AI Engineering · Models you own

We train, release, and run specialised AI models you own.

Naderu is an AI-models company. Not a chatbot, not an API wrapper — the engineering that turns a foundation model into a dependable, domain-specialised model your organization owns and can deploy anywhere. Engineered, not merely prompted.

TrainReleaseServeDeploy anywhereEvery model, evaluated

What we do

Three things, done properly.

We are deliberately narrow. The product is the model — and the engineering that makes it trustworthy.

01

Train

Fine-tune, adapt (LoRA), distill, and quantize foundation models into specialised ones. Data engineering and evaluation are first-class, not afterthoughts.

02

Release

Publish models with real model cards, benchmarks, and clear licensing. Every release names its upstream foundation model — no black boxes.

03

Serve

Consulting, customization, deployment, and operations — the engineering around models, sold as services. You own the result.

Engineered, not prompted

A prompt is one layer. A model is a lifecycle.

Real enterprise AI is data, training, evaluation, deployment, and monitoring — versioned and reproducible end to end.

01 / DATA
Data engineering
Collection, cleaning, formatting, lineage & governance.
02 / TRAIN
Training
Fine-tune · LoRA · distill · quantize, as versioned recipes.
03 / EVAL
Evaluation
The gate: accuracy, hallucination, latency, cost, safety.
04 / SHIP
Deployment
On-prem, cloud, private cloud, or edge — owned by you.
05 / OPS
Monitoring
Continuous evaluation and improvement in production.

Evidence over claims

Every model ships with its receipts.

No model reaches release until it passes its evaluation gate. Cards and benchmarks are part of the product.

RELEASED · v0.1.0 · 2026-07-14live on 🤗 Hugging Face

naderu-geek-py-0.5b

Our first public portfolio model: a compact LoRA fine-tune of Qwen2.5-Coder-0.5B-Instruct (Apache-2.0) that imprints a clean, commented-Python style and a recognisable naderu-geek identity. It demonstrates our pipeline — data → training → evaluation → release — end to end. It is a demonstration piece, not a capability claim: coding ability tracks the base. It passed a qualitative smoke eval (identity recognised · coherent Python), with the card and provenance stated plainly.

RELEASED · v0.1.0 · 2026-07-15live on 🤗 Hugging Face

naderu-loom-7b

An offline interactive-fiction narrator: given a game state and the player's action, it returns a single JSON turn (scene + 2–4 choices + state changes) an app can render and apply — a game master that runs on-device. A QLoRA fine-tune of Mistral-7B-Instruct-v0.3 (Apache-2.0), trained on Apple Silicon. Unlike a smoke test, it ships a quantitative eval gate — and passes it: 100% valid JSON and 0 world-state violations across 34 scripted turns.

RELEASED · v0.1.0 · 2026-07-19live on 🤗 Hugging Face

hunter-crypto-7b

The first model of the Hunter family — a local cryptography-attack specialist for authorized security and CTF work. Given a weak or misconfigured construction, it names the flaw and emits a runnable attack script that recovers the secret, fully offline on Apple Silicon. A QLoRA fine-tune of Qwen2.5-Coder-7B-Instruct (Apache-2.0). Its gate is execution-graded — the attack recovers the secret or it does not — and it passes: 100% solve rate on the in-distribution held-out set and 97% on an independent-method set. A narrow specialist, authorized use only.

MODEL CARDnaderu-geek-py-0.5b
model
naderu-geek-py-0.5b
foundation
Qwen2.5-Coder-0.5B-Instruct (Apache-2.0)
task
Python coding assistant · identity + style
method
LoRA (r=16, α=32) · merged · fp32→bf16
data
39 examples · license-clean · in-repo
license
Apache-2.0 · inherits upstream terms
status
passed eval gate
EVAL · smoke · 2026-07-14PASS
checkoutcome
identity recognisedyes
coherent, runnable Python3/3
held-out identity denialpass
held-out style transferpass
provenance & licence statedyes

Honest scope — this is a qualitative smoke eval, not a capability claim: naderu-geek's coding ability tracks its base. Capability-claiming releases carry reproducible quantitative benchmarks tied to a versioned eval suite.

MODEL CARDhunter-crypto-7b
model
hunter-crypto-7b
foundation
Qwen2.5-Coder-7B-Instruct (Apache-2.0)
task
Crypto-attack scripts · authorized security / CTF
method
QLoRA (r=8) · MLX · merged bf16
data
synthetic · gate-validated · 6 categories · license-clean
license
Apache-2.0 · inherits upstream terms
status
passed eval gate
EVAL · hunter-crypto v1 · 2026-07-19PASS
held-out tierbase → trained
in-distribution solve_rate (48)0.333 → 1.000
valid-script rate (48)0.333 → 1.000
independent-method (36)0.250 → 0.972
OOD-hard (24 · reported)0.000 → 0.125

Capability claim, backed — unlike a smoke eval, hunter-crypto ships reproducible, execution-graded benchmarks tied to a versioned suite. It is a narrow specialist: strong on its six trained attack families, not a general cryptanalysis engine (see the OOD tier).

Own it · Deploy anywhere

Your model. Your infrastructure. Your data.

Privacy by default. Run where compliance and cost demand — we don't hold your model hostage.

On-premise Cloud Private cloud Edge & embedded AWS · Azure · GCP · bare metal
RESTOpenAPIMCPONNXGGUFHuggingFace

Services

Engineering, delivered as a partnership.

Consulting

Where a specialised model beats a general API — with the roadmap and ROI to prove it.

Customization

Fine-tune, distill, and quantize a foundation model to your domain and data.

Deployment

Stand the model up where you want it — cloud, private, or edge — and hand you the keys.

Operations

Monitoring, re-evaluation, and continuous improvement of models in production.

Build your model

Come build an intelligent capability you own.

Tell us the problem. We'll tell you whether a specialised model is the right tool — and if so, engineer it end to end.