github repository

jundot/omlx

LLM inference server with continuous batching & SSD caching for Apple Silicon — managed from the macOS menu bar

Repository facts collected

View on GitHub
Current stars
23,702
Stars in latest 7-day window
183
Stars in latest 30-day window
851

Recent repository activity

jundot/omlx added 183 stars from 2026-11-12 to 2026-11-18 (UTC).

The latest 7-day window recorded 4 fewer star additions compared with 2026-11-05 to 2026-11-11 (UTC). Star additions measure attention, not software quality or adoption.

Weekly rank: #92 in BeWisp’s tracked GitHub cohort on 2026-11-18 (UTC).

Latest recorded push: 2026-11-18 (UTC).

Latest recorded release: v0.8.0rc1, published 2026-11-12 (UTC).

Star history

jundot/omlx added 851 stars from 2026-10-20 to 2026-11-18 (UTC).

Source: GitHub star history. Latest collection: .

Stars added per day
Daily stars added851 stars were added from 2026-10-20 to 2026-11-18. Use the date slider below to inspect recorded days. Gaps represent unrecorded dates.023462026-10-202026-11-18
2026-11-18: 5 stars
851 stars added from 2026-10-20 to 2026-11-18 (UTC), across 30 recorded days. Source: GitHub star history.

Periods end on the latest loaded date. Missing dates remain gaps. Use the slider or arrow keys to inspect a day.

Rank history

Daily, weekly and monthly positions in BeWisp’s tracked GitHub cohort.

2026-10-20 to 2026-11-18 (UTC). daily: #81; weekly: #92; monthly: #100 on 2026-11-18.

Activity rank history#1#1292026-10-202026-11-18

Achievements

Best positions reached in the preserved activity record.

dailyDaily top 10

Reached #2 on 2026-03-09

weeklyWeekly top 10

Reached #6 on 2026-03-12

monthlyBest Monthly rank

Reached #15 on 2026-04-07

Repository activity

Development signals collected separately from star activity.

Latest push2026-11-18Less than 24 hours ago
Commits0Latest GitHub week

Repository facts

Language
Python
Licence
Apache-2.0
Forks
2,146
Created
2026-02-13

Owner

jundot · user.

Explore related repositories

These tracked repositories share topics or a primary language. Shared metadata does not establish that projects are interchangeable.

  • youssofal/MTPLX

    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.

  • AlexsJones/llmfit

    Hundreds of models & providers. One command to find what runs on your hardware.

  • makecindy/cindy

    Consider it done. The open-source AI agent that works out of the box · 想到,就能做到。开源、开箱即用的 AI Agent。