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.
MiniCPM-Llama3-V-2_5Qwen3.6-35B-v2-MoE-Ablit-Heretic-Uncensor-Hermes-MTP-Vision-Llamallama3.8-27b-uc-fp8-jhmoondream2-llamafilevdr-2b-multi-v1InternVL2-Llama3-76BLlama-4-Maverick-17B-128E-Instruct-Projected-Abliterated-GGUFqwen3-vl-2b-instruct-q4-k-m-ggml-llama-cpp-vivo-x300cogito-v2-preview-llama-109B-MoEllama3-2-11b-xray-v1Llama-3.1-8B-Dragonfly-v2Llama-4-Scout-17B-16E-Instruct-abliterated-v2MiniCPM-Llama3-V-2_5-GPTQgemma-4-e2b-uncensored-hauhaucs-aggressive-q6-k-p-llamafileLlama-3-EvoVLM-JP-v2vdr-2b-v1Llama-3.1-8B-Dragonfly-Med-v2cogito-v2-preview-llama-109B-MoE-MXFP4_MOE-GGUFInternVL2-Llama3-76B-AWQChartInstruct-LLama2llava-llama-3-8b-v1_1-Q2_K-GGUFHuihui-Mistral-Small-3.2-24B-Instruct-2506-abliterated-llamacppfixedMistral-Small-3.2-24B-Instruct-2506-llamacppfixedfinal_LlamaV-Docplan-origin-HF-3epGemma4-E2B-it-CustomUI-llamafileLLaVA-llama32-3b-VLfull-s42-s2bqwen3.8-27b-ud-q5-k-xl-llamafileQwen3.5-2B-llamafileLLaVA-llama32-3b-VLfull-s1337-s2bLlamaMedBoard-VL-3.2-11B_ver2
