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.
Tongyi-DeepResearch-30B-A3BAlibaba-NLP_Tongyi-DeepResearch-30B-A3B-GGUFTongyi-DeepResearch-30B-A3B-GGUFDeepSeek-V4-Flash-0731-abliteratedMarco-DeepResearch-8B-i1-GGUFMarco-DeepResearch-8BQwen3-4B-v0.4-deepresearch-no-think-4-GGUFMarco-DeepResearch-8B-GGUFAlibaba-NLP.Tongyi-DeepResearch-30B-A3B-GGUFTongyi-DeepResearch-30B-A3BSaily_220BTongyi-DeepResearch-30B-A3B-MXFP4_MOE-GGUFsaily_100bTongyi-DeepResearch-30B-A3B-FP8Flux-Japanese-Qwen2.5-32B-Instruct-V1.0Huihui-Tongyi-DeepResearch-30B-A3B-abliterated-mlx-8BitHuihui-Tongyi-DeepResearch-30B-A3B-abliterated-MXFP4_MOE-GGUFS1-DeepResearch-8B-PreviewD2IL-Japanese-Qwen2.5-32B-Instruct-v0.1Tongyi-DeepResearch-30B-A3B-4bitSaiLy_experiment_v1test-qwen2.5-14b-wo-system-v1saily-13b-v0deepseek-coder-1.3b-instruct-comment-resolution-baselineQwen3-14B-v0.2-deepresearch-no-think-100-step-bf16-quantized.w8a8Huihui-Tongyi-DeepResearch-30B-A3B-abliterated-mlx-4BitQwen3-4B-v0.3-deepresearch-100-stepTongyi-DeepResearch-30B-A3B-Q8_0-GGUFdeepseek-coder-1.3b-instruct-comment-resolutionTongyi-DeepResearch-30B-A3B-mlx-8Bit