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

DailyWeeklyMonthlyYearly
Live mentionsTopics
RepositoriesDevelopers
InsightsStats
Bifrost
Bifrost

gianlucamazza/xllama

Local LLM inference on Xbox Series S|X in Dev Mode: llama.cpp (GGUF) + ONNX Runtime GenAI, opt-in OpenAI-compatible LAN endpoint, diffusion and on-device training. Measured models are listed in a Hugging Face collection. Independent research project, not affiliated with Microsoft.

#LLM inference
Visit GitHub
C++
73
11
2 contributors
MIT License
website
FeaturedAdvertise to 180K+ monthly visitors
Bifrost

Enterprise AI Gateway Built For Scale: Route, Govern, and Secure All Your AI Traffic

Momentum

How fast gianlucamazza/xllama 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

Aug 27 – Oct 26, 2026

Stars +45 in 61 days

024
4

Forks +10 in 61 days

012
2

Merged PRs 84 in 61 days

051015
14

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

Not in the Trendshift top 25 in this period

Aug 27Sep 4Sep 12Sep 20Sep 28Oct 6Oct 14Oct 22
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
Thu, Aug 27, 2026+0+00
Fri, Aug 28, 2026+0+00
Sat, Aug 29, 2026+2+00
Sun, Aug 30, 2026+0+00
Mon, Aug 31, 2026+0+00
Tue, Sep 1, 2026+0+00
Wed, Sep 2, 2026+0+00
Thu, Sep 3, 2026+0+00
Fri, Sep 4, 2026+0+00
Sat, Sep 5, 2026+1+00
Sun, Sep 6, 2026+0+00
Mon, Sep 7, 2026+0+00
Tue, Sep 8, 2026+0+00
Wed, Sep 9, 2026+1+00
Thu, Sep 10, 2026+1+00
Fri, Sep 11, 2026+1+00
Sat, Sep 12, 2026+0+00
Sun, Sep 13, 2026+0+02
Mon, Sep 14, 2026+0+00
Tue, Sep 15, 2026+1+00
Wed, Sep 16, 2026+0+00
Thu, Sep 17, 2026+0+00
Fri, Sep 18, 2026+0+00
Sat, Sep 19, 2026+1+00
Sun, Sep 20, 2026+0+20
Mon, Sep 21, 2026+0+00
Tue, Sep 22, 2026+1+00
Wed, Sep 23, 2026+0+10
Thu, Sep 24, 2026+1+00
Fri, Sep 25, 2026+2+00
Sat, Sep 26, 2026+0+00
Sun, Sep 27, 2026+1+00
Mon, Sep 28, 2026+0+04
Tue, Sep 29, 2026+0+114
Wed, Sep 30, 2026+0+010
Thu, Oct 1, 2026+0+05
Fri, Oct 2, 2026+2+19
Sat, Oct 3, 2026+0+00
Sun, Oct 4, 2026+0+10
Mon, Oct 5, 2026+0+00
Tue, Oct 6, 2026+1+00
Wed, Oct 7, 2026+0+00
Thu, Oct 8, 2026+2+10
Fri, Oct 9, 2026+0+00
Sat, Oct 10, 2026+0+04
Sun, Oct 11, 2026+2+04
Mon, Oct 12, 2026+1+03
Tue, Oct 13, 2026+4+00
Wed, Oct 14, 2026+3+012
Thu, Oct 15, 2026+1+00
Fri, Oct 16, 2026+2+10
Sat, Oct 17, 2026+4+00
Sun, Oct 18, 2026+1+00
Mon, Oct 19, 2026+0+10
Tue, Oct 20, 2026+2+00
Wed, Oct 21, 2026+3+00
Thu, Oct 22, 2026+0+00
Fri, Oct 23, 2026+1+10
Sat, Oct 24, 2026+2+06
Sun, Oct 25, 2026+1+011
Mon, Oct 26, 2026+0+00
Total+45+1084
  • 1#1 on the list
  • 7Rank that day
  • Not trending

Social mentions

Recent discussions about this repository across the web
  1. Oct 51 post

    • On that GGUF GPU path, Flash Attention AUTO was silently off (D3D12 layers vs CPU FA node). Force-ENABLED when layers go GPU. Measured decode vs CPU (Series S): Coder-3B 1.90×, LFM2.5-1.2B 1.88×.…

      Read full on X, posted by @gmazza1989

      @gmazza1989 · x.com

  2. Oct 21 post

    • Same console vs CPU: about 1.9× decode on both models. Quality gate still held. This came after making GPU the default for those two — after a D2 gate FAIL and a remake that finally passed.

      Read full on X, posted by @gmazza1989

      @gmazza1989 · x.com

  3. Sep 291 post

    • xllama is that eng stack. I’m building it toward on-console use for games and assistants — proving the runtime first, not shipping an SDK.

      Read full on X, posted by @gmazza1989

      @gmazza1989 · x.com

  4. 13 days earlier
  5. Sep 161 post

    • I brought local LLMs + diffusion + on-device training to Xbox Series S|X. xllama: • Multi-turn chat (up to ~119 tok/s) • SD-Turbo in-process • Partial fine-tuning on the console • OpenAI-compatible…

      Read full on X, posted by @gmazza1989

      @gmazza1989 · x.com

  6. 2 months earlier
  7. Jul 271 post

    • Show HN: Xllama – Local LLM Chat and Stable Diffusion on an Xbox Series S

      Read full on Hacker News

      Hacker News

  8. 2 months earlier
  9. May 261 post

    • xllama is a UWP application for #Xbox Series S|X in Dev Mode that runs LLM inference locally, with no cloud dependency and a gamepad-friendly UI.

      Read full on X, posted by @gmazza1989

      @gmazza1989 · x.com

You might also like

Repositories close to gianlucamazza/xllama
FeaturedAdvertise to 180K+ monthly visitors
Bifrost

Enterprise AI Gateway Built For Scale: Route, Govern, and Secure All Your AI Traffic

sudoingX/local-ai-on-your-gaming-gpu

Python

run a 27b local ai on your gaming gpu, rtx 3060 and up, radeon rx 6600 and up in beta, 8gb or more, linux and windows, one line to install

16719

cobanov/PS5LM

C++

llama.cpp on a jailbroken PS5: run any GGUF model natively on the console, starting with Qwen 3.8

70760

am17an/llama.cpp

C++

LLM inference in C/C++

5722

janhq/cortex.cpp

C++

Local AI API Platform

2.7k183

quatrixone/ProsperoAI

C++

A simple LLM-based chat app that runs on the PS5 GPU

6517

eddoursul/StrataFast

C++

A fork of https://github.com/Niko1221/Strata optimized for my 3090+5070 Ti setup, see docs/COMPARISON.md. Renamed to StrataFast.

525

Quazmoz/InferBridge

Python

Windows-first OpenAI-compatible local LLM server powered by OpenVINO GenAI for Intel CPU/GPU/NPU, with chat UI, model conversion, and setup scripts.

513

ifm-ai/llama.cpp

LLM inference in C/C++

2618

rulith-dev/rulith-inference

Python

Rulith Inference, formerly Strix Llama. Serving a 125B MoE model fast on one AMD Strix Halo machine, on Windows: a patched llama.cpp, a manager, and a desktop app.

435