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.
DeepReasoning_1Rdeepseek-r1-distill-qwen-1.5b-reasoning-finetuneDeepthink-Reasoning-7B-imatrix-GGUFDeepthink-Reasoning-7B-GGUFDeepSeek-V4-Flash-0731-Latent-ReasoningLlama3.1-MOE-4X8B-Gated-IQ-Multi-Tier-Deep-Reasoning-32BDeepthink-Reasoning-7BDeepthink-Reasoning-14BDeepthink-Reasoning-7B-Q4_K_M-GGUFHelion-V1-reasoningDeepthink-Reasoning-7B-Q4_K_M-GGUFdeepseek-finetune-python-reasoningqwen-3-reasoning-combination-with-deepseekLlama-3.1-Swallow-8B-v0.2-reasoningvector-deepseek-r1deepseek-clinical-reasoning-qwen3-8bDeepSeek-R1-SpamAssassin-with-reasoningDeepSeek-FreedomIntelligence_medical-o1-reasoning-SFTMobile-ReasoningLLM-v0.1deepseek-qwen-grpo-reasoning-v1-8bitDeepSeek-R1-8B-FT-medical-o1-reasoning-SFTDeepSeek-R1-Distill-Llama-8B_korean-reasoning-mixture-20250203-previewgemma3-1b-sft-sitcom-office-reasoning-float16DeepSeek-Magpie-Reasoning-1.5b-V2-250K-CoTTdeepseek-r1-reasoning-prompt-generatorDeepSeek-R1-Distill-Llama-8B_korean_reasoningSWE-BENCH-2000-enriched-reasoning-claude-localization_deepcoder_14b_2000_enriched_reasoningDeepSeek-R1-Medical-COT-ReasoningV2dmWM-deepseek-ai-DeepSeek-R1-Distill-Qwen-1.5B-KGWB-Reasoning-think-3Deepthink-Reasoning-7B-IQ4_NL-GGUFDeepSeek-R1-Medical-COT-NO-REASONING