Skip to content

Beta: real launches, updated every morning. Rankings may change while we tune them.

Maple

Sub-2-BPW Moe Pruning to Run Gemma 4 26B at 45 TPS on a 6GB GPU

Maple launched on 8 November 2026. It ranked #24 on Daily Launch on 9 November 2026 with a Launch Score of 61, from 20 points on Show HN. It was new in the ranking that day.

Visit siteTop on Show HN the day before · 20 points
Share

What is Maple?

The MAPLE mathematical formulation operates on the fundamental routing mechanism shared by all Sparse Mixture-of-Experts (SMoE) transformers. It is architecturally portable to any MoE model family, including: - Liquid AI LFM-2 MoE / LFM 24B (fine-grained hybrid conv/attention MoE) - Mistral / Mixtral 8x7B & 8x22B (standard top-2 routed MoE) - DeepSeek-V2 / DeepSeek-V3 / DeepSeek MoE (fine-grained routed experts with shared expert isolation) - Qwen 2.5 MoE (e.g.

From its README on GitHub

Maple is a launch on Show HN. It is written in Python.

Daily Launch card for Maple

Launch timeline

  1. Show HNPosted on Show HN

  2. Show HN20 points, ranked #24 on Daily Launch

Launch Score, last 7 days

Ranked on one day so far: 61 of 100 on 9 November.

#58 of 228 in the roundup for the week of 9-15 November 2026.