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

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

san-digital/tokspur

Private chat and code on your Mac. Run a 177B model on a 128 GB M5 Max: local Qwen3.8 Flash-Next inference with a 65,536-token default or optional 131,072-token context, Tokspur's own Metal engine with native MTP or DFlash2 drafting, and an OpenAI-compatible API. Apache 2.0.

#LLM inference
Visit GitHub
C++
25
2
1 contributors
Apache License 2.0
website
FeaturedAdvertise to 180K+ monthly visitors
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

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

OfinTech Desk

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

Momentum

How fast san-digital/tokspur 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 9 – Nov 19, 2026

Stars +13 in 11 days

0510
10

Forks +2 in 11 days

01
1

Merged PRs 8 in 11 days

0123
3

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

Not in the Trendshift top 25 in this period

Nov 9Nov 11Nov 13Nov 15Nov 17Nov 19
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
Mon, Nov 9, 2026+0+13
Tue, Nov 10, 2026+1+10
Wed, Nov 11, 2026+0+00
Thu, Nov 12, 2026+0+01
Fri, Nov 13, 2026+1+00
Sat, Nov 14, 2026+10+00
Sun, Nov 15, 2026+0+03
Mon, Nov 16, 2026+0+01
Tue, Nov 17, 2026+1+00
Wed, Nov 18, 2026+0+00
Thu, Nov 19, 2026+0+00
Total+13+28
  • 1#1 on the list
  • 7Rank that day
  • Not trending

Social mentions

Recent discussions about this repository across the web
  1. Nov 161 post
    • 0.3.2 is out 🚀🚀🚀

      Read full on X, posted by @lee_crossley

      @lee_crossley · x.com

  2. Nov 121 post
    • How does 169.7 tok/s (159.5 comp request) on an M5 with Qwen3.8 Flash-Next sound? There's more to come, much more.

      Read full on X, posted by @lee_crossley

      @lee_crossley · x.com

  3. Nov 101 post
    • Show HN: Tokspur a 3x faster open source inference engine for Macs

      Read full on Hacker News

      Hacker News

You might also like

Repositories close to san-digital/tokspur
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

Bifrost

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

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

youssofal/MTPLX

Python

The fastest way to run Qwen 3.8 Flash Next, Qwen 3.8 27B and Ternary Bonsai 2 27B on a Mac: 125 tok/s in OpenCode on an M5 Max, and a 27B model on 16 GB Macs. Native MTP speculative decoding on Apple Silicon, exact at any temperature. OpenAI and Anthropic compatible local server.

2.7k231

1picassoai/coachwhip

Metal

The 80B Qwen3-Coder-Next on a 16 GB Mac, about 13 tok/s, fully offline. A mixture-of-experts inference engine for Apple silicon.

694

walter-grace/mac-code

Python

mac code — Claude Code, but it runs on your Mac for free. 35B AI agent at 30 tok/s via Apple Silicon flash-paging. $0/month.

1k117

Neywa-Labs/nativ

Swift

Nativ is an open-source local AI app for Mac. It runs open AI models on Apple Silicon, and nothing leaves your Mac.

1.6k123

paperniuk/ds4

C

Fork of antirez/ds4 for Apple Silicon, tuned mostly for M1/M2: Qwen3.8-Flash-Next with 262K context on 64 GB and up, 35 tok/s on an M1 Max, MTP and vision, one-line install.

403

tuff-app/TUFF

Swift

The local AI app built for the Mac. Run LLMs like Qwen, Gemma and GPT-OSS on Apple Silicon, including models far bigger than your Mac's memory, by streaming MoE experts from the SSD.

778

arinltte/ari

Swift

Quiet AI on Your Mac.

261

signerlabs/Klee

Swift

A native macOS AI chat app powered by MLX. 100% local inference on Apple Silicon, no cloud required. Built with ShipSwift.

1.8k160

magicnight/Mac-MLX

Swift

macMLX brings local LLM inference to Apple Silicon with a first-class native macOS experience. No cloud, no telemetry, no Electron — just your Mac running models at full speed.

866