Loading…
Your privacy choices
Necessary storage keeps the site working. Analytics and advertising stay off unless you allow them. Cookie notice
Thox-ai
At THOX.ai, we build local-first, privacy-first AI around the people using it. Our focus is making capable AI practical across edge devices, workstations, portable hardware, and embedded systems—without making cloud dependence the default or compromising user control.
We research how models, runtimes, devices, and agents can work together to deliver useful, reliable intelligence closer to the data.
Areas of interest
- Edge AI and efficient models: Small and specialized language models, custom architectures, instruction tuning, quantization, distillation, and hardware-aware inference optimization.
- Portable and privately connected AI: Offline-ready runtimes, model portability, and permissioned networks that connect authorized devices and compute resources.
- Intelligent routing and agentic systems: Task-aware model selection, multi-agent coordination, and Digital Employees operating with scoped permissions, reviewable actions, and human oversight.
- Multimodal and human-centered experiences: Language, speech, vision, and digital-human interfaces that make advanced AI more accessible and useful in everyday work.
Across ThoxOS™, MeshStack™, and the upcoming ThoxWork™, our goal is to turn these capabilities into a coherent experience—not a collection of disconnected tools.
We value reproducible evaluations, transparent model provenance, honest hardware compatibility claims, and explicit user choice about where data is processed.
Your AI. Your Data. Your Rules.™
- Develops
- 10 model versions
Model families and versions
Every model version this company develops, newest first; each links to its own model card.
1–10 of 10
| Model | Released | Context window | Weights | Licence |
|---|---|---|---|---|
| ThoxOS-Kernel-27B | 262,144 tokens Per Hugging Face; not confirmed by the developer | |||
| ThoxOS-Kernel-4B | 262,144 tokens Per Hugging Face; not confirmed by the developer | |||
| ThoxOS-Kernel-0.8B | 262,144 tokens Per Hugging Face; not confirmed by the developer | |||
| ThoxAir-0.5B | 32,768 tokens Per Hugging Face; not confirmed by the developer | |||
| ThoxMini-Phi4Mini | 131,072 tokens Per Hugging Face; not confirmed by the developer | |||
| ThoxEdge-RustCoder-0.5B | 32,768 tokens Per Hugging Face; not confirmed by the developer | |||
| ThoxUSB-Edge | 262,144 tokens Per Hugging Face; not confirmed by the developer | |||
| ThoxEdge-0.5B | 32,768 tokens Per Hugging Face; not confirmed by the developer | Open weights Per Hugging Face; not confirmed by the developer | ||
| ThoxMini-125M-role | 1,024 tokens Per Hugging Face; not confirmed by the developer | |||
| ThoxLLM-327M-v2 | 2,048 tokens Per Hugging Face; not confirmed by the developer |
Pricing
Offers this company serves as a provider, whoever developed the model. Each price uses the currency and billing unit shown with it.
Thox-ai serves no priced offer itself.