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.
gemma-4-26B-A4B-itQwen3-4BQwen3.5-4BQwen3.8-27B-MLX-4bitgemma-4-E4B-itQwen3-4B-Instruct-2507NVIDIA-Nemotron-3-Nano-4B-BF16Qwen3-VL-4B-InstructQwen3-Reranker-4BQwen3-Embedding-4BTRELLIS.2-4BVoxtral-Mini-4B-Realtime-2602Gemma-4-E4B-Uncensored-HauhauCS-Aggressivegemma-3-4b-itGemma-4-26B-A4B-NVFP4Qwen3-4B-Basegemma-4-E4B-it-GGUFgemma-4-26B-A4B-it-AWQ-4bitOTel-LLM-E4B-ITgemma-4-E4B-it-MLX-4bitgemma-4-E4B-it-MLX-8bitgemma-4-E4B-it-MLX-5bitgemma-4-E4B-it-MLX-6bitmedgemma-4b-itLlama-3.1-8B-Instruct-4bite5-mistral-7b-instruct-bnb-4bitQwen3-Coder-30B-A3B-Instruct-AWQ-4bitgemma-4-26B-A4B-it-FP8-dynamicQwen3-4B-Instruct-2507-FP8Qwen3.5-4B-GGUF
