stablyai/orca
earendil-works/pi
diegosouzapw/OmniRoute
pbakaus/impeccable
moeru-ai/airi
// OWNER · gavamedia · REPO SNAPSHOT
gavamedia
Run Kimi K3, a 2.8T-parameter Mixture-of-Experts LLM, on a single Apple Silicon Mac. Streams MXFP4 experts on demand over HTTP into a local disk cache — fused NEON kernels, Metal/MPS compute, exact reproducible decoding, and an OpenAI-compatible API server for local chat and coding agents.
gavamediaSTARS13+0 · 7d
FORKS0+0 · 7d
CONTRIBUTORS0maintainer graph thin
OPEN ISSUES · PRS0· 0
LICENSE—no license file
LANGUAGEPython
FOUNDED—
LOCATION—
MEMBERS—
PUBLIC REPOS—
TOTAL STARS—
FOCUS—
FUNDING—
//STAR HISTORY · 12M
+0 all-time-window
Star history not yet available
We don't have a sampled star timeline for gavamedia/deltafin yet. The chart populates once the daily snapshot pass collects its first data points for this repo.
//WHY IT'S TRENDING· narrative synthesis · medium confidence
gavamedia/deltafin is sitting at #1577 on the trending leaderboard with a pulse of 10/100 with no cross-source channels firing yet — GitHub-stars-only signal so far.
It sits at 13 stars without a fresh weekly delta on record — the trending placement here is steady-state interest in the AI agent / LLM tooling stack rather than a 7-day breakout.
Watch-outs: no tagged release on record (treat as pre-stable).
↻ refreshed 50m ago· next sync in 15m· sourced from 0 channels · 0 mentions / 24h
// RELATED REPOS · CROSS-SOURCE OVERLAP
#01
open-webui/open-webui
agent-memoryllm-infralocal-llmShared tag: agent-memory.
CO-MENTIONS · 30D (0 total)
0
#02
raullenchai/Rapid-MLX
agent-skillsclaude-codellm-infraShared tag: agent-skills.
CO-MENTIONS · 30D (0 total)
0
#03
LearningCircuit/local-deep-research
claude-codelocal-llmShared tag: claude-code.
CO-MENTIONS · 30D (5 total)
5#04
dograh-hq/dograh
local-llmShared tag: local-llm.
CO-MENTIONS · 30D (3 total)
1
1
1#05
mlc-ai/mlc-llm
llm-infralocal-llmShared tag: llm-infra.
CO-MENTIONS · 30D (0 total)
0
▌ FAQ · answers from the data spine
What is gavamedia/deltafin?
Run Kimi K3, a 2.8T-parameter Mixture-of-Experts LLM, on a single Apple Silicon Mac. Streams MXFP4 experts on demand over HTTP into a local disk cache — fused NEON kernels, Metal/MPS compute, exact reproducible decoding, and an OpenAI-compatible API server for local chat and coding agents.
Who maintains deltafin?
Maintained by gavamedia (the owner) on GitHub.
What language is deltafin written in?
Primarily Python.
When was deltafin created? When was the last update?
Created July 28, 2026 · last commit July 28, 2026.
How do I install deltafin?
Clone the repo:
git clone https://github.com/gavamedia/deltafin.gitIs deltafin actively maintained?
yes — but slowing (commits within months)
Created
Updated
Last commit
//COMMENTS · 0
Sign in to join the discussion