Inside The Machine

← All business recipes

B-03Blueprint · assembly sheet

Thumbnail & title lab

Make many title and thumbnail ideas on your machine, score them all, and let Claude pick the few worth testing.

Title blockbuild.ts

Part no.
B-03
Family
Content studio
Runs from
8 GBParts run one at a time
Status
Not tested yet
In
A finished video and a few lines about it.
Out
3 title options and 2 thumbnail ideas, each with a reason.
Tools
OllamaComfyUIDraw Things
Note
Blueprint. Not run yet. First run on the Mac Studio from 10 Nov 2026.
1Claude's job

Claude does the few hard parts.

Planning, the hard writing and the final review. That takes few tokens.

Claude does
  • Writes a short brief once: the angle, who it is for, and three title rules.
  • Picks the top 3 titles and 2 thumbnail ideas from the scored list, and says why.
Claude never sees

Claude sees the brief and the scored shortlist, not the video.

2Local partsFig. 1 · Parts listmodels.json ·

Your machine does the bulk.

Find your memory. Each row names the model for each part. Free, private, on your computer.

The model for each part at each memory size. Parts run one at a time.models.json · images.json ·
No.MemoryDrafterDecider (Local Jev)Image maker
SZ-018 GB6 GB usableQwen3.5 4Bneeds 5.8 GBRuns, but tightQwen3.5 4Bneeds 5.8 GBRuns, but tightZ-Image Turboneeds 4 GBRuns well
SZ-0216 GB12 GB usableGemma 4 12Bneeds 11.2 GBRuns, but tightQwen3.5 0.8Bneeds 2.6 GBRuns wellZ-Image Turboneeds 4 GBRuns well
SZ-0324 GB18 GB usableGemma 4 12Bneeds 11.2 GBRuns wellQwen3.5 4Bneeds 5.8 GBRuns wellZ-Image Turboneeds 4 GBRuns well
SZ-0432 GB24 GB usableQwen3.8 27Bneeds 22.7 GBRuns, but tightQwen3.5 4Bneeds 5.8 GBRuns wellMing-Image 0.1 Designneeds 24 GBRuns, but tight
SZ-0548 GB36 GB usableQwen3.8 27Bneeds 22.7 GBRuns wellGemma 4 12Bneeds 11.2 GBRuns wellMing-Image 0.1 Designneeds 24 GBRuns well
SZ-0664 GB48 GB usableQwen3.8 27Bneeds 22.7 GBRuns wellGemma 4 12Bneeds 11.2 GBRuns wellMing-Image 0.1 Designneeds 24 GBRuns well
SZ-0796 GB72 GB usableQwen3.8 27Bneeds 22.7 GBRuns wellQwen3.8 27Bneeds 22.7 GBRuns wellMing-Image 0.1 Designneeds 24 GBRuns well
SZ-08128 GB96 GB usableQwen3.8 27Bneeds 22.7 GBRuns wellQwen3.8 27Bneeds 22.7 GBRuns wellMing-Image 0.1 Designneeds 24 GBRuns well
SZ-09192 GB144 GB usableQwen3.8-Flash-Next (125B-A6B)needs 140 GBRuns, but tightQwen3.8 27Bneeds 22.7 GBRuns wellMing-Image 0.1 Designneeds 24 GBRuns well
SZ-10256 GB192 GB usableQwen3.8-Flash-Next (125B-A6B)needs 140 GBRuns wellQwen3.8 27Bneeds 22.7 GBRuns wellMing-Image 0.1 Designneeds 24 GBRuns well
SZ-11512 GB384 GB usableQwen3.8-Flash-Next (125B-A6B)needs 140 GBRuns wellQwen3.8 27Bneeds 22.7 GBRuns wellMing-Image 0.1 Designneeds 24 GBRuns well
Drafter

Writes the first draft of many small things: summaries, title options, reply drafts.

How we pick it: The smartest chat model that fits your usable memory and has an Ollama download (the same model the /do recipes install).

Decider (Local Jev)

Answers typed questions about each item: pick one, give a score, or yes/no. It never writes.

How we pick it: The smartest chat model with an Ollama download that needs no more than a third of your usable memory. Smaller models answer sooner, and a decider only picks a label. If no model is that small, the drafter's model decides too.

Image maker

Draws rough thumbnail ideas from a short prompt.

How we pick it: The best-rated image model that fits and whose license allows commercial use. A YouTube thumbnail is commercial use.

Fit labels

We count 75% of your memory as usable for AI. The rest is for the system and your apps. Runs well: the model fits in usable memory with at least 10% to spare. Runs, but tight: it fits, but less than 10% of usable memory is left. Close other apps first. Needs N GB+: it does not fit. N is the smallest memory size it fits in.

3Steps

7 steps.

Each step says who does it: you, Claude, your machine or a script.

  1. Claudebrief

    Claude writes the brief

    The angle, the viewer, three rules for titles. A few hundred words, once per video.

