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.
gpt-oss-6.0b-specialized-all-pruned-moe-only-7-experts-i1-GGUFgpt-oss-6.0b-specialized-all-pruned-moe-only-7-experts-GGUFQwen1.5-MoE-A2.7B-20-experts-Maths-reasoning-trained-GGUFmoe-expert-coder-4bDeepseek-V2-13B-Math7K-Expert-Enhance-Subset-Expert-MoE-32-experts-i1-GGUFDeepseek-V2-13B-Math7K-Expert-Enhance-Subset-Expert-MoE-32-experts-GGUFQwen1.5-MoE-A2.7B-20-experts-SFT-trained-GGUFExpertRamonda-7Bx2_MoE-GGUFmoe-expert-security-4bQwen1.5-MoE-A2.7B-pruned-random-40-experts-GGUFMermaid-Flow-MoE-Expert2-i1-GGUFmoe-expert-research-4bQwen1.5-MoE-A2.7B-Chat-20_experts_Maths_FT-GGUFmoe-expert-precision-4bmoe-expert-omni-4bmoe-expert-datainfra-4bmoe-expert-graphrag-4bmoe-expert-governance-4bQwen1.5-MoE-A2.7B-20-experts-GGUFpredictor_mmlu_deepseek-moe-16b-chat_moe_patterns_finetuneMermaid-Flow-MoE-Expert2-GGUFQwen3-2x0.6B-Sushi-Code-Expert-MoEQwen1.5-MoE-A2.7B-Chat-20_experts-L2Norm-Pruningpredictor_mmlu_Qwen3-30B-A3B_moe_patterns_finetuneMermaid-Coder-MoE-Expert1-GGUFMermaid-Flow-MoE-Expert2Qwen1.5-MoE-A2.7B-Chat-20_experts_Maths_FTDeepseek-V2-13B-Math7K-Expert-Enhance-Subset-Expert-MoE-32-expertsMoe_codellama_3x7B_all_expertsQwen1.5-MOE-sft-coommonsense15k-aux-free-share-experts
