# Deepgrove's Maple Preview bets on ternary-weight MoE

> A permissively licensed reasoning model that pairs a mixture-of-experts design with ternary weights, aiming for efficiency.

Published by The Open Weights on Aug 4, 2026. Canonical: https://theopenweights.com/news/maple-5v71

## Key facts

- Company: Deepgrove
- Model: Maple Preview
- Version: Preview
- Category: Reasoning
- Modalities: Text / LLM, Reasoning
- License: MIT (Open weights, commercial use allowed)
- Context window: 131K tokens
- Architecture: MapleForCausalLM
- Precision: BF16
- Weights size: 40.4 GB
- Significance: minor
- Published: 2026-08-04
- Last verified: 2026-08-16
- Hugging Face: https://huggingface.co/deepgrove/maple-preview
- Canonical URL: https://theopenweights.com/news/maple-5v71

Deepgrove has published **Maple Preview**, an early look at a reasoning-focused language model that combines two efficiency-minded ideas: a mixture-of-experts (MoE) architecture and ternary weights. The model is available now on [Hugging Face](https://huggingface.co/deepgrove/maple-preview) under a permissive MIT license.

The design choices are the headline here. MoE models route each token through a subset of specialized "expert" networks rather than activating the full parameter count, which can lower the compute cost of inference. Ternary weights push in a similar direction by constraining values to three states, a quantization approach that can shrink memory footprint substantially compared with standard floating-point weights.

## Why it matters

Pairing ternary weights with an MoE layout is an aggressive efficiency play, and reasoning models are a demanding place to try it — they typically lean on longer generations and more compute per query. If the approach holds up, it points toward capable reasoning on tighter hardware budgets.

A few caveats come with the "preview" label:

- Parameter count and context length are not specified in the release record.
- No benchmark results accompany this listing, so quality claims remain to be validated.
- The MIT license keeps the door open for both research and commercial experimentation.

For now, Maple Preview is best read as a signal of direction from Deepgrove rather than a finished product. Teams interested in low-footprint reasoning models will want to test it directly against their own workloads before drawing conclusions.

## Get the model

- [Hugging Face](https://huggingface.co/deepgrove/maple-preview)

## Sources

- [deepgrove/maple-preview](https://huggingface.co/deepgrove/maple-preview) — Hugging Face, Aug 4, 2026

---
Source: The Open Weights (https://theopenweights.com/). Aggregated and written by Claude, curated by humans. Cite as: "Deepgrove's Maple Preview bets on ternary-weight MoE", The Open Weights, Aug 4, 2026, https://theopenweights.com/news/maple-5v71