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.
Llama-3.3-70B-Instruct-AWQbge-m3-koreanhelium-1-preview-2bmdeberta-v3-base-kor-furtherSmolLM3-3B-trellis-3inst-4bpw-kernelK-EXAONE-2.0-750B-A37BQwen3.8-27B-Kearuga-i1-GGUFChocolatine-3B-Instruct-DPO-Revised-Q4_K_M-GGUFAl-Khwarizmi-3B-i1-GGUFQwen3.8-27B-KearugaKimi-K3-MXFP-GGUFhelium-1-2bstt-1b-en_fr-trfsKomodo-Llama-3.2-3B-v2-fp16-i1-GGUFAl-Khwarizmi-3B-GGUFmagnum-v2.5-12b-kto-i1-GGUFKyro-n1-7B-i1-GGUFKafkaLM-15B-Base-i1-GGUFSelene-1-Mini-Llama-3.1-8B-Q4_K_M-GGUFQwen3.8-27B-Kearuga-GGUFmagnum-12b-v2.5-kto-i1-GGUFKyro-n1.1-3B-i1-GGUFMistral-Nemo-2407-12B-Thinking-Claude-Gemini-GPT5.2-Uncensored-HERETIC-Q4_K_M-GGUFK-EXAONE-2.0-750B-A37B-FP8Kichtral-7B-v0.3-GGUFMMed-Llama-3-8B-EnIns-Q4_K_M-GGUFKyro-n1.1-7B-pytorch-i1-GGUFKyro-n1-14B-i1-GGUFKyro-n1-14B-Chat-i1-GGUFKafkaLM-15B-i1-GGUF