Mac Studiohost
M4 Max · 64 GB
- Role
- Model server (oMLX)
- Runs
- Qwen3.8-27B · 4-bit & 8-bit
Welcome.txt
My personal diary — from what I know, towards what I don't.
I'm trying to make a film
It's my first attempt, and it has only just begun. That's all I'll share about it for now.
By profession, I'm an officer of the Indian Revenue Service. By curiosity, I'm deep in AI — exploring the interface between people and machines: how AI is changing the way we work with computers, how we decide, and how its intuition is quietly entering everyday life.
This desktop is my personal diary of that exploration — the layer through which I meet the world. I start from what I know and walk towards what I don't.
Rig — local AI
Local-first AI · at home
A small AI rig on my desk.
Three Macs on one private Tailscale network. The Studio serves open models through oMLX, so private work never has to leave home — and the other machines can use it from anywhere.
Mac mini
M2 · 8 GB
- Role
- Worker
- Runs
- Agents and jobs
MacBook Air
M4 · 16 GB
- Role
- Client, on the move
- Runs
- Chat · coding sessions
Local models served · 178M tokens · 7,337 requests
- Qwen3.8-27B-4bit3,698 req82M
- Qwen3.8-27B-8bit1,884 req64M
- Qwen3.5-9B-4bit1,147 req24M
- Qwen3-Coder-30B-A3B-Instruct-4bit371 req5M
- gemma-4-26b-a4b-it-4bit69 req1M
- Qwen3.6-35B-A3B-4bit21 req692K
Three Macs on one private Tailscale network. The Studio serves the models through oMLX; the mini and the Air reach it from anywhere and share the work.
The ground I stand on.txt
Civil service and digital public infrastructure (DPI), 2016–2026
Everyone brings their own story. Mine includes about ten years inside India's digital public systems, as an officer of the Indian Revenue Service (Customs and Indirect Taxes) since 2016 — in the field, in policy and in product. It is part of who I am, not all of it.
More on the field, policy and product yearsPulse — 52 weeks
Oct 2025Last 7 days: 774
- Commits
- 2,887
- Merged PRs
- 525
- From AI agents
- 320+
AI drafts; I decide. Most changes start as a pull request from Claude Code (257) or Codex (63); I review them and decide what merges. Only counts leave GitHub — never code, file names or commit messages. As of 10 Oct 2026.
Burn — tokens
Tokens through my AI toolsAs of 10 Oct 2026
31.1Btokens
97% re-read from prompt cache · 536M fresh in · 74M out
- Re-read from cache30.3B · 97%
- Written to cache228M · 0.7%
- Fresh input536M · 1.7%
- Output74M · 0.2%
By tool
Claude CodeAnthropic · agentic coding58% of all · since May 202618.1B
CodexOpenAI · agentic coding31% of all · since May 20269.72B
Z.ai GLMZCode app + opencode · GLM-5.39.4% of all · since Jun 20262.94B
Local (oMLX)On my Macs · Qwen3.8 and friends0.6% of all · lifetime178M
opencode · otherDeepSeek, GPT via opencode0.6% of all · since Jun 2026173M
Burning about 5B a week lately — 9.32B in the last 7 days. Cloud agents carry 99% of it; the local rig, 0.6%.
Week of 21 JunLast 7 days
The cloud agents — Claude Code, Codex and GLM — do the heavy lifting and re-read long contexts from cache all day. The local rig handles the private work. They draft; I review and decide what ships. Counted on my Mac from each tool's own usage logs; only totals leave the machine. Claude Code keeps its local logs for a limited time, so its count covers the retained history only.
Experiments
9 items · 1 film · 5 private · 3 openAs of 10 Oct 2026
Some names are withheld on purpose: a name or a web address is easy for someone else to claim, so I describe the work instead.
Info — A film
A film
Film · Starting
My first attempt at making a film. It has only just begun.
- Last moved
- Just starting
- Activity
- Nothing to count yet
- Source
- Not shown yet