Documentation
From first launch
to full control.
Clear guidance for running local models on Intel Macs with AMD GPUs. Start with installation, then tune performance, connect clients and understand every benchmark you share.
Guides
Find the answer
without digging.
Each guide is focused, linkable and written around the decisions you make inside ToshLLM.
Getting started
Install ToshLLM, choose the correct build, pass the first-launch security check and start a local model.
Read guide →02Choose what fitsModels and performance
Understand VRAM estimates, quantization, dense and MoE models, context size and multi-GPU configurations.
Read guide →03Connect local clientsLocal API
Use ToshLLM as an OpenAI-compatible server for editors, agents and other applications on your network.
Read guide →04Measure consistentlyBenchmark guide
Read prompt and generation measurements, compare configurations and share signed results from the app.
Read guide →05Know what leaves the MacPrivacy and security
Learn what remains local, what benchmark sharing sends and how ToshLLM protects submission identity.
Read guide →06Resolve common issuesTroubleshooting
Fix first launch, CPU compatibility, memory pressure, model loading and local server connection problems.
Read guide →