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.
Qwopus-GLM-18B-Merged-GGUFMERaLiON-SER-v1Qwopus-GLM-18B-Merged-GGUFmmbert32k-feedback-detector-mergedmmbert32k-modality-router-mergedMERaLiON-3-3B-ASRCantoneseLLM-v2.0-30B-A3B-Thinking-Chat-Vector-Merged-i1-GGUFCantoneseLLM-v2.0-8B-Thinking-Chat-Vector-Merged-i1-GGUFMERaLiON-2-10Bziya-llama-13b-medical-merged-i1-GGUFMERaLiON-SpeechEncoder-2Tralalabs_Pythia-6.9B-Instruct-v1-Merged-GGUFCantoneseLLM-v2.0-8B-Thinking-Chat-Vector-Merged-GGUFCantoneseLLM-v2.0-30B-A3B-Thinking-Chat-Vector-Merged-GGUFNewton-bot-2A-standard_merged-i1-GGUFMERaLiON-2-3B-GGUFTiny-Purr-350M-merged-i1-GGUFNewton-bot-2A-standard_merged-GGUFapproval_bureau_merged-i1-GGUFMistral-Small-3.1-24B-Instruct-2503-GGUFziya-llama-13b-medical-merged-GGUFLLaMA-3-MERaLiON-8B-Instruct-GGUFCantoneseLLM-v2.0-30B-A3B-Thinking-Chat-Vector-MergedMERaLiON-3-10Bgemma4_e2b_reasoner_mergedCantoneseLLM-v2.0-8B-Thinking-Chat-Vector-MergedNanbeige4.2-3B-mlx-8bitpiper-plus-mera-multilingualQwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled-heretic-v2-GGUFlightx2v_Qwen-Image-Lightning-4step-8step-Merge
