Footer

Your go-to destination for discovering trending open-source projects and uncovering the insights that matter

Legal

  • Terms and conditions
  • Privacy policy

More

  • Pricing
  • Advertise
  • onedump
  • gosnakego
  • Contact us

Social

  • X (Twitter)
  • GitHub
Trendshift owl
What they build speaks louder than words
© 2026 Trendshift, created by Julian Li with ❤️
SignalAdvertise
Trendshift
SignalAdvertise
Sign in
Trendshift owl

Discover trends that matter

SignalAdvertise
DailyWeeklyMonthlyYearly
Live mentionsTopics
RepositoriesDevelopers
InsightsStats

OfinTech Desk
OfinTech Desk
Omnigraph
Omnigraph
Busbar
Busbar
It's a plan
It's a plan
Bifrost
Bifrost
Trina AX
Trina AX

AmSach/maple

MAPLE: Manifold-Activated Pruning of Latent Experts for Sub-2-BPW MoE LLMs

#Language model
Visit GitHub
Python
65
5
1 contributors
Custom license
FeaturedAdvertise to 180K+ monthly visitors
OfinTech Desk

An open-source AI workspace for finance and accounting teams, in which every figure is traced to its source

Omnigraph

Versioned graph database on object storage. Git-style workflows and multimodal retrieval

Busbar

Control what AI can do before it acts

It's a plan

Open-source Linear alternative

An issue tracker where AI agents take the work you assign them

Bifrost

Fastest Enterprise AI Gateway for Routing, Governing, and Securing all your AI Traffic

Trina AX

A self-hosted team AI workspace for company files, with per-person folder permissions

Momentum

How fast AmSach/maple is gaining stars, and where it lands on Trendshift and GitHub Trending

Activity and trending

Stars, forks and merged pull requests each day or month, lined up with the repository's rank on Trendshift Trending

Nov 7 – Nov 22, 2026

Stars +65 in 16 days

02040
31

Forks +5 in 16 days

01
1

Merged PRs 0 in 16 days

01

Trendshift Trendingwhere the repository ranked each day it made the top 25

Not in the Trendshift top 25 in this period

Nov 7Nov 9Nov 11Nov 13Nov 15Nov 17Nov 19Nov 21
The left and right arrow keys step from day to day; Home and End go to the first and the last

Stars, forks, merged pull requests and Trendshift Trending rank, by day
DayStars gainedForks gainedMerged PRs
Sat, Nov 7, 2026+0+00
Sun, Nov 8, 2026+31+10
Mon, Nov 9, 2026+12+10
Tue, Nov 10, 2026+3+10
Wed, Nov 11, 2026+1+00
Thu, Nov 12, 2026+3+00
Fri, Nov 13, 2026+1+00
Sat, Nov 14, 2026+0+00
Sun, Nov 15, 2026+1+00
Mon, Nov 16, 2026+8+10
Tue, Nov 17, 2026+2+00
Wed, Nov 18, 2026+1+10
Thu, Nov 19, 2026+0+00
Fri, Nov 20, 2026+2+00
Sat, Nov 21, 2026+0+00
Sun, Nov 22, 2026+0+00
Total+65+50
  • 1#1 on the list
  • 7Rank that day
  • Not trending

Social mentions

Recent discussions about this repository across the web
  1. Nov 82 posts
    • JUST IN: Maple's creator says a pruned Gemma 4 26B runs at 45.4 tokens per second on a 6GB laptop GPU, versus 6.9 for the larger model. The project checks keyword matches across four tasks.

      Read full on X, posted by @namefi_io

      @namefi_io · x.com

    • Show HN: Maple – Sub-2-BPW Moe Pruning to Run Gemma 4 26B at 45 TPS on a 6GB GPU

      Read full on Hacker News

      Hacker News

You might also like

Repositories close to AmSach/maple
FeaturedAdvertise to 180K+ monthly visitors
Trina AX

A self-hosted team AI workspace for company files, with per-person folder permissions

It's a plan

Open-source Linear alternative

An issue tracker where AI agents take the work you assign them

Busbar

Control what AI can do before it acts

Omnigraph

Versioned graph database on object storage. Git-style workflows and multimodal retrieval

Bifrost

Fastest Enterprise AI Gateway for Routing, Governing, and Securing all your AI Traffic

OfinTech Desk

An open-source AI workspace for finance and accounting teams, in which every figure is traced to its source

krafton-ai/moe-to-dense

Python

Pruning and Distilling Mixture-of-Experts into Dense Language Models

263

AbdelrhmanEbied/Tiny-MoE

Python

Tiny-MoE is a lightweight Mixture-of-Experts language model built entirely from scratch in native PyTorch and trained end-to-end on Kaggle using free 2× NVIDIA T4 GPUs. The project implements modern LLM techniques—including MLA, RoPE, YaRN, streaming pre-training, and efficient inference—without relying on existing model implementations.

233

FujitsuResearch/OneCompression

Python

Python package for LLM compression

44623

miltos22/llama-wackMall

C++

Caching experts made model agnostic for llama. Drastically speeds up generation speed on MoE models that fully fit in the RAM but partially in Vram. WIP: Same speedup but for models that don't fit in the ram either.

3110

OpenBMB/MiniCPM

Jupyter Notebook

MiniCPM5: SOTA on-device LLMs, small yet powerful.

11.9k862

yalun753/moe-l2

Cuda

MoE expert offload for low-VRAM GPUs — run 100B+ MoE models (DeepSeek, Qwen, Mixtral) on 8 GB cards. Expert cache with LRU hot experts, OpenAI-compatible proxy, GGUF multi-shard.

1476

CASE-Lab-UMD/Unified-MoE-Compression

Python

The official implementation of the paper "Towards Efficient Mixture of Experts: A Holistic Study of Compression Techniques (TMLR)".

937

General-Instinct/InstinctRazor

Python

An Efficient Compression Framework for LLM

708

Vahe1994/AQLM

Python

Official Pytorch repository for Extreme Compression of Large Language Models via Additive Quantization https://arxiv.org/pdf/2401.06118.pdf and PV-Tuning: Beyond Straight-Through Estimation for Extreme LLM Compression https://arxiv.org/abs/2405.14852

1.3k198