Open-source tooling and open-weight models, matched to the device.
selbsai is configured around memory, thermal and latency envelopes. That means the configurator maps to workload packages and model/runtime fit, not to one frozen marketing name. The stack combines classic open-source software with open-weight model releases, and the exact deployment is matched to your device, languages, workload and licensing profile at provisioning time.
Personal chat + light knowledge
Curated local assistant stack for fast private drafting and Q&A
Fast local assistance for private chat, email drafting, small document Q&A and day-to-day offline copilots.
- RAM floor
- 16 GB
- Target speed
- 15-40 t/s
Documents + retrieval + coding support
Curated local knowledge stack with retrieval, longer context and workflow tools
Balanced local reasoning for document-heavy work, private search, research, coding support and office assistants.
- RAM floor
- 32 GB
- Target speed
- 12-30 t/s
High-memory local agent node
Curated high-memory stack for coding agents, orchestration and heavier secure workloads
High-memory local intelligence for coding agents, larger private knowledge bases, orchestration and heavier secure workloads.
- RAM floor
- 64 GB
- Target speed
- 8-18 t/s
Representative model families we actually watch.
These are representative families used to calibrate the current selbsai workload packages. Exact shipped models can change as newer open releases and faster local runtimes prove better on independent benchmarks.
Llama 3.1 8B Instruct
Meta Llama · Meta
Our compact baseline for fast local assistants, offline drafting and lighter retrieval on personal desktop devices.
Ministral 3 14B Instruct
Mistral / Ministral · Mistral
A strong local step-up for multilingual work, long-context tasks and richer instruction-following on balanced desktop systems.
Gemma 4 E4B / 26B A4B
Google Gemma · Google DeepMind
A model family we track for responsive multimodal chat, coding assistants and agentic workflows because Gemma 4 combines long context, native function-calling support and multi-token prediction drafters.
Qwen3 30B A3B
Qwen · Qwen
One of the main higher-capability open families we watch for larger reasoning, coding and multilingual deployments on high-memory local devices.
Artificial Analysis
Independent model pages with direct comparisons across intelligence, speed, price, context window and methodology notes.
Hugging Face Open LLM Leaderboard
A widely used open-model benchmark hub for comparing community and lab releases across standard eval suites.
Arena Leaderboard
Useful for broad human-preference comparisons and keeping an eye on how major open releases stack up in live arena-style evaluation.
What actually gets installed
We do not promise that every workload package always ships with the same named model. A serious local AI hardware shop should choose the right open-weight stack for the job and update that recommendation as open models, drafters and local runtimes improve.
- The workload package determines the feasible memory floor, latency envelope and supporting tools.
- Workflow presets determine tooling around the base model: coding support, document review, retrieval, operations support, or audit features.
- Final selection depends on language mix, data sensitivity, licensing constraints and whether the build optimizes for speed, depth or multimodality.
- When acceleration paths such as Gemma-style MTP drafters, MLX, Ollama, vLLM or SGLang become the best fit, they can be adopted without changing the customer's workflow.
- Benchmark positions move over time, so this page links out to live third-party references instead of freezing stale claims into marketing copy.
Hugging Face scale is useful only after filtering.
The value for customers is not simply that open models exist. The value is that selbsai turns a fast-moving model ecosystem into a controlled local setup with documented choices, workload fit, and a clear update channel.
Source reputation
Publisher history, release notes, model-card quality, community usage, and maintenance signals are reviewed before a model is treated as a provisioning candidate.
License and usage fit
The configurator now captures whether the customer wants permissive-only, commercial-ready, or restricted-model avoidance before final model selection.
Safe format preference
Where supported, selbsai prefers formats and runtimes with clearer supply-chain posture, including Safetensors, GGUF, MLX packages, and established local runtimes.
Hardware match
The selected model/runtime stack is checked against RAM, VRAM, thermal budget, storage, context length, and the customer's target workloads.
What the customer should know about the installed stack.
- Model family, exact source repository, publisher, model-card link, and release reference.
- Runtime path, file format, quantization level, checksum or verification reference where available.
- License posture, intended use, known limitations, language fit, and benchmark references.
- Selected update policy: stable, balanced, or fast track.
OCR and document extraction
For invoice, receipt and document-heavy presets we pair the language model with open OCR and document-understanding tooling rather than relying on the base LLM alone.
Retrieval and reranking
Search-heavy presets use additional embedding and reranking components so large local indexes stay usable at real-world scale.
Preset workloads
Software coding
Local help for private repositories.
Explain code, draft tests, review snippets, write scripts, and search repository notes without sending proprietary source to cloud tools.
- Repo-aware Q&A
- Test and script drafts
- Error explanation
Documents and writing
Draft, rewrite, summarize, extract.
Create letters, policies, proposals, memos, summaries, and structured extracts from files that should stay inside your office.
- PDF & DOCX ingestion
- Memo and report drafts
- Tables and summaries
Email and personal assistant
Inbox work without inbox exposure.
Draft replies, sort messages, extract tasks, prepare agendas, and turn notes into follow-ups from approved local exports.
- Reply drafts
- Action extraction
- Meeting follow-ups
Research desk
Turns reading piles into briefings.
Compare sources, summarize PDFs, answer questions with citations, and prepare decision notes from local research folders.
- Citation-aware Q&A
- Long-context search
- Briefing notes
Document review
Find clauses, risks, gaps, and dates.
Review contracts, policies, case files, leases, and due-diligence packs for obligations, inconsistencies, and missing attachments.
- Clause search
- Obligation extraction
- Risk and gap lists
Sales assistant
Prepare better conversations faster.
Draft outreach, summarize accounts, prepare call notes, handle objections, and build proposals from approved sales material.
- Proposal drafts
- Call preparation
- CRM-style summaries
Compliance management
Policies and evidence, searchable locally.
Answer audit questions, compare obligations, identify missing evidence, and prepare control summaries from internal policy folders.
- Policy Q&A
- Evidence checklists
- Audit response drafts
Warehouse management
Operations support from local records.
Search SOPs, summarize shift notes, prepare supplier messages, and answer operational questions from warehouse documentation.
- SOP search
- Shift note summaries
- Supplier message drafts
Inventory management
Stock lists, reorder issues, and reports.
Review stock exports, flag reorder risks, summarize item movements, and prepare plain-language inventory reports.
- CSV and table review
- Reorder flags
- Inventory summaries
Company knowledge base
Ask your manuals, folders, and notes.
Build a local question-answer layer over manuals, procedures, project folders, email exports, and internal documentation.
- Local vector index
- Folder Q&A
- Source-grounded answers