Brief Details: 8B parameter GGUF-quantized fiction-focused language model available in multiple compression formats from 2.3GB to 6.7GB, optimized for creative writing.
Brief-details: An 8.03B parameter GGUF-formatted model offering various quantization options, optimized for performance and efficiency with imatrix implementation
Brief Details: OLMo-2-1124-7B-RM is a 7B parameter reward model built by Allen AI, fine-tuned on preference data for improved instruction following and safety.
Brief-details: French language model fine-tuned for generating student evaluations, based on Llama-3.1-8B. Helps teachers write personalized progress reports. AGPL-3.0 licensed.
Brief Details: Bilingual 1.54B parameter instruction-tuned LLM based on Qwen-2.5, optimized for Russian/English text processing using GGUF format
BRIEF-DETAILS: 14B parameter GGUF-quantized language model offering multiple compression variants from Q2 to Q8, optimized for different performance/quality trade-offs
Brief Details: A GGUF-quantized version of MFANNv0.25 with 8.03B parameters, offering multiple quantization options from Q2_K to f16, optimized for efficient inference.
BRIEF-DETAILS: 14B parameter GGUF-quantized conversational model with multiple compression variants (Q2_K to Q8_0), optimized for efficient deployment and inference.
BRIEF DETAILS: 12B parameter Mistral-based model quantized for efficient deployment, offering multiple GGUF variants optimized for different size/performance tradeoffs
Brief-details: 8B parameter GGUF quantized language model optimized for high fantasy content, offering multiple compression variants from 2.1GB to 6.7GB with imatrix quantization
Brief-details: An 8B parameter GGUF-quantized model optimized for conversational tasks, offering multiple compression variants from 2.1GB to 6.7GB with imatrix quantization
BRIEF DETAILS: 17.4B parameter GGUF language model with multiple quantization options, offering flexible performance-size tradeoffs from 6.7GB to 18.6GB. Optimized for English conversation.
Brief-details: 8B parameter LLM with multiple GGUF quantization options (2.1GB-6.7GB), featuring iMatrix architecture and optimized for English conversation
Brief-details: An 8.03B parameter GGUF-quantized language model offering multiple compression variants, optimized for efficient deployment with various quality-performance tradeoffs.
Brief-details: A 14.8B parameter GGUF-quantized conversational model based on Qwen2.5-14B, optimized with Axolotl training framework and featuring enhanced attention mechanisms.
Brief Details: A 7.62B parameter GGUF-quantized language model based on Qwen/Qwen2.5-7B, fine-tuned on Tulu-3 dataset with strong performance on reasoning tasks.
Brief Details: 8B parameter LLaMA-based conversational AI model with dual personality modes (standard helpful assistant & experimental hacker mode) and 8K context
BRIEF DETAILS: An 8B parameter multilingual translation model supporting 5 Southeast Asian languages with strong BLEU scores (45-78) and ROUGE metrics (72-91) for pairwise translation.
Brief-Details: An 8B parameter merged model combining Llama-3.1 and MFANN using SLERP technique, optimized for text generation with BF16 precision
Brief-details: French language LLM (3B parameters) specialized in generating student evaluations for French secondary teachers, built on Llama-3.2-3B-Instruct
Brief Details: 8.48B parameter LLaVA-based vision-language model optimized for conversational visual question-answering, using BF16 precision tensors.
