Tune an open model with LoRA on your own or rented GPU
No company's docs show a full fit yet. The listings below do the job with a limit, or not at all.
What counts as done
A 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.
Measured, 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. No docs we read state these figures, so they don't count against a listing here.
How 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
Does the job, with a limit 2
It 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.
| Listing | Why |
|---|---|
| Axolotl B 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. source |
| Unsloth C 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. source |
Doesn't do this job 7
Listings in the category that do something else, with the reason.
| Listing | Why |
|---|---|
| Amazon Bedrock model customisation A Amazon Web Services, Inc. | A hosted AWS service; training runs in Bedrock. source |
| Microsoft Foundry fine-tuning (Azure OpenAI) C Microsoft Corporation | A hosted service; training runs on Azure capacity. source |
| Fireworks AI Fine-tuning B Fireworks.ai, Inc. | Training runs on Fireworks GPUs, serverless or dedicated; there is no local trainer. source |
| Nebius Token Factory fine-tuning D Nebius B.V. | A hosted service; jobs run on Nebius GPUs. source |
| Tinker D Thinking Machines Labs, Inc. | The loop runs locally but training runs on Thinking Machines' GPUs; nothing trains on the user's own card. source |
| Together AI Fine-tuning C Together Computer, Inc. | A hosted service; training runs on Together's GPUs, not the user's. source |
| Vertex AI Gemini tuning B Google LLC | A hosted Google Cloud service; training runs on Google's accelerators. source |
What stops agents finishing
- new model architecture crashes in the first forward pass
- end-of-turn token not trained so the model never stops
- accelerator (Ascend, Intel, some AMD) not supported
Around it
Before: gpu-compute.find-and-provision, gpu-compute.training-run. After: fine-tuning.export-and-serve.
Where this comes from
Weight 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
The same as data: /api/v1/use-cases/fine-tuning.local-lora.json, or the MCP tool get_use_case with id fine-tuning.local-lora. Other jobs in this category: /api/v1/niches?category=fine-tuning.
For companies
Do agents find, use and choose your tools?
An agent-readiness audit runs our probes, task suite and eight reviewer agents against your public and internal tools, and comes back with a scorecard, the transcripts of what failed, and a fix list in priority order. From $2,500, re-run included. We never take payment to move a rank. We do help companies earn one.