Slotstream Studio
Plan 125B MoE LLM streaming on your Mac
Slotstream Studio — free Swift engine planner streaming 125B MoE LLMs from SSD via Ollama plus OpenAI APIs, open-source.
How to use Slotstream Studio
- Enter your Mac RAM size to get a Slotstream memory plan for 125B MoE inference
- Pick a model size and context length to estimate tokens per second
- Generate the slotstream serve config with your chosen settings
- Test the OpenAI compatible API endpoint with the built-in playground
- Copy the install command to set up Slotstream on your Mac
Features
- Memory planner mirroring slotstream doctor for Apple Silicon Macs
- Speed and context estimates for 125B Qwen MoE streamed from SSD
- Serve config builder for Ollama and OpenAI compatible endpoints
- API playground with curl snippets and localhost probe
- One click install commands for macOS
- SSD streaming explained with VRAM and RAM trade offs
Frequently asked questions
Is it free?
Yes, unlimited.
Login to use this free online tool. Create a free account to get started.
