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

A GGUF-quantized model fine-tuned based on Llama 3.1 8B Instruct, with a strong, decisive, and provocative AI persona, optimized for role-playing and creative writing scenarios, and supports local inference on CPU or GPU.

Natural Language ProcessingTransformers

This is an 8 billion parameter network security professional model based on LLaMA 3.1, which has undergone 8-bit quantization processing and is specifically designed for network security tasks, including threat intelligence summarization, vulnerability classification, and event analysis.

Natural Language ProcessingTransformersEnglish

This is a quantized version based on the Llama 3.1 8B model, optimized using the imatrix technology of llama.cpp. It provides multiple quantization options to adapt to different hardware environments, significantly reducing resource consumption while maintaining model quality.

Natural Language ProcessingGguf

Magistral Small 1.1 is a high - efficiency reasoning model with 24 billion parameters, built on the basis of Magistral Small 3.1. It has new reasoning capabilities, supports multiple languages, and uses the Apache 2.0 license. It can be locally deployed and run on a single RTX 4090 or a MacBook with 32GB of memory.

Natural Language ProcessingGgufMultiple Languages

A.X 3.1 Light is a lightweight large language model (LLM) optimized for Korean understanding and enterprise deployment, fully independently developed by SKT.

Natural Language ProcessingTransformersMultiple Languages

A Turkish language educational Q&A chatbot fine-tuned based on the Meta LLaMA 3.1 8B large language model, optimized specifically for Turkish language education scenarios.

Natural Language ProcessingAdaptersOther

Magistral-Small-2506-Vision is an inference fine-tuned version based on Mistral Small 3.1 with GRPO training, an experimental checkpoint with visual capabilities.

MultimodalSafetensorsMultiple Languages

Gervásio 8B PTPT is an open-source decoder model for Portuguese, fine-tuned based on LLaMA 3.1 8B Instruct, with powerful text generation capabilities.

Natural Language ProcessingTransformersOther

Magistral-Small-2506 is a small and efficient inference model built on Mistral Small 3.1, with 24 billion parameters, supporting multilingual and long-chain reasoning.

Natural Language ProcessingSafetensorsMultiple Languages

Foundation-Sec-8B-Q8_0-GGUF is a large language model specialized in network security that has undergone 8-bit quantization. It is based on the LLaMA 3.1 architecture and focuses on network security text processing tasks.

Natural Language ProcessingTransformersEnglish

Poro 2 8B Instruct is an instruction - following chatbot model based on the Llama 3.1 8B architecture, designed for conversational AI applications in Finnish and English.

Natural Language ProcessingTransformersMultiple Languages

A financial domain-specific model fine-tuned from Llama 3.1 8B, excelling in financial reasoning, Q&A, and multi-turn dialogues

Natural Language ProcessingTransformersEnglish

Llama-3.1-Nemotron-Nano-4B-v1.1 is a large language model optimized based on Llama 3.1, achieving a good balance between accuracy and efficiency. It is suitable for various scenarios such as AI agents and chatbots.

Natural Language ProcessingTransformersEnglish

Llama-3.1-Nemotron-Nano-4B-v1.1 is a large language model derived from Llama 3.1 8B through compression, optimized for inference efficiency and task execution, suitable for local deployment on a single RTX GPU.

Natural Language ProcessingTransformersEnglish

This is the GGUF quantized version of DXP - Zero - V1.0 - 24b - Small - Instruct, specifically optimized for text generation tasks and particularly good at role - playing and story - creation scenarios. The model is based on the Mistral - Small - 3.1 - 24B architecture and uses the TIES merging method to integrate the capabilities of multiple excellent models.

Natural Language ProcessingGgufMultiple Languages

KernelLLM is a large language model specifically trained based on Llama 3.1 Instruct, focusing on writing GPU kernels using Triton. It can efficiently convert PyTorch modules into Triton kernels, making GPU programming more accessible and efficient.

Natural Language ProcessingTransformers

KernelLLM is a model fine-tuned based on Llama 3.1 Instruct, specifically designed for writing GPU kernels using Triton.

Natural Language ProcessingGguf

Meta Llama 3.1 series multilingual large language model, featuring 8B parameters, optimized for multilingual conversational use cases, supporting 8 languages.

Natural Language ProcessingSafetensorsMultiple Languages

Eurydice-24b v3 is a multi-character dialogue companion model built on Mistral 3.1, excelling in creative expression, natural conversation, and storytelling.

Natural Language ProcessingTransformersEnglish