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-VL-8B-Instruct-Batch16Huihui-Qwen3.8-27B-abliterated-FP8-v2gemma-4-12B-it-GGUFHuihui-Qwen3.6-35B-A3B-abliterated-FP8Agents-A1-NVFP4-MTP-GGUFLlama-4-Scout-17B-16E-Instruct-GGUFNex-N2-mini-GGUFHuihui-Qwen3.6-35B-A3B-Claude-4.7-Opus-abliterated-FP8Fara-7B-GGUFQwen3-VL-2B-Instruct-Batch16batiseeHuihui-Qwen3.6-35B-A3B-Claude-4.6-Opus-abliterated-FP8Qwen2.5-VL-72B-Instruct-bnb-4bit-2025-10-07_13-35_batch_size_4_no_wrong_doc_4bHuihui-Qwen3.5-35B-A3B-Claude-4.6-Opus-abliterated-FP8Qwopus3.6-27B-Coder-NVFP4-MTP-GGUFQwen3-VL-4B-Instruct-Batch16UHR-BATmodel-fullset-batch4BattleKAT-Coder-V2.5-Dev-Vision-oQ4ebatch16_3.5e_5_dino_2mantis-8b-idefics2-video-eval-95k-batch32_4096batch32_5e_5_VEDdeplot-batch-1-token-freeze-curri-update-lossdonut-all-w960-h1280-docile-batch-3indi-deplot-batch-16model-fullset-batch4_cleanedUni-IAD-R2-Qwen3.5-GRPO-answer_last-no-hard_total_batch_8batch32_1e_5_VEDbatch16_2e_5_dino_2indi-deplot-batch
