models
Open weights, fine-tunes and adapters. Every listing here comes live from the Hugging Face Hub, attributed to it, and links back to the source.
Qwen3.8-27B-EfficientThink-Uncensored-K3-Opus5-Grok4.6-GPT5.6Sol-SFT-SimPO-DFlash2Qwen3.8-27B-EfficientThink-Uncensored-VAL-APEX-I-NanoPlus-GGUFQwen3.8-27B-EfficientThink-Uncensored-VAL-APEX-I-MiniPlus-V2.1-GGUFnerkyor-Qwen3.8-27B-EfficientThink-SimPO-KQVQ4-IQ3Floor-10G-MTP-GGUFnerkyor-Qwen3.8-27B-EfficientThink-KQVQ4-IQ3Floor-10G-MTP-Fast-GGUFt5-efficient-base-grammar-correctionMeta-Llama-Guard-2-8BEfficient_legal_model_distillationQwen3-12B-20pct-Compressed-14B-EN-V2Qwen3-11B-25pct-Compressed-14B-EN-V2Llama-3.1-6B-35pct-Compressed-8B-EN-V1Qwen2-VL-7B-InstructQwen3-12B-20pct-Compressed-14B-EN-V1EfficientMath-AIMeta-Llama-3.1-70B-InstructQwen3-11B-25pct-Compressed-14B-EN-V1Qwen3-11B-30pct-Compressed-14B-EN-V2Qwen3-3B-20pct-Compressed-4B-EN-V1Qwen3-11B-30pct-Compressed-14B-EN-V1.5Qwen3-11B-30pct-Compressed-14B-EN-V1Qwen3-11B-25pct-Compressed-14B-EN-V1.5Llama-3.1-6B-30pct-Compressed-8B-EN-V1Qwen3-3B-30pct-Compressed-4B-EN-V1Llama-3.2-2B-35pct-Compressed-3B-EN-V1Meta-Llama-3.1-70BLlama-3.2-3B-20pct-Compressed-3B-EN-V1Llama-3.2-3B-25pct-Compressed-3B-EN-V1Qwen3-12B-20pct-Compressed-14B-EN-V1.5Qwen3-10B-35pct-Compressed-14B-EN-V2Llama-3.1-6B-25pct-Compressed-8B-EN-V1