thomas9120/gufo-windows

Activity and trending

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

Sep 27 – Oct 26, 2026

Stars +22 in 30 days

Forks +4 in 30 days

Merged PRs 85 in 30 days

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

Not in the Trendshift top 25 in this period

Sep 27Oct 1Oct 5Oct 9Oct 13Oct 17Oct 21Oct 25

Stars, forks, merged pull requests and Trendshift Trending rank, by day
Day	Stars gained	Forks gained	Merged PRs
Sun, Sep 27, 2026	+0	+0	1
Mon, Sep 28, 2026	+0	+0	2
Tue, Sep 29, 2026	+0	+0	3
Wed, Sep 30, 2026	+0	+0	2
Thu, Oct 1, 2026	+0	+0	5
Fri, Oct 2, 2026	+3	+0	1
Sat, Oct 3, 2026	+1	+0	1
Sun, Oct 4, 2026	+0	+0	1
Mon, Oct 5, 2026	+0	+0	4
Tue, Oct 6, 2026	+0	+0	1
Wed, Oct 7, 2026	+0	+0	1
Thu, Oct 8, 2026	+1	+1	5
Fri, Oct 9, 2026	+0	+0	3
Sat, Oct 10, 2026	+0	+0	1
Sun, Oct 11, 2026	+0	+0	0
Mon, Oct 12, 2026	+1	+0	1
Tue, Oct 13, 2026	+1	+0	2
Wed, Oct 14, 2026	+1	+0	1
Thu, Oct 15, 2026	+4	+0	8
Fri, Oct 16, 2026	+5	+0	1
Sat, Oct 17, 2026	+0	+1	1
Sun, Oct 18, 2026	+0	+0	4
Mon, Oct 19, 2026	+0	+0	2
Tue, Oct 20, 2026	+1	+0	3
Wed, Oct 21, 2026	+0	+0	6
Thu, Oct 22, 2026	+1	+1	11
Fri, Oct 23, 2026	+3	+0	7
Sat, Oct 24, 2026	+0	+0	5
Sun, Oct 25, 2026	+0	+1	2
Mon, Oct 26, 2026	+0	+0	0
Total	+22	+4	85

#1 on the list
Rank that day
Not trending

pixmaate/gufo

C++

Strix Halo inference engine. Qwen Flash Next Q4_K_XL: 1,628.52pp, 59.41tg single user, 157.22 tok/s 8 users; Qwen27B Q4_K_XL: 656.33pp, 70.56tg tok/s single user with DFlash2

389

gufo-org/gufo

C++

The Open Source Strix Halo AI engine. Qwen 3.8 Flash Next Q4_K_XL: 1,801.01 pp, 73.17 tg single user, 194.37 tok/s 8 users; Qwen 3.8 27B Q4_K_XL: 656.33pp, 70.56tg tok/s single user with DFlash2

934127

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

mikealanni/gufo

C++

Strix Halo (gfx1151) + XDNA2 NPU inference fork: Qwen3.8 Flash-Next UD-IQ4_XS with MTP. About 2,000 tok/s prefill (GPU + NPU, 2,013 at 8K), ~50 tok/s decode at 116k context, 76 tok/s on HumanEval.

797

BBALabs/athanor-lite

Rust

Free GPU detection and local AI model manager. Scans your hardware, recommends compatible models, and handles download + launch in one click.

415

tsaipifong/whirl-llm

C++

WHIRL (Windows HIP Inference for RDNA LLMs): native Windows C++/HIP LLM inference engine for the AMD Ryzen AI Max+ 395 (Radeon 8060S) and Radeon AI PRO R9700. Unzip and run, only the AMD driver.

343

gufo-org/toolboxes

Nix

Gufo OCI Images for AMD Strix Halo

235

Hal0ai/hal0

Python

Open-source self-hosted home AI inference platform for AMD Strix Halo — multi-backend slots, OpenAI-compatible gateway, Vue 3 + FastAPI + systemd.

8414

Momentum