Qwen3.5-27B-abliterated-ko-GGUFby mradermacherπ» CPUGGUF~17 GB27B paramsβ¬ 0β₯ 0OtherconversationalView on Hugging Face
Nanbeige4.3-33B-GGUFby mradermacherπ» CPUGGUF~20 GB33B paramsβ¬ 0β₯ 0OtherconversationalView on Hugging Face
qwen3-1.7b-sft-multisource-math-knk-last50pct-math2x-step500by JingwenGuπ₯οΈ GPUFP16~5 GB1.7B paramsβ¬ 0β₯ 0OtherView on Hugging Face
systemone-decider-e4b-qpaby mohameddhameemπ₯οΈ GPUFP16~10 GB4B paramsβ¬ 0β₯ 0Otherapache-2.0dataset:hotpotqa/hotpot_qalicense:apache-2.0View on Hugging Face
systemone-decider-e4b-qpby mohameddhameemπ₯οΈ GPUFP16~10 GB4B paramsβ¬ 0β₯ 0Otherapache-2.0dataset:hotpotqa/hotpot_qalicense:apache-2.0View on Hugging Face
DAVID-fine-tuned-SmolLM2-1.7B-Instructby Nikhil1581β‘ CPU/GPU~5 GB1.7B paramsβ¬ 0β₯ 0Othermitlicense:mitView on Hugging Face
Qwen2.5-Coder-7B-Instruct-mlx-4bitby rao-studiosπ» CPUMLX~5 GB7B paramsβ¬ 0β₯ 0text-generationLanguageapache-2.0codeconversationallicense:apache-2.0View on Hugging Face
R1-Distill-Qwen-1.5B-OPD-R1-7B-Step200by leizhao7π₯οΈ GPUFP16~17 GB7B paramsβ¬ 0β₯ 0text-generationLanguagemitconversationaldataset:bytedtsinghua-sia/dapo-math-17klicense:mitView on Hugging Face
qwen3.5-9b-valiant-koala-4540-nvfp4by sereneeβ‘ CPU/GPU~22 GB9B paramsβ¬ 0β₯ 0OtherView on Hugging Face
Spark-X2.6-4B-CEDby darioooooo0oπ» CPUGGUF~3 GB4B paramsπ§²βTorrent availableβ no seedersβ±βΊβ¬ 0β₯ 0text-generationLanguageapache-2.0license:apache-2.0conversationalView on Hugging Face
medgemma-4b-it-sft-lora-crc100kby hiutakyβ‘ CPU/GPU~10 GB4B paramsβ¬ 0β₯ 0OtherView on Hugging Face
charon-v2-minicpm5-1bby Bhoidyπ₯οΈ GPUFP16~3 GB1B paramsβ¬ 0β₯ 0text-generationLanguageapache-2.0conversationallicense:apache-2.0View on Hugging Face
R1-Distill-Qwen-1.5B-OPD-Skywork-7B-Step200by leizhao7π₯οΈ GPUFP16~17 GB7B paramsβ¬ 0β₯ 0text-generationLanguagemitconversationaldataset:bytedtsinghua-sia/dapo-math-17klicense:mitView on Hugging Face
mtg-oracle-qwen3-4b-research-adaptersby vishvanandaπ₯οΈ GPUFP16~10 GB4B paramsβ¬ 0β₯ 0text-generationLanguageapache-2.0license:apache-2.0View on Hugging Face
R1-Distill-Qwen-1.5B-OPD-JustRL-Step200by leizhao7π₯οΈ GPUFP16~4 GB1.5B paramsβ¬ 0β₯ 0text-generationLanguagemitconversationaldataset:bytedtsinghua-sia/dapo-math-17klicense:mitView on Hugging Face
Qwen3.5-4B-OriginalBBQ-selfby MinaMilaπ₯οΈ GPUFP16~10 GB4B paramsβ¬ 0β₯ 0text-generationLanguageconversationalView on Hugging Face
Qwen3.5-4B-OriginalBBQ-Qwen7Bby MinaMilaπ₯οΈ GPUFP16~17 GB7B paramsβ¬ 0β₯ 0text-generationLanguageconversationalView on Hugging Face
Qwen2.5-1.5B-OriginalBBQ-selfby MinaMilaπ₯οΈ GPUFP16~4 GB1.5B paramsβ¬ 0β₯ 0OtherView on Hugging Face
Qwen2.5-1.5B-OriginalBBQ-Qwen7Bby MinaMilaπ₯οΈ GPUFP16~17 GB7B paramsβ¬ 0β₯ 0OtherView on Hugging Face
Phi4-mini-OriginalBBQ-Qwen7Bby MinaMilaπ₯οΈ GPUFP16~17 GB7B paramsβ¬ 0β₯ 0text-generationLanguageconversationalView on Hugging Face
Mistral7B-OriginalBBQ-selfby MinaMilaπ₯οΈ GPUFP16~17 GB7B paramsβ¬ 0β₯ 0OtherView on Hugging Face
Mistral7B-OriginalBBQ-Qwen7Bby MinaMilaπ₯οΈ GPUFP16~17 GB7B paramsβ¬ 0β₯ 0OtherView on Hugging Face
Llama3.1-8B-OriginalBBQ-selfby MinaMilaπ₯οΈ GPUFP16~20 GB8B paramsβ¬ 0β₯ 0OtherView on Hugging Face