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.
GLM-OCRQwen3-VL-Embedding-8B-FP8Qwen3.6-27B-Text-NVFP4-MTPOrnith-1.0-35B-NVFP4Ornith-1.0-35B-NVFP4North-Micro-Vision-InstructLlama-4-Scout-17B-16E-InstructLlama-3.2-90B-Vision-InstructLightOnOCR-2-1BGLM-OCR-4bitLlama-3.2-11B-Vision-InstructLFM2.5-VL-1.6B-GGUFLlama-4-Maverick-17B-128E-Instruct-FP8Mistral-Small-3.2-24B-Instruct-2506-GGUFcommand-a-plus-05-2026-bf16LFM2.5-VL-450MLlama-4-Scout-17B-16E-Instruct-GGUFdeplotGLM-OCRLFM2.5-VL-3B-GGUFLlama-4-Scout-17B-16E-Instruct-quantized.w4a16LFM2.5-VL-3BLFM2.5-VL-1.6Bmistralai_Ministral-3-3B-Instruct-2512-GGUFMistral-Small-3.2-24B-Instruct-2506-MLX-6bitpix2struct-baseQwen3.5-9B-abliterated-GGUFMistral-Small-3.2-24B-Instruct-2506-MLX-4bitMistral-Small-3.2-24B-Instruct-2506-MLX-8bitHuihui-Mistral-Small-3.2-24B-Instruct-2506-abliterated-Q4_K_M-GGUF
