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.
mathstral-7B-v0.1-GGUFmath-shepherd-mistral-7b-prmMathstral-7B-v0.1-i1-GGUFBert-MLM_arXiv-MP-class_zbMathMathstral-7B-v0.1-GGUFMathSmith-HC-Problem-Synthesizer-Qwen3-8B-i1-GGUFMathSmith-Hard-Problem-Synthesizer-Qwen3-8B-i1-GGUFNeural-4-Maths-7b-i1-GGUFYoutu-Agent-RL-Maths-Qwen2.5-7B-i1-GGUFMathSmith-HC-Qwen3-14B-ShortCoT-i1-GGUFMathSmith-Qwen3-8B-LongCoT-i1-GGUFmathstral-7B-v0.1-iMat-GGUFMathSmith-DS-Qwen-7B-LongCoT-i1-GGUFMathSmith-hc-Qwen3-8B-i1-GGUFmath-shepherd-mistral-7b-prm-GGUFSAND-MathScience-DeepSeek-Qwen32B-i1-GGUFLlama-3.1-8B-Instruct_SFT_mathsp_ewc_v00.15_s43Llama-3.1-8B-Instruct_SFT_mathsp_ewc_v00.15_s44MathSageFR-DeepSeek-R1-Distill-Qwen-1.5B-i1-GGUFMathSmith-HC-Qwen3-32B-ShortCoT-i1-GGUFMathstral-7B-v0.1-4bitMathSmith-Hard-Problem-Synthesizer-Qwen3-8B-GGUFMathSmith-HC-Qwen3-8B-Qwen2_5-32B-ShortCoT-i1-GGUFmathstral-7B-v0.1-GGUFMathSaka-7.6B-i1-GGUFYoutu-Agent-RL-Maths-Qwen2.5-7B-GGUFmath-self-play-0.5B-GGUFQwen1.5-MoE-A2.7B-20-experts-Maths-reasoning-trained-GGUFMathSmith-HC-Qwen3-8B-Qwen2_5-32B-ShortCoT-GGUFMathSmith-hc-Qwen3-8B-GGUF