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.
gemma4-e4b-claims-comparisonKwaipilot_KAT-Coder-V2.5-Dev-GGUFQwopus3.6-27B-Fusion-GGUFQwopus-GLM-18B-Merged-GGUFA.X-K2-NVFP4A.X-K2Mellum2-12B-A2.5B-Instruct-GGUF-Q4_K_Mnl2sh-1.5b-Q4_K_MLlama-3.3-70B-Instruct-AWQsvara-tts-v1Llama-3.2-1B-Instruct-Q4_K_M-GGUFTIPO-500M-ftQwen3.8-27B-EfficientThink-Uncensored-K3-Opus5-Grok4.6-GPT5.6Sol-SFT-SimPO-DFlash2K2-Horizon-MoVA-36B-A4B-GGUFQwen2.5-Coder-7B-Q4_K_M-GGUFNanbeige4.1-3B-Q4_K_M-GGUFLlama-3.2-3B-Instruct-Q4_K_M-GGUFTIPO-500MK2-Horizon-0.9BMidm-2.0-Mini-InstructMidm-2.0-Base-InstructK2-Horizon-7B-GGUFkeys-DeepSeekV4-Flash-GA-0731-Dspark-Abliterated-Anchored-TensorsK2-Horizon-7BK2-Horizon-MoVA-36B-A4B-GGUFWrench-35B-A3B-Q4_K_M-GGUFK-EXAONE-236B-A23BQwen3.6-12B-IQ-Ultra-Heretic-Uncensored-Thinking-V2-Hightop-GGUFK2-Horizon-MoVA-36B-A4BQwen2.5-Coder-32B-Instruct-abliterated-Q4_K_M-GGUF