Deploy & compare local models
GGUF / llama.cpp / Ollama-style runtimes, quantisation choices, context, VRAM, latency and practical fit across NVIDIA and AMD hardware.
a product guy who speaks fluently with engineers — and increasingly works directly with technical systems myself
solodkiy.cv
TECH
I’m an AI-native technical product builder and applied AI systems prototyper. I turn messy real-world problems into systems that humans and machines can actually test.
NOT CLAIMING
SOFTWARE ENGINEER
OR ML ENGINEER.
CLAIMING:
I CAN MAKE
TECHNICAL THINGS
EXIST — AND PROVE
WHAT THEY DO.
SOFTWARE ENGINEER
OR ML ENGINEER.
CLAIMING:
I CAN MAKE
TECHNICAL THINGS
EXIST — AND PROVE
WHAT THEY DO.
A product guy fluent in engineering, AI systems and regulated infrastructure
— without pretending to be a software engineer.
— without pretending to be a software engineer.
What I can actually operate.
I do not measure technical ability by whether I memorised the syntax. I measure it by whether I can frame the problem, specify constraints, direct the build, inspect the evidence, catch bad results and get to a reproducible artefact.
3
physical AI compute nodes
NVIDIA + AMD; different jobs, one lab.
24/24/12
GB GPU VRAM by node
Heterogeneous local inference rather than one-box demos.
128
tests in a full-stack identity reference build
AI-assisted implementation; inspectable repo and test suite.
0
AI authority override in the decision-plane demo
The model can propose evidence. It cannot overrule controls.
Orchestrate cloud → local execution
Use cloud reasoning as the planning/review layer while Linux-hosted CLI agents, local models and services do the execution.
Turn “seems better” into a test
Baselines, matched prompts, controlled conditions, synthetic cases, regression checks, raw evidence and explicit failure criteria.
Separate AI output from authority
Deterministic validation → First-Order Logic / Prolog → institutional policy / OPA, with AI kept outside the final authority path.
Run speech, image & research stacks
Local STT/TTS, image generation/editing, research pipelines and specialist model roles rather than forcing one LLM to do everything.
Direct AI-assisted full-stack builds
APIs, data models, onboarding logic, web/mobile surfaces, test suites and public technical artefacts — without pretending I hand-coded every layer.
LOCAL / SOVEREIGN AI
PLATE 01
PLATE 01
A small AI lab I built at home.
The point is not “three computers with Ollama”. The point is role separation: operator UX, reasoning, execution, inference and specialist media workloads do not need to live in the same place.
Olares One
- main local LLM services
- research / RAG experiments
- formal-methods work
- image generation / editing
- agent execution
↔
Minisforum
- second LLM worker
- AMD / Vulkan experiments
- matched model benchmarks
- parallel local inference
↔
Morefine
- Whisper speech-to-text
- local TTS / voice tests
- audio utilities
- small specialist workloads
CLOUD REASONING / REVIEW → TASK SPEC → WINDOWS COCKPIT → LINUX / LOCAL EXECUTION →
MODEL / TOOL OUTPUT → EVIDENCE → CLOUD REVIEW → REVISE OR ACCEPT
FLAGSHIP TECHNICAL CASE
PLATE 02
PLATE 02
AI can propose. It does not get authority.
My most useful technical thread so far: a reproducible synthetic demonstrator for regulated decisions, where model output must survive deterministic and formal checks before institutional policy can act.
SOVEREIGN DECISION PLANE / LIVE CASE 01
Same decision plane.
Different evidence.
Different outcome.
A local demonstrator that treats the LLM as a perception layer — not as the final decision authority. The public repo includes a reproducible path, committed artefacts and CI.
“The model may perceive and explain. It cannot override a failed deterministic control.”
DECISION PATH / MACHINE-INSPECTABLE
01 / Evidence
02 / Nemotron candidate observations
03 / Deterministic verification
04 / SWI-Prolog / First-Order Logic
05 / OPA / Rego institutional policy
06 / ALLOW · ESCALATE · BLOCK
07 / Evidence packet + SHA-256
GREEN / CONTROL
FORMAL: accept_extraction
ACTION: ALLOW
AI OVERRIDE: false
FORMAL: accept_extraction
ACTION: ALLOW
AI OVERRIDE: false
RED / MODEL-DERIVED
FORMAL: request_better_evidence
ACTION: ESCALATE_TO_HUMAN
AI OVERRIDE: false
FORMAL: request_better_evidence
ACTION: ESCALATE_TO_HUMAN
AI OVERRIDE: false
SELECTED BUILDS / 2026
PLATE 03
PLATE 03
Things you can open.
Not a gallery of every page I have made. A short evidence set showing the range: infrastructure, evaluation, identity systems, formal reasoning and AI-assisted product builds.
AI-01 / LOCAL INFRASTRUCTURELIVE LAB
Slava AI Lab
Three local compute nodes with distinct roles; local LLMs, research, audio and image stacks; NVIDIA ↔ AMD comparisons; cloud planning connected to local execution.
PROOF SIGNAL / measured VRAM, latency, context behaviour, services, local outputs
ID-02 / FULL-STACK REFERENCE BUILDPUBLIC REPO
LarePass Reference System
AI-assisted self-sovereign identity reference system with web + mobile surfaces, PostgreSQL, OpenAPI 3.1, generated clients and a branching KYC/KYB onboarding engine.
