20B—A1B TERNARY REASONING MODEL
Intelligence,
grown locally.
Maple-Preview runs entirely on your GPU. Your prompts stay on your device, while a 2-bit official checkpoint delivers fast, private reasoning.
403 MB of KV cache — 5.71 GB of GPU memory in total.
- 20B
- PARAMETERS
- 1B
- ACTIVE / TOKEN
- 2-bit
- OFFICIAL WEIGHTS
Made with Opus 5 and GPT 5.6 sol
CULTIVATING YOUR LOCAL MODEL
0%
REQUESTING WEBGPU
0.00 / 5.31 GB
The tree grows as Maple's weights move directly to your GPU.
MAPLE · LOCAL SESSION
What are we thinking about?
READY · WEBGPU
Maple is ready. Everything you write stays in this browser.