  2. Your machineDraftertitles

    Draft 40 titles

    The drafter writes 40 title options that follow the brief.

  3. Your machineDecider (Local Jev)score

    Score every title

    Local Jev scores each title for clarity and curiosity, and asks: does it promise something the video does not deliver (yes/no)? Those are dropped.

  4. Your machineImage makerimages

    Sketch thumbnail ideas

    The image model draws rough ideas from 3 prompts. Ideas only: the final thumbnail is yours.

  5. Claudechoose

    Claude picks the shortlist

    3 titles and 2 thumbnail ideas, each with a one-line reason.

  6. Youyours

    Make it yours

    Make the real thumbnail with your own face or footage. Never use a title the video does not deliver.

  7. Youshare

    Share your run (optional)

    At the end, the script shows exactly what it would upload: your chip, memory, the models, how long each stage took and the token counts. No prompts, no outputs, no file names. Say yes and it goes to our review queue. Nothing is public until we approve it.

4Make it yours

The step only you can do.

Before you publish
  • A title must match the video. Misleading titles and thumbnails break YouTube's rules.
  • Use the AI sketches as ideas, then make the real thumbnail yourself.
5Receiptsapproved runs

What a run costs.

Claude tokens for this recipe and for doing it all in Claude, local minutes and dollars. Only from runs a person has approved.

Receipts

No runs yet
Claude tokens, this recipe
not run yet
Claude tokens, all in Claude
not run yet
Local minutes
not run yet
Claude dollars (estimate)
not run yet
Not run yet

Not run yetBlueprints now, numbers later. We run every recipe on a 128 GB Mac Studio from 10 Nov 2026, then publish the receipts.

6Share your run

Share your run. Only if you want to.

At the end, the script shows exactly what it would upload and asks first. A person reviews every run before it shows here.

It sends
  • Your chip, memory, graphics card and operating system
  • The recipe and the models you used
  • How long each stage took
  • Token counts: Claude in and out, local in and out
  • How many items came out
  • Tool versions
  • A fingerprint (SHA-256) of the log and up to 15 cleaned log lines
  • A handle you pick (not your name or email)
It never sends
  • Your prompts or the model's answers
  • Your files, file names or folder paths
  • Emails, links, keys or IP addresses (the server rejects any upload that has one)
  • Your IP address in plain form: we keep a scrambled copy for rate limits only

Agents can share with the submit_run tool of https://insidethemachine.ai/mcp. Privacy

Agent view · text/markdown · or send Accept: text/markdown
# Blueprint: Thumbnail & title lab

URL: https://insidethemachine.ai/build/thumbnail-title-lab
Part: B-03. Family: Content studio. Status: Blueprint, not run yet.
Blueprint. Not run yet. First run on the Mac Studio from 10 Nov 2026.

Make many title and thumbnail ideas on your machine, score them all, and let Claude pick the few worth testing.

- Input: A finished video and a few lines about it.
- Output: 3 title options and 2 thumbnail ideas, each with a reason.
- Runs from: 8 GB of memory.
- Tools: ollama (https://insidethemachine.ai/setups/ollama.md), comfyui (https://insidethemachine.ai/setups/comfyui.md), draw-things (https://insidethemachine.ai/setups/draw-things.md)

## Claude's job

- Writes a short brief once: the angle, who it is for, and three title rules.
- Picks the top 3 titles and 2 thumbnail ideas from the scored list, and says why.

What Claude never sees: Claude sees the brief and the scored shortlist, not the video.

## Local parts per memory size

Data: models.json 2026-10-15, speech.json 2026-10-15, images.json 2026-10-15.
| memory GB | Drafter | Decider (Local Jev) | Image maker |
|---|---|---|---|
| 8 | Qwen3.5 4B (needs 5.8 GB, runs, but tight) | Qwen3.5 4B (needs 5.8 GB, runs, but tight) | Z-Image Turbo (needs 4 GB, runs well) |
| 16 | Gemma 4 12B (needs 11.2 GB, runs, but tight) | Qwen3.5 0.8B (needs 2.6 GB, runs well) | Z-Image Turbo (needs 4 GB, runs well) |
| 24 | Gemma 4 12B (needs 11.2 GB, runs well) | Qwen3.5 4B (needs 5.8 GB, runs well) | Z-Image Turbo (needs 4 GB, runs well) |
| 32 | Qwen3.8 27B (needs 22.7 GB, runs, but tight) | Qwen3.5 4B (needs 5.8 GB, runs well) | Ming-Image 0.1 Design (needs 24 GB, runs, but tight) |
| 48 | Qwen3.8 27B (needs 22.7 GB, runs well) | Gemma 4 12B (needs 11.2 GB, runs well) | Ming-Image 0.1 Design (needs 24 GB, runs well) |
| 64 | Qwen3.8 27B (needs 22.7 GB, runs well) | Gemma 4 12B (needs 11.2 GB, runs well) | Ming-Image 0.1 Design (needs 24 GB, runs well) |
| 96 | