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.
GRAG-HERMES-MOBIUS-R1-LLAMA-i1-GGUFgemma4-E2B-it-qat-Q4-unsloth-hereticgemma-4-26b-a4b-mobius-custom-c1Intern-S2-Mobiusgemma-4-12b-mobius-customGRAG-MOBIUS-R1-LLAMA-DISTILL-MERGE-GGUFGRAG-Mobius-DeepSeek-R1-ReDistill-LLAMA-8B-v1.1-SFT-DE-GGUFGRAG-HERMES-MOBIUS-R1-LLAMA-GGUFMobiusv0.5-i1-GGUFgpt_FT_modelgpt_FT_ggufmodelIntern-S2-Mobius-FP8gemma-4-12b-mobius-custom-c1mobiuslabsgmbh.DeepSeek-R1-ReDistill-Qwen-1.5B-v1.0-GGUFLlama-2-7b-chat-hf_1bitgs8_hqqMobiusv0.5-GGUFqwen2_5_FT_ggufmodelLlama-2-7b-chat-hf_2bitgs8_hqqdistilbert-distilbert-base-uncased-a0072225_FT_adaptermobiuslabsgmbh-faster-whisper-large-v3-turbogpt2_FT_modelDeepSeek-R1-ReDistill-Qwen-1.5B-v1.1aanaphi2-v0.1Mixtral-8x7B-Instruct-v0.1-hf-attn-4bit-moe-2bit-HQQopenai-community-gpt2-43775f53_FT_modelopenai-community-gpt2-2bb7baf5_FT_modelMixtral-8x7B-Instruct-v0.1-hf-attn-4bit-moe-3bit-metaoffload-HQQMixtral-8x7B-Instruct-v0.1-hf-attn-4bit-moe-2bitgs8-metaoffload-HQQMixtral-8x7B-Instruct-v0.1-hf-attn-4bit-moe-2bit-metaoffload-HQQopenai-community-gpt2-cadd3c13_FT_model