# Low-Resource Quantization

Seed-Coder-8B-Reasoning is a code generation model based on the Transformer architecture, with powerful reasoning capabilities and suitable for a variety of coding tasks. It performs excellently among open-source models of the same scale.

Qwen3 is the latest generation large language model in the Tongyi Qianwen series, a 235B parameter Mixture of Experts (MoE) model, significantly reducing memory usage after INT4 quantization

A quantized version based on burtenshaw/GemmaCoder3-12B, optimized for code generation tasks, supporting multiple quantization levels to adapt to different hardware requirements.

This is a weighted/matrix quantized version of the Fanbin/STEVE-R1-7B-SFT model, suitable for resource-constrained environments.

This is a weighted/importance matrix quantized version of the Minthy/ToriiGate-v0.4-7B model, offering multiple quantization options to suit different needs.

The static quantized version of ToriiGate-v0.4-7B, suitable for multimodal, vision, and image-text-to-text tasks

Tifa-DeepsexV2-7b-MGRPO-safetensors is a multilingual (Chinese and English) large language model based on the transformers library, optimized through incremental pre-training, supervised fine-tuning, and reinforcement learning, suitable for role-playing and chain-of-thought tasks.

NoticIA-7B is a Spanish-language news summarization model, specialized in processing news content and generating summaries.

StarCoder2-3B is an open-source model with 3 billion parameters focused on code generation, developed by the BigCode team.

VNTL LLaMA 3 8B qlora is a merged model based on LLaMA 3 8B, supporting Japanese and English translation tasks, with an added chat mode suitable for answering Japanese grammar questions.

NeuralStar_AlphaWriter_4x7b is a 7B-parameter language model built on Mixture of Experts (MoE) technology, specifically optimized for creative writing tasks by integrating four expert models specialized in different writing domains.