[{"data":1,"prerenderedAt":113},["ShallowReactive",2],{"categories-init":3,"subcategory-fine-tuning":4,"category-meta-data-ml-libraries":73,"score-types":77,"pricing-models":99},true,{"subcategory_id":5,"name":6,"slug":7,"description":8,"category_id":9,"display_order":10,"tool_count":11,"tools":12},67,"Fine-Tuning","fine-tuning","Libraries and tools for fine-tuning open-weight models — LoRA\u002FQLoRA adapters, quantization, and memory-efficient training that runs on consumer or single-GPU setups. You reach for these to specialise a base model (Llama, Qwen, Mistral) on your own data without full pretraining. Distinct from ML Frameworks (the underlying training engines) and ML Operations (experiment tracking).",14,30,1,[13],{"tool_id":14,"name":15,"slug":16,"tooltip_description":17,"logo_url":18,"logo_bg":19,"pricing_model":20,"learning_curve_score":24,"popularity_score":25,"hosting_assignment_type":26,"hosting_provider_restriction":27,"hosting_target_restriction":27,"hosting_compatible_tool_ids":28,"parent_tool_id":28,"category":29,"subcategory":32,"categories":33,"subcategories":36,"flexibility_score":25,"performance_score":38,"portability_score":38,"is_featured":39,"tags":40,"score_reasonings":66,"published_date":72,"last_updated_date":28},236,"Unsloth","unsloth","An open-source library for fast, memory-efficient fine-tuning of open-weight LLMs — custom fused kernels cut VRAM use by roughly 70% and speed up LoRA\u002FQLoRA training ~2x, making single-GPU and consumer-hardware fine-tuning practical.","https:\u002F\u002Fassets.tekyous.dev\u002Flogos\u002Ftools\u002Funsloth.png","dark",{"slug":21,"display_name":22,"description":23},"open_source","Open Source","Source code is publicly available and free to use, modify, and distribute. No paid plans from the project itself.",3,4,"library","open",null,{"category_id":9,"name":30,"slug":31},"Data & ML Libraries","data-ml-libraries",{"subcategory_id":5,"name":6,"slug":7},[34],{"category_id":9,"name":30,"slug":31,"is_primary":3,"display_order":35},0,[37],{"subcategory_id":5,"name":6,"slug":7,"category_id":9,"is_primary":3,"display_order":35},5,false,[41,45,49,53,57,62],{"tag_id":11,"name":42,"slug":43,"tag_type":44},"Python","python","technology",{"tag_id":46,"name":22,"slug":47,"tag_type":48},11,"open-source","feature",{"tag_id":50,"name":51,"slug":52,"tag_type":48},12,"Self-hostable","self-hostable",{"tag_id":54,"name":55,"slug":56,"tag_type":48},16,"AI-powered","ai-powered",{"tag_id":58,"name":59,"slug":60,"tag_type":61},25,"Machine Learning","machine-learning","use_case",{"tag_id":63,"name":64,"slug":65,"tag_type":61},39,"Data Science","data-science",{"learning_curve":67,"flexibility":68,"performance":69,"popularity":70,"portability":71},"The prebuilt Colab and Kaggle notebooks make a first fine-tune approachable, but producing a genuinely good model still requires dataset preparation, hyperparameter tuning, and evaluation skill.","Covers LoRA, QLoRA, full fine-tuning, pretraining, and RL methods across many model families, though it is purpose-built for fine-tuning rather than a general training framework.","Hand-written fused kernels deliver roughly 70% memory reduction and about 2x faster training with no accuracy loss, best-in-class for efficient fine-tuning.","One of the most-starred projects in the fine-tuning space and a common default in tutorials, with widely used quantized model releases on Hugging Face.","Apache 2.0 licensed, self-hostable on any compatible GPU, and exports adapters to GGUF, Ollama, and vLLM, so trained models run anywhere with no lock-in.","2026-09-27",{"category_id":9,"name":30,"slug":31,"description":74,"icon_url":75,"display_order":9,"tool_count":76},"Libraries for data manipulation, machine learning, and statistical analysis.","https:\u002F\u002Fassets.tekyous.dev\u002Ficons\u002Fcategories\u002Fdata-ml-libraries.svg",10,[78,82,87,91,95],{"slug":79,"name":80,"description":81,"display_order":11},"popularity","Popularity","How widely adopted the tool is in the developer community. 1 = niche; 5 = mainstream and widely used.",{"slug":83,"name":84,"description":85,"display_order":86},"learning_curve","Learning Curve","How quickly a developer can become productive with this tool. 1 = beginner-accessible; 5 = steep, requires significant prior experience.",2,{"slug":88,"name":89,"description":90,"display_order":24},"flexibility","Flexibility","How much you can customise or extend the tool for your specific needs. 1 = highly opinionated with few escape hatches; 5 = highly flexible.",{"slug":92,"name":93,"description":94,"display_order":25},"performance","Performance","How well the tool performs its primary function. For runtimes: execution speed. For services: throughput and latency. For editors: responsiveness. 1 = slow or resource-heavy; 5 = fast and efficient.",{"slug":96,"name":97,"description":98,"display_order":38},"portability","Portability","How easy it is to migrate away from this tool once you are invested in it. Based on: data\u002Fcode exportability, skills transferability to other tools, and adherence to open standards. 1 = high lock-in; 5 = fully open, skills transfer universally.",[100,101,105,109],{"slug":21,"display_name":22,"description":23,"display_order":11},{"slug":102,"display_name":103,"description":104,"display_order":86},"freemium","Freemium","A free tier is available; additional features, usage limits, or managed hosting require a paid plan.",{"slug":106,"display_name":107,"description":108,"display_order":24},"paid","Paid","No meaningful free tier — a subscription or one-time purchase is required to use the tool.",{"slug":110,"display_name":111,"description":112,"display_order":25},"usage_based","Usage-Based","Pricing scales with consumption: API calls, data volume, compute time, or similar metered units.",1790518774356]