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.
Llama3.1-MOE-4X8B-Gated-IQ-Multi-Tier-Deep-Reasoning-32B-i1-GGUFLlama3.1-MOE-4X8B-Gated-IQ-Multi-Tier-Deep-Reasoning-32B-GGUFgemma_3_4B_reasoning_multimodal_en_ft_v2Qwen-2.5-Instruct-Multishot-First-Reasoning-7Bv2-GGUFLlama3.1-MOE-4X8B-Gated-IQ-Multi-Tier-Deep-Reasoning-32BDiscussion-Phi-4-multimodal-instruct-audio-dimp-reasoningBagel-Zebra-CoTgpt-oss-120b-multilingual-reasoning-i1-GGUFgpt-oss-120b-multilingual-reasoninggpt-oss-20b-tool-use-multiturn-reasoning-mxfp4gpt-oss-20b-multilingual-reasoninggpt-oss-20b-2-multilingual-reasoningllama_multi_reasoninggpt-oss-20B-finetuned-multilang-reasoning-full-modelQwen-2.5-Instruct-Multishot-Last-Reasoning-7Bmeta-Llama-3.1-8B-Instruct_reasoning-multilingual-R1-indic-trainQwen-2.5-Instruct-Multishot-First-Reasoning-7Bv2Qwen-2.5-Instruct-Multishot-First-Reasoning-7BLlamaAIRecruit-Llama-Multimodal-Reasoning-f2gpt-oss-20b-multilingual-reasoninggpt-oss-120b-multilingual-reasoning-GGUFgpt-oss-20b-sft-multilingual-reasoning-qlora-v1gpt-oss-20B-finetuned-multilang-reasoningMulti_agent_reasoning_V1_Qwen3_VL_8B_Instruct_type_reasoning_epoch_100_lr_1e_05Multi_agent_reasoning_V1_Qwen3_VL_8B_Instruct_type_reasoning_epoch_3_lr_1e_05Multi_agent_reasoning_V1_Qwen3_VL_8B_Instruct_type_reasoning_epoch_2_lr_1e_05Multi_agent_reasoning_V1_Qwen3_VL_8B_Instruct_type_reasoning_epoch_3_lr_1e_05sample_length_2635Multi_agent_reasoning_V1_Qwen3_VL_8B_Instruct_type_reasoning_epoch_3_lr_1e_05sample_length_4634Multi_agent_reasoning_V1_Qwen3_VL_8B_Instruct_type_reasoning_epoch_1_lr_1e_05sample_length_5449MultiAgent_V1_iacc.3_Qwen3_VL_8B_Instruct_reasoning_ep1_lr1neg05_len5449