paperniuk/splash

Activity and trending

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

Sep 23 – Nov 5, 2026

Stars +208 in 44 days

Forks +16 in 44 days

Merged PRs 19 in 44 days

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

Not in the Trendshift top 25 in this period

Sep 23Sep 29Oct 5Oct 11Oct 17Oct 23Oct 29Nov 4

Stars, forks, merged pull requests and Trendshift Trending rank, by day
Day	Stars gained	Forks gained	Merged PRs
Wed, Sep 23, 2026	+0	+0	0
Thu, Sep 24, 2026	+9	+1	0
Fri, Sep 25, 2026	+12	+0	0
Sat, Sep 26, 2026	+14	+1	0
Sun, Sep 27, 2026	+16	+1	0
Mon, Sep 28, 2026	+10	+1	0
Tue, Sep 29, 2026	+3	+0	0
Wed, Sep 30, 2026	+2	+0	0
Thu, Oct 1, 2026	+6	+0	0
Fri, Oct 2, 2026	+9	+0	0
Sat, Oct 3, 2026	+8	+0	0
Sun, Oct 4, 2026	+4	+0	0
Mon, Oct 5, 2026	+2	+0	0
Tue, Oct 6, 2026	+1	+0	0
Wed, Oct 7, 2026	+2	+1	0
Thu, Oct 8, 2026	+6	+0	0
Fri, Oct 9, 2026	+1	+0	0
Sat, Oct 10, 2026	+3	+0	0
Sun, Oct 11, 2026	+3	+1	0
Mon, Oct 12, 2026	+6	+0	0
Tue, Oct 13, 2026	+1	+0	0
Wed, Oct 14, 2026	+3	+1	0
Thu, Oct 15, 2026	+7	+0	0
Fri, Oct 16, 2026	+2	+0	0
Sat, Oct 17, 2026	+1	+0	0
Sun, Oct 18, 2026	+5	+1	0
Mon, Oct 19, 2026	+8	+1	0
Tue, Oct 20, 2026	+4	+0	1
Wed, Oct 21, 2026	+9	+2	3
Thu, Oct 22, 2026	+4	+0	2
Fri, Oct 23, 2026	+5	+0	0
Sat, Oct 24, 2026	+3	+1	4
Sun, Oct 25, 2026	+2	+1	0
Mon, Oct 26, 2026	+5	+0	0
Tue, Oct 27, 2026	+3	+0	0
Wed, Oct 28, 2026	+4	+1	0
Thu, Oct 29, 2026	+0	+0	0
Fri, Oct 30, 2026	+7	+0	0
Sat, Oct 31, 2026	+1	+2	0
Sun, Nov 1, 2026	+1	+0	9
Mon, Nov 2, 2026	+4	+0	0
Tue, Nov 3, 2026	+9	+0	0
Wed, Nov 4, 2026	+3	+0	0
Thu, Nov 5, 2026	+0	+0	0
Total	+208	+16	19

#1 on the list
Rank that day
Not trending

incoai/splash

C++

A local inference engine for Apple silicon, built around the model.

2.1k191

paperniuk/ds4

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.

343

struffl/ishizuki

Swift

works well with rocks; native Apple Silicon inference engine for capable and tiny models (ternary, Qwen) via MLX Swift. Hadamard-rotated KV cache, vision, tool calling, OpenAI + Anthropic APIs

294

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.

2.7k226

publicExcess/splish

C++

Splish: a fork of Inco's Splash, tuned for Apple M5 GPUs. Apache-2.0

323

nace-ai/kapitsa

C++

Blazing fast Apple Silicon inference engine optimized for Qwen & Nemotron. OpenAI + Anthropic API compatible. Built by folks from nace.ai

64596

samuelfaj/lightning-mlx

Python

🔥 The fastest local AI engine for Apple Silicon. Optimised for agentic use.

9812

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.

672

lithos-ai/lithos-metal

Python

lithos-metal: high-performance LLM inference kernels and serving for Apple silicon.

33231

Momentum