Lumeo · A family of language models

One model,
every side of the light.

Lumeo runs a single open model that fits a 16 GB card — with three personas: Solis to talk, Prism to code, Beacon to research. It reasons out loud, and you can watch it think.

100,000 tokens free every week · no credit card

The personas

Three personas, one model.

The same weights under a different system prompt — each set up for a different job, and named for the way light behaves. Switch anytime; there’s nothing new to load.

Available

Solis

Conversation

Warm, direct, and quick — for questions, writing, and thinking out loud. Sees images, takes voice, searches the web, and calls your tools.

Available

Prism

Code

The same model tuned to write, refactor, and review code — complete, runnable answers that match your style, with tools and the web on hand.

Available

Beacon

Retrieval

The same model set to look things up — it reaches for web search, page fetch, and your MCP tools, and cites what it used.

A closer look at Solis 1.9 — available now
20B
MoE, 3.6B active
4-bit
MXFP4 serving
Reasoning
low · medium · high
Vision
image understanding
Voice
audio input
MCP
tools + web search
DetailValue
ModelGPT-OSS-20B (open weights)
Parameters20B total · 3.6B active per token (MoE)
Serving precision4-bit MXFP4
VRAM to serve~14 GB — fits a 16 GB card
ReasoningNative — low, medium, high (streamable)
VisionImages routed to a vision model
VoiceWhisper for audio input
ToolsMCP tool calling + web search
APIOpenAI-compatible /v1/chat/completions

Quantized to 4-bit so the whole model serves comfortably on a single 16 GB card.

How we build

One model,
many senses.

Lumeo runs GPT-OSS-20B — a 20B mixture-of-experts with only 3.6B active per token, served in 4-bit inside about 14 GB of VRAM. It fits a single 16 GB card and decodes like a much smaller model, and it reasons natively — so you can stream its thinking and hide it when you don't need it.

Around that core, requests route by what you send: images go to a vision model, audio through Whisper, and anything needing the outside world reaches for web search or a tool you've connected over MCP.

your request
Solis 1.9
Text
GPT-OSS-20B
Images
vision model
Audio
Whisper
Tools
MCP · search

Requests route by modality — 4-bit, ~14 GB to serve

Honesty first

Built in the open, still improving.

Lumeo is built on open weights (GPT-OSS) and still improving. It can be wrong, and it will sometimes make things up — please don't rely on it for anything important without checking. Your chats are tied to your account and used only to run the service — see our Privacy Policy and Terms of Service.

Say hello to Solis.

Create a free account and start a conversation in seconds.