LLM Development & Fine-Tuning
Outcomes
Consistent behaviour on a narrow task
Where a general model needs a long prompt and still varies, a fine-tuned model can produce reliable output from a short one. Consistency is often the real win rather than raw accuracy.
Lower cost at volume
A small fine-tuned model matching a large general model on one specific task can cut inference cost substantially. This only pays off above a volume threshold, which we calculate with your numbers before recommending it.
Data residency and control
Self-hosted open-weight models keep everything inside your infrastructure. For some regulated workloads this is the deciding factor regardless of cost.
Domain language handled correctly
Specialised terminology, internal abbreviations and industry conventions that general models handle inconsistently.
What we build
Training data preparation. The dominant cost and the dominant determinant of success. Collection, cleaning, labelling, deduplication, and building held-out evaluation sets. A thousand well-constructed examples routinely outperform ten thousand noisy ones.
Fine-tuning pipelines using parameter-efficient methods — LoRA and QLoRA — which achieve most of the benefit at a fraction of the compute of full fine-tuning, and are what almost every practical project should use.
Evaluation. Task-specific benchmarks measuring whether the tuned model actually beats the baseline. Including the honest possibility that it does not, in which case we say so rather than shipping it.
Self-hosted inference with quantisation, batching and autoscaling — sized against real load rather than peak fantasy.
Model routing so the tuned model handles the task it was built for and a general model handles everything else. Most systems benefit from more than one model.
Retraining process. Fine-tuned models drift as your data and language change. We build the pipeline to refresh them rather than leaving you with a model that quietly ages.
How it works
Week 1 — Feasibility. We establish whether fine-tuning is the right tool at all. This means baselining a well-prompted general model first. If the baseline meets your requirement, we recommend stopping there and say so — it is a shorter engagement and the correct answer.
Weeks 2–4 — Data preparation. Assembling and cleaning training data, building the held-out evaluation set. Consistently the longest phase and the one that determines the outcome.
Weeks 4–5 — Training and iteration. Base model selection, hyperparameter tuning, multiple runs measured against the evaluation set. Fast compared to data preparation.
Weeks 5–7 — Deployment. Inference infrastructure, quantisation, load testing, monitoring, routing and fallback.
Ongoing. Performance monitoring, drift detection, periodic retraining.
Seven weeks is typical where usable training data already exists. Where it must be created or labelled from scratch, add several weeks — and be sceptical of anyone who quotes a fine-tuning timeline without asking about your data first.
Technology
Base models: Llama, Mistral, Qwen and Gemma for open-weight work; provider fine-tuning APIs where hosted is acceptable and simpler.
Training: LoRA and QLoRA via Hugging Face PEFT, Axolotl or Unsloth. Full fine-tuning only where the case is unusually strong.
Serving: vLLM, TGI or Ollama depending on scale; GPU sizing calculated against real throughput requirements.
Evaluation: task-specific benchmarks plus held-out sets. Public leaderboards are close to useless for narrow production tasks.
Where this applies
Strongest where a narrow high-volume task runs constantly, where output format must be rigidly consistent, or where data cannot leave your infrastructure.
Weakest where the task is broad, the volume is low, or the knowledge changes frequently. Changing knowledge is a retrieval problem, not a training problem — fine-tuning a model on facts that will be outdated next quarter is a common and expensive mistake.
How we scope and price
Fixed scope, quoted after a feasibility assessment — and the assessment can legitimately conclude that no fine-tuning project is warranted. Cost is driven overwhelmingly by training-data readiness: an existing labelled dataset makes this a modest engagement, while creating and labelling one from scratch dominates the budget. Self-hosted inference carries ongoing GPU cost that we model before you commit.
Frequently asked questions
RAG for knowledge, especially knowledge that changes or requires citation. Fine-tuning for behaviour — style, format, specialised task performance. If the requirement is "the model should know our documentation", that is RAG. If it is "the model should always respond in this exact structure", that is fine-tuning. They combine well.
For task-specific fine-tuning, several hundred to a few thousand high-quality examples is often sufficient. Quality and consistency matter far more than volume — inconsistent labelling teaches the model to be inconsistent.
On its specific narrow task, often yes, and at much lower cost. On anything outside that task, no — and it may be worse than before. This is why routing matters.
Not with self-hosting. With provider fine-tuning APIs, it depends on their terms, which we review with you before recommending a route.
GPU cost, which is continuous rather than per-request. It becomes cheaper than API pricing above a volume threshold and more expensive below it. We calculate that threshold with your actual numbers rather than assuming self-hosting is cheaper.
Depends on how fast your domain and data change. Some models run for a year unchanged; others need quarterly refreshes. Drift monitoring tells you rather than a calendar.
Fine-tuning availability varies by provider and model, and changes over time. We check current availability at the point of scoping rather than assuming, and compare it against open-weight alternatives.
More AI services
AI Strategy Consulting
Turn scattered AI ambition into a sequenced, costed plan. We decide what to build, what to buy, what to ignore, and in what order.
AI Readiness Audit
A 3–4 week assessment of your data, systems and processes that returns a ranked, costed list of AI use cases and an honest verdict on what you can deploy now.
Agentic AI Automation
We build AI agents that complete multi-step work inside your systems — with defined scope, human checkpoints, and evaluation. Deployed to production, not demos.