Qwen 3
4B8B14B30B32B235B
- Minimum hardware
- Basic tier
- Backend
- Ollama, LM Studio, or llama.cpp
Apache 2.0
Official pageSupported AI models
InnerZero runs open-source language models directly on your PC via Ollama, LM Studio, or your own llama.cpp server. The main families are Qwen 3, Gemma 3, and gpt-oss, covering everything from a 1B voice model on a basic laptop to a 235B reasoning model on a datacenter-class workstation. Local AI is free, no subscription, no account required.
Cloud support is optional. If you want frontier-quality models for hard tasks, subscribe to InnerZero's managed cloud plans, or bring your own API keys for any of seven providers with zero markup. Keys stay encrypted on your machine.
Local models
Installed automatically based on your hardware tier. These run entirely on your machine, offline if you want.
Gemma 3
1B4B12B
- Minimum hardware
- Entry tier
- Backend
- Ollama, LM Studio, or llama.cpp
Gemma Terms of Use
Official pagegpt-oss
120B
- Minimum hardware
- Pro tier
- Backend
- Ollama, LM Studio, or llama.cpp
Apache 2.0
Official pageHow we choose supported models
Supported local families run reliably on consumer hardware, ship under permissive licences, are actively maintained by their upstream teams, and work cleanly through Ollama, LM Studio, or llama.cpp without custom glue. We prefer families with a range of sizes so the same recipe scales from a budget laptop up to a frontier workstation. Models that satisfy those constraints land in the default hardware tiers and get tested as new versions ship.
Cloud models
This section is optional, and it is the bring-your-own-key catalogue: add your own provider API key and your prompts go directly to that provider, at the provider's own prices with no markup. Managed cloud plans are separate: they run on InnerZero's own cloud service with monthly credits and per-tier routing rather than a per-model choice. See pricing for the plans.
DeepSeek
OpenAI
GPT-5.6 Sol
gpt-5.6-solBYOPricing
GPT-5.6 Terra
gpt-5.6-terraBYOPricing
GPT-5.6 Luna
gpt-5.6-lunaBYOPricing
GPT-5.5
gpt-5.5BYOPricing
GPT-5.5 Pro
gpt-5.5-proBYOPricing
GPT-5.4
gpt-5.4BYOPricing
GPT-5.4 Mini
gpt-5.4-miniBYOPricing
GPT-5.4 Nano
gpt-5.4-nanoBYOPricing
GPT-4.1
gpt-4.1BYOPricing
GPT-4.1 Mini
gpt-4.1-miniBYOPricing
GPT-4.1 Nano
gpt-4.1-nanoBYOPricing
GPT-4o
gpt-4oBYOPricing
o3
o3BYOPricing
o4 Mini
o4-miniBYOPricing
GPT-5.3 Codex
gpt-5.3-codexBYOPricing
GPT-5.3 Chat
gpt-5.3-chatBYOPricing
Anthropic
Qwen
Model support last reviewed 16 August 2026. Pricing is set by each provider and changes over time; follow the pricing links above for current rates. Local models are free to download and run.