Brief-details: ResNet-18 model for binary classification of clean vs. noisy images. Achieves 95.2% accuracy with dynamic quantization for efficient inference. Input: 224x224 RGB images.
Brief-details: Levlex-Math-One-14B-GGUF is a quantized version of the math-focused language model, offering various compression options from 5.7GB to 15.7GB while maintaining performance.
Brief Details: ModernBERT-based AI text detector achieving 99.64% validation accuracy. Fine-tuned on 35K+ samples for distinguishing AI vs human content.
Brief-details: ResNet-18 based model for cataract detection with 97.52% accuracy. Processes 224x224 images to classify between normal and cataract conditions. Quantized for efficiency.
Brief Details: An 8B parameter Llama-based instructional model with multiple GGUF quantization options (2.1GB-6.7GB), optimized for efficient deployment and uncensored responses.
BRIEF DETAILS: 8B parameter GGUF-quantized LLaMA model with multiple compression variants (Q2-Q8), offering flexible performance-size tradeoffs. Fast inference with Q4_K variants recommended.
Brief-details: Quantized version of Llama 3.1 8B uncensored model optimized for SQL injection tasks, offering various GGUF compression formats from 2.1GB to 6.7GB
Brief-details: Quantized version of NAPS-AI's LLaMA 3.1 8B instruct model, offering multiple GGUF variants optimized for different size/performance tradeoffs
BRIEF-DETAILS: NAPS-LLaMA 3.1 8B Instruct GGUF - Optimized quantized versions of NAPS-ai's LLaMA model, offering various compression options from 3.3GB to 16.2GB with different quality-performance tradeoffs.
Brief-details: QWEN 7B quantized model offering various compression levels (IQ1-Q6) in GGUF format, optimized for different size/performance trade-offs, from 2.0GB to 6.4GB
BRIEF DETAILS: L3.3-Electra-R1-70b-GGUF is a quantized version of the 70B parameter Electra model, offering multiple compression formats from IQ2_M to Q8_0 for efficient deployment.
Brief-details: A quantized version of Mistral-Nemo StoryWriter 12B, optimized for different performance/size tradeoffs with GGUF format support and imatrix quantization
Brief-details: EAGLE3-LLaMA3.3-Instruct-70B is a 70B parameter instruction-tuned language model based on LLaMA architecture, developed by yuhuili for advanced NLP tasks.
Brief Details: A 1B parameter quantized instruction-tuned language model optimized for GGUF format, offering efficient local deployment via llama.cpp
BRIEF-DETAILS: Quantized version of Mistral-Small-24b-Sertraline with multiple GGUF variants optimized for different size/performance tradeoffs. Features imatrix quantization for improved quality.
BRIEF DETAILS: An 8-bit quantized vision-language model converted from CohereForAI/aya-vision-8b, optimized for MLX framework with efficient image description capabilities.
BRIEF DETAILS: A GGUF-optimized version of BigKartoffel-mistral-nemo offering multiple quantization options (Q2_K to Q8_0), with sizes ranging from 7.9GB to 21.8GB. Fast and efficient implementation.
BRIEF-DETAILS: A quantized version of Epimetheus-14B-Axo with multiple GGUF variants optimized for different size/performance tradeoffs. Features imatrix quantization for improved quality.
Brief-details: A quantized 8B parameter instruction-tuned language model offering multiple GGUF variants optimized for different size/quality trade-offs, with sizes ranging from 1.9GB to 6.8GB
BRIEF-DETAILS: 8B parameter GGUF-formatted Llama 3.1 DeepSeek model with multiple quantization options (Q2_K to Q8_0), optimized for instruction-following tasks
Brief-details: A 24B parameter Mistral-based model by BeaverAI, optimized with GGUF format for efficient inference and deployment. Features enhanced performance and compatibility.