PROOF SIGNAL / 40+ endpoints · 36-node flow · 128-test suite
FL-03 / FORMAL REASONINGEXPERIMENT SERIES
FOL × Qwen × Nemotron
Experiments around whether natural-language model outputs can be translated into explicit, inspectable logic and then constrained by deterministic or institutional policy layers.
PROOF SIGNAL / Prolog · OPA/Rego · evidence regeneration · reproducible demo
RG-04 / REGULATED SYSTEMSDESIGN + PROTOTYPE
Revolut / Governed Agent
A set of experiments asking a harder question than “can an agent act?”: under what evidence, mandate, scope and revocation state should an agent be allowed to act?
PROOF SIGNAL / authority schema · scope · provenance · revocation · deterministic gates
MM-05 / MULTIMODAL LOCAL AIWORKING TOOLS
Audio + Image Local Stacks
Local speech recognition and TTS on a dedicated NVIDIA worker; ComfyUI image generation and editing on the main node; specialist workloads kept separate from the main LLM path.
PROOF SIGNAL / local WAV · local transcription · generated & edited images · isolated runtimes
DI-06 / DOMAIN DEPTH2025—2026
Digital Identity Research
The domain behind much of the technical work: reusable identity, compliance-grade architecture, proof-of-personhood, government wallets, KYC/KYB and AI-era institutional trust.
PROOF SIGNAL / public research repository · releases · reports · DOI-linked work
AI-NATIVE BUILD MODE
PLATE 04
PLATE 04
I don't compete with programmers at typing code.
My useful skill is the loop around the code: turning a hard problem into an executable experiment, using specialist AI and tools as leverage, and refusing to accept a green screen without evidence.
01FrameWhat is the actual problem? What is not the problem?
02SpecifyConstraints, invariants, schemas, expected outcomes.
03DelegateChoose cloud agent, CLI, local model or specialist tool.
04BuildLet the machine do machine work; keep architecture inspectable.
05AttackCounterexamples, false premises, edge cases, matched comparisons.
06VerifyDeterministic checks, tests, formal logic, CI, raw evidence.
07ShipRepo, page, report, benchmark or reproducible artefact.
Not claiming
- career software engineer
- ML researcher who designs model architectures
- CUDA / kernel / compiler specialist
- that every line in my repos was typed by me
Actually doing
- AI-native technical product building
- systems prototyping & orchestration
- local inference and model evaluation
- agent supervision and technical specification
- formal decision experiments
- AI-assisted full-stack prototyping
REVISION LEDGER / HOW EVIDENCE CHANGES THE SYSTEM
INCIDENT → INVARIANT → TEST
R001 / CHANNEL
A real channel is evidence, not authority.
Government-domain origin can start verification; it cannot release data.
R002 / HOLD
Irreversible disclosure stays null until authority resolves.
A “small provisional payload” still leaks. HOLD means zero outbound PII.
R003 / CAPACITY
Identity is not enough; current capacity must also hold.
The ontology changed when the evidence showed that role and authority can diverge.
WORKING TOOLBOX
PLATE 05
PLATE 05
The stack I can reason about and operate.
Not a keyword cloud. These are tools, layers and concepts that have appeared in working experiments or current builds.
| Layer | Current toolbox | What I use it for |
|---|---|---|
| Local LLM | Qwen · Nemotron · Mistral · Gemma-class experiments · abliterated sandbox models | Inference, extraction, synthesis, coding, adversarial comparisons. |
| Runtime | llama.cpp · Ollama · LM Studio · FreeToken experiments | Local serving, GPU offload, quantised inference, heterogeneous hardware tests. |
| Agents | ChatGPT/Claude / Codex/Caude CLI · desktop/CLI hand-off patterns | Plan → execute → inspect → revise loops across cloud and local environments. |
| Formal | SWI-Prolog · First-Order Logic · OPA / Rego · Z3-direction experiments | Make assumptions explicit; keep policy and AI output separable. |
| Research | Local Deep Research · SearXNG-style search layer · local LLM synthesis | Evidence-led research without treating the base model as a current-information oracle. |
| Media | ComfyUI · FLUX-class image models · Whisper · local TTS | Local image generation/editing and speech workflows. |
| Product build | OpenAPI · React / Vite · React Native / Expo · PostgreSQL · Docker Compose | AI-assisted reference systems and prototypes with inspectable interfaces and tests. |
| Evidence | Git · GitHub Actions · hashes · manifests · raw outputs · regression suites | Turn a demo into something another person can inspect and rerun. |
WHY THESE PROBLEMS?
PLATE 06
PLATE 06
I entered tech through institutions, not computer science.
Banking, fintech, compliance and digital identity taught me to care about who is allowed to do what, on whose evidence, under which rules.
Not a career change — the same profession.
Only the subject of trust changed: first the institution, now the model.
That is why my technical experiments keep converging on authority, evidence, provenance, identity, local control and regulated decision-making.
I am not trying to become a better programmer than programmers. I am learning to become very good at turning difficult institutional problems into systems that can be built, attacked, measured and inspected.
// OPEN TO HARD PROBLEMS
Give me a messy system with real constraints.
I’m most useful where product, AI, regulation, identity, infrastructure and institutional reality collide — and where a slide deck is not enough. I like turning the problem into something we can run.