Custom model training
Custom model training: LLM fine-tuning for one high-volume task
We fine-tune an open-weight model on your labelled cases for one defined task, then test it against your current model on cases it has never seen. You switch only if it costs less and is at least as accurate. Cloudsail does this work for companies across Europe, with engineers in Germany and Poland.
Our team has built software and production AI for
What a narrow task needs from a model
Frontier models are trained to handle almost any request. A task such as classification, extraction, scoring or routing needs one behaviour, done reliably. Cases you have already labelled teach a smaller model exactly that.
Your past cases
Records where the right answer is already known, such as confirmed fraud, corrected extractions or resolved tickets.
Base model
An open-weight model with a few billion parameters. It fits on a single GPU, and its licence allows commercial use.
Fine-tuning
The base model learns from your known outcomes through supervised fine-tuning or reinforcement learning, with LoRA adapters.
Comparison
The model you use today and the new one answer the same cases, none of them seen in training. We compare accuracy, latency and cost per request.
What a training project involves
On rented GPUs, a training run finishes within hours. Most of the effort goes into the training data and the test set, and into operating the model in your infrastructure once real requests reach it.
Data and tests
Model training
In production
When a task is worth its own model
The thresholds below come from our own cost models, and we check them against your real traffic.
Volume
A single task that receives several hundred thousand requests a month
Labels
The true outcome of each case becomes known later
Control
Strict response-time limits, or data that must stay on your own systems
Below these thresholds, a smaller hosted model is the cheaper choice, and that is what we recommend.
Talk to an engineerHow the two models compare on your cases
We run both models on one set of held-out cases and report accuracy, latency and cost next to each other. The trained model takes over only if it is cheaper to run and loses no accuracy.
Frontier model compared with a trained model
Example with synthetic data
At 2 million requests a month, the cost falls from €9600 to €1400
Your data and the model stay under your control
We take no payments from model or tool vendors. Our recommendations depend only on how each option performs on your task.
Your training data does not leave your environment.
You own the weights of the trained model.
We record test results and decisions so your auditors can follow them.
We deal with your works council's requirements early on.
Questions
Do you charge for the first call?
No. You talk to one of our engineers for 30 minutes about the task you have in mind. You don't share any data, and we don't need access to your systems.
Is there evidence that a small trained model can beat a frontier model?
Yes, for narrow tasks with good labels. In October 2026, Coinbase reported that a Qwen3.5-9B model trained on its own fraud outcomes did better than a frontier model, with less than half the latency. For open-ended reasoning, or tasks that draw on broad knowledge, frontier models remain the better choice.
What if the trained model falls short of our current one?
Then you keep your current model. The test set and the evaluation pipeline stay with you, and you can use them to choose and monitor any model you run later.
Have you trained and run models in production before?
Yes. Our engineers trained computer vision models on more than 100 million images and ran them for a website with millions of visitors a day. We still work in the order we used then: first the test set, then the training, then monitoring once the model is live.
What do you need from us?
A task with enough volume and earlier cases whose outcomes you know, ideally several thousand of them. We also need one or two hours a week from a domain expert who can judge the model's answers.
What if we can't share production data?
Then training starts from open datasets or synthetic data. Or we begin with model selection: we compare existing models on your task and train only if it still pays off.
Which base models do you work with?
Open-weight models whose licences allow commercial use, such as Qwen, Gemma, Mistral, Granite and gpt-oss. The terms differ between models. Some exclude companies above a certain size or companies based in the EU, so we check them for every project. If your procurement rules require it, we use models of European or US origin.
How does the EU AI Act affect a fine-tuned model?
LoRA fine-tuning needs only a small fraction of the compute that went into training the original model. That is well below the threshold the Commission's guidelines set for becoming the provider of a general-purpose AI model. Your obligations then depend on what the model is used for. We prepare the documentation your data protection and compliance teams need, and the legal assessment remains with your counsel.
When to retrieve and when to fine-tune
Retrieval supplies facts that change, such as current prices, policies or product documentation. The model looks them up when it answers, so an update needs no new training run.
Fine-tuning teaches repeatable behaviour. A model that sorts incoming claims into your categories, or pulls the same fields from every invoice, learns that pattern from your past cases.
Related services
AI agent evals
Evals for agents that act in your systems: outcomes, tool calls and how reliably a run repeats.
AI automation
Business processes automated step by step with rules, models and agents, tested on past cases and reported as cost per case.
AI chatbots
Chatbots and assistants for customer service and internal support that answer from your data, act through approved tools and hand over to people.
AI consulting
AI strategy, use case assessment and readiness checks from engineers who also build and measure the first system.
AI engineers for your team
Experienced AI engineers who join your team part-time or for longer and build AI features, agents and platforms with you.
AI evals engineering
Evals for AI products, agents and RAG, built from your own traces, with a test set and release gate that stay in your repository.
Enterprise AI
Assistants, agents and private AI built into your systems, with your permissions, audit logs and a platform team that can run them.
MCP server development
MCP servers that connect approved internal APIs to AI assistants, with narrow permissions, approval for changes and tests.
RAG development
Assistants that answer from your internal documents, with permissions, citations and tests on your own questions.
RAG evaluation
Assistants that answer from your documents, tested on retrieval and on answers, in each language your users write in.
From the blog
RAG or fine-tuning?
Decision criteria for choosing retrieval, fine-tuning or both: whether the task needs changing knowledge or consistent behaviour, with a worked table and an order of work.
Fine-tuning data quality
Four checks that show whether your examples are ready for fine-tuning: label errors, coverage of real traffic, provenance and leakage into the test set.
Fine-tuned model evaluation
How to show that a fine-tuned model should replace the current one: acceptance criteria written in advance, a fair held-out comparison, and cost and latency in the same table.
Talk to an engineer
Bring one piece of work you would like to improve. The call takes 30 minutes and needs no access to your systems or your data.
Look for the draft in your email program
Send it from there, and an engineer replies in person with times for a 30-minute call. If no draft has opened, write to us at miki@cloudsail.com.