quality and performance than the mainstream llama.cpp at the same size. This model needs to be used with ik_llama.cpp. On a configuration of 128GB dual-channel DDR5 memory, a single CCD Ryzen 7000 processor + a single 3090 graphics card, the text generation speed can reach approximately 6.8 tokens per second.

Natural Language ProcessingGgufMultiple Languages

Apertus-70B-Instruct-2509 is a quantized version of a large language model with 70 billion parameters developed by swiss-ai, focusing on instruction following and text generation tasks. This project is dedicated to freely sharing knowledge and is of an experimental nature. It provides an optimized quantized model to reduce the demand for computing resources.

Natural Language ProcessingGguf

This is a large language model with 70B parameters merged using the Linear DELLA method. Based on the Llama-3.1-Nemotron-lorablated-70B base model, it integrates multiple high-performance Llama-3.3-70B variant models, aiming to provide more powerful language understanding and generation capabilities.

Natural Language ProcessingTransformers

Code Llama is a large language model with 70 billion parameters developed by Meta, specifically optimized for the Python programming language. This model is based on an optimized Transformer architecture and supports code synthesis and understanding tasks, with a maximum context length of 16k tokens.

Natural Language ProcessingPytorchOther

GoldDiamondGold-70b is a large language model merged from multiple pre-trained language models using the mergekit tool. This model adopts the SCE merging method, based on cogito-v2, and integrates 17 different 70B parameter-scale models, aiming to combine the advantages of each model and provide intelligent text generation and dialogue capabilities.

Natural Language ProcessingTransformers

FastVideo FastWan2.2-TI2V-5B-FullAttn-Diffusers is a text-to-video generation model built on the diffusers library. It is fine-tuned using a novel sparse distillation strategy, supports 3-step fast inference, and can generate videos with a high-quality resolution of 121×704×1280.

MultimodalDiffusers

Lilith's-Whisper-L3.3-70b-0.1 is a large language model with 70 billion parameters based on the Llama 3.3 architecture, specifically optimized for role-playing (RP) scenarios. This model uses a 2/3 stage merging method to integrate the advantages of multiple top RP models, providing powerful dialogue generation capabilities for role-playing applications.

Natural Language ProcessingTransformers

Eden-L3.3-70b-0.3 is a 70B parameter large language model specifically optimized for creative writing and role-playing scenarios. It uses the SCE merging method to fuse multiple advanced 70B models and has excellent text generation and dialogue capabilities.

Natural Language ProcessingTransformers

IONOS Llama 3.3 70B Instruct FP8 is an optimized version of Meta's Llama 3.3 70B Instruct model, using FP8 quantization technology to improve performance and efficiency, suitable for deployment in production environments.

Natural Language ProcessingTransformersMultiple Languages

This is a quantized version of a large language model with 70B parameters, offering multiple quantization levels to meet different hardware requirements

Natural Language ProcessingGguf

A large language model with 70B parameters based on the Llama 3 prompt format, optimized for role-playing and creative writing, offering a GGUF quantized version.

Natural Language ProcessingGgufEnglish

Text-to-image model using DFloat11 lossless compression technology, reducing volume by 70% while maintaining 100% accuracy

MultimodalDiffusers

4-bit DWQ quantized version of the Llama 3.3 70B instruction-tuned model, optimized for efficient inference on the MLX framework

Natural Language ProcessingMlxMultiple Languages

This is a 70B-parameter large language model based on Llama 3.3, fine-tuned with SFT+DPO, specializing in character-driven dialogues and creative content generation

Natural Language ProcessingTransformers

The first real-time high-quality video generation model based on DiT architecture, supporting 1216×704 resolution at 30FPS

MultimodalDiffusersEnglish