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.
Qwen3.5-2Bgemma-4-E2B-itQwen3-VL-2B-InstructQwen2-VL-2B-InstructQwen3-VL-Embedding-2BInternVL2-2BQwen3-VL-Reranker-2Bgemma-4-E2B-it-qat-GGUFtyphoon-ocr1.5-2bQwen3.5-2B-GGUFgemma-4-E2B-it-qat-w4a16-ctQwen3.5-2B-Basegemma-4-E2B-it-MLX-4bitgemma-4-E2B-it-MLX-8bitgemma-4-E2B-it-MLX-5bitgemma-4-E2B-it-MLX-6bitgemma-3n-E2B-itgemma-4-E2BQwen3-VL-2B-Instruct-GGUFQwen3.5-2BNuExtract-2.0-2BQwen3-VL-2B-ThinkingQwen3-VL-2B-Instruct-AWQ-4bitQwen3-VL-2B-Instruct-unsloth-bnb-4bitInternVL2_5-2BQwen3-VL-2B-Instruct-GGUFQwen3-VL-2B-Instruct-FP8gemma-3n-E2B-it-GGUFgemma-4-E2B-it-AWQ-INT4gemma-4-E2B-it-qat-mobile-GGUF
