NotesXML ships with 10 AI models you can download and run entirely on your device. No API keys, no subscriptions, no data leaving your machine. Here's how they compare to the cloud giants.
Every model listed below runs inside NotesXML via llama.cpp — the same inference engine used by researchers worldwide. Cloud models are shown for reference only.
| Model | Parameters | RAM (peak) | Context | Vision | Tier | Educational Equivalent |
|---|---|---|---|---|---|---|
| GPT-5.4 Pro Cloud | Proprietary | API | 1M+ | Yes | Cloud | PhD / Researcher |
| Claude Opus 4.6 Cloud | Proprietary | API | 1M | Yes | Cloud | PhD / Researcher |
| Llama 3.2 1B Instruct Local Free Tier | 1.2B | 1.3 GB | 128K | — | Ultra-Light | Basic / Elementary |
| Ministral 3 3B Local Free Tier Electron Default | 3B | 3.0 GB | 256K | Yes | Lightweight | High School |
| Llama 3.2 3B Instruct Local | 3.2B | 3.2 GB | 128K | — | Lightweight | High School |
| Phi-4 Mini 3.8B Local | 3.8B | 3.9 GB | 128K | — | Lightweight | High School |
| Gemma 4 E2B Local | 2.3B effective | 4.5 GB | 128K | Yes | Standard | High School |
| Gemma 4 E4B Local | 4.5B effective | 6.4 GB | 128K | Yes | Enhanced | Undergraduate |
| Ministral 3 8B Local | 8B | 7.0 GB | 256K | Yes | Enhanced | Undergraduate |
| Ministral 3 14B Desktop only Intel GPU pick | 14B | 11.0 GB | 256K | Yes | Advanced | Undergraduate |
| Gemma 4 12B Local | 12B | 10.0 GB | 256K | Yes | Enhanced | Undergraduate |
| Gemma 4 26B-A4B (MoE) Desktop only | 26B (4B active, MoE) | 22.0 GB | 256K | Yes | Desktop Pro | Post-Graduate |
RAM (peak) = peak memory used by the model during inference (per NX-AI-MODEL-015 RAM safety floor). This is the model’s own memory consumption, not the total device RAM required — your operating system, background apps, and the NotesXML application itself also consume RAM. As a guideline, add 4–6 GB to the peak RAM figure for Android devices or 5–8 GB for desktops to estimate the total device RAM needed. Context = native context window. MoE = Mixture of Experts (active parameters per token shown in parentheses). Vision-capable models accept images, PDFs, and screenshots as input. Free Tier models are available without a Professional license. Catalog source: notesxml-model-catalog.json v2026.07.08.03.
AI models run entirely on your device and produce results based on statistical patterns. Output quality varies by model and task. Always review AI-generated content before relying on it.
Specialty family catalogs are available for Gemma, Llama, Mistral, Phi, Granite, and GPT-OSS — 54 additional models across 6 families.
The catalog is organized into six tiers based on RAM requirements and capability. Pick the tier that matches your hardware.
1 model · ~1.3 GB model runtime RAM · 6–8 GB total device RAM · Free Tier (Llama 3.2 1B)
Llama 3.2 1B Instruct (Android Free-tier default). The fastest model in the catalog and the Android Free-tier default — ideal for auto-titling notes, simple text cleanup, and basic transcription polish. Fits comfortably on phones and low-memory devices, with a 128K-token context window.
3 models · 3.0–3.9 GB model runtime RAM · 8–14 GB total device RAM recommended
Ministral 3 3B (Free Tier, vision, Electron default), Llama 3.2 3B, and Phi-4 Mini 3.8B. Ideal for quick tasks: formatting, basic summarization, general conversation. Ministral 3 3B brings image analysis into the Free tier and is the Electron default, with a 256K context. Phi-4 Mini offers strong instruction-following, an MIT license, and a 128K context.
1 model · ~4.5 GB model runtime RAM · 8–14 GB total device RAM recommended
Gemma 4 E2B (vision). A compact, fast, vision-capable model (~2.3B effective parameters) that sits between the Lightweight trio and the Enhanced tier. Strong knowledge scores for its size, with image analysis at a modest footprint. Cross-platform, 128K context, Apache 2.0.
3 models · 6.4–10.0 GB model runtime RAM · 16 GB total system RAM recommended · Professional
Gemma 4 E4B (vision, tool calling), Ministral 3 8B (vision), and Gemma 4 12B (vision). Gemma 4 E4B delivers expert-level tool calling and image analysis. Ministral 3 8B is the catalog’s speed/quality leader for AI Chat and structured actions. Gemma 4 12B is the highest-quality model that still runs cross-platform, second only to the desktop-only 26B MoE. All three require Professional tier.
1 model · ~11 GB model runtime RAM · 24 GB total system RAM recommended · Desktop & Professional
Ministral 3 14B (vision, Intel GPU pick). The large-model choice for Intel iGPU/GPU systems — it runs on the Intel GPU, where the Gemma 4 models fall back to CPU-only. 14B dense, vision-capable, 256K-token context, Apache 2.0. Desktop only (Windows and Linux); does not appear in the Android model picker.
1 model · ~22 GB model runtime RAM · 32 GB total system RAM or 16+ GB VRAM · Desktop & Professional
Gemma 4 26B-A4B (MoE) — 26B total parameters with 4B active per token via Mixture-of-Experts, vision-capable, 256K-token native context. The highest-quality model in the catalog: top scores on HEE, PLE, and PhD Philosophy, plus the strongest SDB-100 deductive-reasoning result. Best with a discrete GPU with 16+ GB VRAM (e.g., RTX 4080, RTX 5070 Ti, or higher); CPU-only inference is possible but significantly slower. Apache 2.0.
Cloud AI means sending your notes, documents, and ideas to someone else's server. With NotesXML, the AI runs on your device. Your data never leaves your machine — not even for processing.
Cloud AI services typically charge ongoing subscription fees — sometimes hundreds of dollars per month for top-tier models, plus per-token fees for usage. NotesXML Professional is $39.99 lifetime — and includes access to all 10 models with no per-token charges, ever.
No internet? No problem. Once you've downloaded a model, it works everywhere — airplanes, rural areas, secure facilities. Cloud models require a constant internet connection.