{
  "data": null,
  "kind": "anchor.page",
  "links": {
    "api": "https://www.anchorterminal.com/api/v1/index.json",
    "html": "https://www.anchorterminal.com/niches/fine-tuning.local-lora/",
    "json": "https://www.anchorterminal.com/niches/fine-tuning.local-lora/index.json",
    "llms": "https://www.anchorterminal.com/llms.txt",
    "markdown": "https://www.anchorterminal.com/niches/fine-tuning.local-lora/index.md",
    "mcp": "https://www.anchorterminal.com/mcp",
    "slim": "https://www.anchorterminal.com/niches/fine-tuning.local-lora/index.min.md"
  },
  "markdown": "No company's docs show a full fit yet. The listings below do the job with a limit, or not at all.\n\n| Companies, full fit | With a limit | Carry the tag | Share of the category's work | First-hand accounts |\n| --- | --- | --- | --- | --- |\n| 0 | 2 | 13 | 15 | 8 |\n\n## What counts as done\n\nA documented config or notebook for the chosen base model runs to completion on the stated GPU, the chat template and end-of-turn token are trained so the model stops, the docs state the minimum VRAM and supported accelerators, and the adapter is saved to disk.\n\nMeasured, for our own tests: a LoRA run on a 7-8B model over 1,000 examples finishes in under an hour on one 24 GB GPU.\n\nHow agents ask for it: fine-tune Llama on my chat logs; QLoRA Qwen on my GPU; train a small model for my app on my own machine\n\n## Does the job, with a limit\n\nIt does the job, but something in the docs or a user's account will get in an agent's way. The limit is named in each row.\n\n- **Axolotl (Axolotl AI)**: YAML configs per model, chat_template with roles_to_train and train_on_eos, and NVIDIA (Ampere or newer) or AMD support are documented, but no VRAM table was found, and acc-08 saw a new model crash in the first forward pass and acc-09 an example whose end-of-turn token was not trained.\n- **Unsloth (Unsloth)**: A VRAM table (8B: 6 GB QLoRA, 22 GB LoRA), NVIDIA, AMD, Intel and Mac support and get_chat_template with EOS mapping are documented, but acc-07 saw a script fail on a conversation format, acc-13 flat loss, and acc-47 no NPU backend.\n\n- not this job: Amazon Bedrock model customisation (Amazon Web Services, Inc.): A hosted AWS service; training runs in Bedrock.\n- not this job: Microsoft Foundry fine-tuning (Azure OpenAI) (Microsoft Corporation): A hosted service; training runs on Azure capacity.\n- not this job: Fireworks AI Fine-tuning (Fireworks.ai, Inc.): Training runs on Fireworks GPUs, serverless or dedicated; there is no local trainer.\n- not this job: Nebius Token Factory fine-tuning (Nebius B.V.): A hosted service; jobs run on Nebius GPUs.\n- not this job: Tinker (Thinking Machines Labs, Inc.): The loop runs locally but training runs on Thinking Machines' GPUs; nothing trains on the user's own card.\n- not this job: Together AI Fine-tuning (Together Computer, Inc.): A hosted service; training runs on Together's GPUs, not the user's.\n- not this job: Vertex AI Gemini tuning (Google LLC): A hosted Google Cloud service; training runs on Google's accelerators.\n\n## What stops agents finishing\n\n- new model architecture crashes in the first forward pass\n- end-of-turn token not trained so the model never stops\n- accelerator (Ascend, Intel, some AMD) not supported\n\n## Around it\n\nBefore: gpu-compute.find-and-provision, gpu-compute.training-run. After: fine-tuning.export-and-serve.\n\n## Where this comes from\n\nWeight 15 of 100 in Fine-tuning: 8 of 47 accounts: Unsloth and Axolotl issues (new-model crashes, templates, flat loss, accelerator support), Hacker News reports of quick Gemma tunes, and one forum thread on an on-device model\n\nAs data: https://www.anchorterminal.com/api/v1/use-cases/fine-tuning.local-lora.json, or the MCP tool get_use_case with id fine-tuning.local-lora. Draft, read 2026-11-15 from public docs and first-hand accounts, not yet reviewed by a person.\n",
  "meta": {
    "attribution": "Anchor Terminal (https://www.anchorterminal.com)",
    "attributionRequired": true,
    "credit": "CC BY 4.0, credit Anchor Terminal and link the page or API address you took it from (https://www.anchorterminal.com/terms/#data)",
    "docs": "https://www.anchorterminal.com/docs/",
    "generatedAt": "2026-11-16",
    "license": "CC-BY-4.0",
    "method": "https://www.anchorterminal.com/benchmark/",
    "methodology": "0.8",
    "openapi": "https://www.anchorterminal.com/openapi.json",
    "preview": false,
    "run": "2026-10-01",
    "runLabel": "October 2026 research run",
    "terms": "https://www.anchorterminal.com/terms/#data"
  },
  "page": {
    "breadcrumbs": [
      {
        "name": "Home",
        "url": "https://www.anchorterminal.com/"
      },
      {
        "name": "For agents",
        "url": "https://www.anchorterminal.com/agents/"
      },
      {
        "name": "Niches",
        "url": "https://www.anchorterminal.com/niches/"
      },
      {
        "name": "Tune an open model with LoRA on your own or rented GPU",
        "url": ""
      }
    ],
    "description": "Tune an open model with LoRA on your own or rented GPU: 0 companies fully do it, 2 with a limit, 13 carry the tag. Every listing in Fine-tuning with the reason and a source.",
    "facts": null,
    "h1": "Tune an open model with LoRA on your own or rented GPU",
    "image": "https://www.anchorterminal.com/assets/og/default.png",
    "path": "/niches/fine-tuning.local-lora/",
    "published": "",
    "section": "agents",
    "title": "Tune an open model with LoRA on your own or rented GPU | Anchor…",
    "toc": null,
    "updated": "2026-11-15",
    "url": "https://www.anchorterminal.com/niches/fine-tuning.local-lora/"
  },
  "tokens": {
    "markdown": 1000,
    "slim": 230
  },
  "version": 1
}
