90 repos across 4 sub-areas
Cluster 462282
31 repos
Quantized LLM Model Collections
23 repos
Pre-quantized and converted large language models in GGUF format, optimized for efficient inference on consumer hardware. These repositories primarily collect model weights and conversion artifacts for various open-source LLMs (Llama, Qwen, Gemma, MiniCPM) rather than containing source code, making them distribution points for practitioners looking to run LLMs locally via llama.cpp or Open WebUI. The cluster reflects the practical infrastructure around making state-of-the-art models accessible without GPU resources.
LLM Model Quantization & ROCm Optimization
18 repos
Model quantization and optimization techniques for large language models, particularly focused on AMD ROCm hardware acceleration and GGUF format compatibility. The cluster centers on optimized model variants (Qwen, Qwopus, KAT-Coder, AEON) with multiple quantization schemes (FP4, FPX, MTP) targeting specific AMD architectures like Strix Halo. While most repos appear to be model artifacts or configuration repositories rather than frameworks, they reflect active work in making LLMs efficient for inference on AMD GPUs through aggressive quantization strategies.
Uncensored LLM Model Variants
18 repos
Quantized and fine-tuned variants of large language models (primarily Qwen and Gemma) distributed in GGUF format for local deployment. These repositories represent community efforts to create conversational AI models with modified safety parameters, targeting developers and users who want endpoint-compatible inference without content filtering. The cluster focuses on model format optimization and behavioral customization rather than foundational model architecture.