Seismograph

What’s gaining stars on GitHub right now

antirez/ds4

Language modelsC
Open on GitHub My finds →
More actions
Open on Seismograph

DeepSeek 4 Flash and PRO local inference engine for Metal, CUDA and ROCm

Save to My finds to follow releases and star growth. Saved in this browser.

About the project

DwarfStar (ds4) is a native C inference engine for running a few specific large LLMs (DeepSeek V4 Flash/PRO, GLM 5.x, Qwen3.8 Flash Next) on Metal, CUDA and ROCm. Targets consumer hardware like MacBooks, DGX Spark and Strix Halo, with SSD streaming and multi-GPU support.

Useful for
  • Run DeepSeek V4 Flash locally on a 96+ GB MacBook via Metal
  • Set up a multi-user LLM server on several L40S cards via CUDA
  • Build a two-Mac RDMA cluster with tensor parallelism for 4-bit models

README summarized by DeepSeek V4.1 Flash. Details may be inaccurate.

5.1 Breakout Magnitude out of 10 — how fast interest is growing, not a quality score.

Star growth looks organic. Data as of October 4, 2026, 13:15 UTC.

The star-growth assessment does not verify whether the project is safe to run.

Stars per day

0200400July 7, 2026October 4, 2026

Bars show daily stars; the line is a moving average of the available history. Short histories do not yet establish a reliable usual pace. Red marks spike days.

Why it’s trending

  • 74 stars so far today, about 149 expected by the end of the day. The usual pace is 31 per day, so that's 4.9× as much.
  • Over the last two days the pace is 6.5× that of the previous week and a half.
  • The spike has held for 3 days in a row — not a one-off blip.
  • GitHub Trending today: #15, +211 stars.
  • About 23 forks a day — people are taking the code.

Explore related projects

  1. 0xShug0/audio.cpp

    A native C++ inference engine for audio models built on ggml: TTS, speech recognition, VAD, voice cloning, music generation. Runs without Python on CPU, CUDA, ROCm, Vulkan and Metal.

    Similar descriptions and use cases
  2. MiaAI-Lab/Qwen3.8-Flash-Next-Single-DGX-Spark-TensorFold

    Scripts to serve Qwen3.8 Flash Next on a single NVIDIA DGX Spark via an OpenAI-compatible API, with image and video input and a 262,144-token context.

    Similar descriptions and use cases
  3. JustVugg/colibri

    A pure-C, zero-dependency inference engine for running large MoE models (744B–2.8T parameters) on consumer hardware by treating VRAM, RAM, and storage as a single multitier hierarchy and streaming experts from disk.

    Similar descriptions and use cases

Three GitHub discoveries in each edition

What they do, why they are gaining interest, and what to check before using them.

Editions at 10:00, 16:00, 22:00 MSK.

Read daily discoveries in English Project updates · English RSS Telegram · in Russian
Share on X Telegram

Numbers

Total stars
23,286
Today
74 · ≈ 149 by evening
Forks
2,239
Issues and pull requests
1,173
Watchers
176
Language
C
License
MIT
Created
May 6, 2026
Last push
September 20, 2026

Star trust

Growth looks organic: forks and discussion are in line with active projects, and stars arrive unevenly, the way people give them.

These are heuristics, not a verdict: we judge by the repository’s behavior, not by a list of stargazers.

Spotted in
README badge

Paste it into your README — the badge shows the current magnitude and links to this page.

Seismograph: 5.1 
[![Seismograph](https://gitnova.dev/badge/antirez/ds4.svg?lang=en)](https://gitnova.dev/en/r/antirez/ds4)