Research · October 2026

The thinking, on your Mac.

Sting is our own engine for running AI on an ordinary 16 GB MacBook. For the two jobs Smart Jelly does most, finding what you owe and noticing when it’s done, it comes close to the cloud, in under a second.

See the results Coming to the app

81Finding what you owe: how often it matches the cloud.the cloud matches itself 93 · the same model, run the usual way, 66

92Noticing when it’s done.the cloud matches itself 99 · the usual way 65

0.6 sTo read a conversation for tasks.the cloud call takes 2.1 s

16 GBAn ordinary MacBook with an M4 chip.no server, no data centre

Results

Nearly as good as the cloud, on the jobs that matter.

Each job is asked exactly the way Smart Jelly asks it today. The score is how often the answer matches the cloud model the app uses. The black line is the cloud matched against itself: the most anyone can score.

StingThe same model, run the usual wayThe cloud, matched against itself

Finding what you oweThe tasks in a conversation that are yours to do.200 test conversations · 4 languages

81.1

65.6

The cloud matches itself 92.6% of the time

Noticing when it’s doneWhich open tasks the new messages finish.100 test conversations · 4 languages

91.8

65.4

The cloud matches itself 98.9% of the time

Does this need a reply?A yes or no for each new message.14 real messages · a small first check

85.7

not run

The cloud matches itself 85.7% of the time

Scored on test conversations no model learned from. Ranges and how we measured are in the research notes below.

Speed

Faster than asking the cloud.

No round trip to a server. Median times on a 16 GB MacBook with an M4 chip, against the app’s cloud call for the same job.

Read a conversation for tasks

Sting0.6 sCloud2.1 s

Does this need a reply?

Sting0.1 sCloud4.1 s

Is this a group message, not for you?

Sting0.1 sCloud1.2 s

How it works

Most local AI runs any prompt. Sting runs one job.

It is written for one model, one kind of Mac and one task at a time. Knowing the job ahead of time is what makes a small model good enough.

Built for one modelHand-written code for the graphics chip, shaped to one 4-billion-parameter model (Qwen3.5-4B, at 4 bits). No Python and no server: a small library made to ship inside the app.

One pack per jobEach job comes as a pack: the model, a small add-on trained for that one job, the job’s instructions prepared once and kept in memory, and the app’s own safety checks.

Yes or no in one stepFor a yes-or-no question, Sting reads the answer straight from the model in a single pass instead of writing it out: about 0.1 seconds.

Stops earlyMost conversations have nothing to report. Sting can tell after one pass, and stops there.

Same answer, every timeEvery change to the engine is checked word by word against a reference. A change that alters an answer is a bug, never a speed-up.

Careful when unsureThe checks drop a task nobody asked of you, and won’t close a task without proof. When in doubt, a task stays open.

Compared

Sting and Husky.

Husky, from Underdog, is the fastest engine for one model on Apple silicon that we know of. Husky is built for speed on any prompt. Sting is built for the right answer to one job, on the laptop people already own.

Measure	Husky · M5 Max, 128 GB · their figures	Sting · M4, 16 GB · measured	What it means
Checking 8 drafted words, cost vs 1	1.5×	1.03–1.1×	Sting checks a draft almost for free, so every accepted word is nearly pure gain.
A yes or no for a job	not offered	~90 ms	Sting reads the answer in one pass; there is no text to write.
“Nothing to report”	writes the answer	one pass, then stops	Most chats hold no task; Sting stops as soon as it knows.
Scored on the app’s real jobs	not published	81 / 92 vs cloud 93 / 99	Every Sting number here is scored against the cloud model the app uses.
Words kept per read, copy-heavy job	5.4	2.3–3.3	Husky trains its drafter; Sting drafts from the conversation itself.
Plain writing speed vs MLX	up to 4.5×	~1× (31 vs 33 words/s)	Both are limited by memory speed; Husky’s code gets closer to the limit.
Reading a new prompt	5,150 tokens/s	275–310 tokens/s	The M5 has matrix hardware the M4 lacks; Sting keeps job instructions in memory instead.

Bold marks the side ahead on that row. Husky’s numbers are Underdog’s published figures on different hardware; Sting’s are measured on a 16 GB M4.

Research notes

How we measured it.

The jobsEach request is built by Smart Jelly’s own code, in the app’s exact layout, and scored against the cloud model the app uses for that job.

The test conversations300 conversations written for this test, in English, Hindi, Hinglish and Marathi-English: work, family, small business and college chats, with real tasks, traps and noise. No real person’s messages. No model learned from them.

The scoreF1 over the tasks found or closed, after the app’s own safety checks. Most conversations have nothing to report, so answering “nothing” every time scores 0.

RangesFinding tasks: 81 (75 to 87). Noticing when done: 92 (85 to 97). 95% ranges, by conversation.

The machineA 16 GB MacBook with an M4 chip. Greedy decoding, thinking off. Times are medians.

Same answersSting matched the reference implementation, running the same model and add-on, on 116 of 119 test requests; the other three differ where two next words score almost the same.

What we’re working on.

People and projectsTeaching Sting the jobs that build your memory: who people are, and how your day splits into episodes.

A trained drafterDrafting from the app’s own answers, to keep 5 or more words per read.

Faster codeFrom about 70% to about 90% of the chip’s memory speed.

Newer chipsPrompt code for the M5’s matrix hardware.

Coming soon

On your Mac, in Smart Jelly.

Sting is coming to Smart Jelly as a third way to run it. For your to-dos, your conversations will be read on your Mac and nothing will be sent to a server. Everything else keeps working the way you choose today.

Download Smart Jelly today macOS 14+ · Apple silicon · On-device mode will need 16 GB of memory

Our relayToday · all featuresOnly the few lines a question needs leave your Mac.

Your own keysToday · all featuresThe same lines, sent straight to your own AI account.

On your Mac, with StingComing soon · your to-dosFinding and closing what you owe, with nothing sent anywhere.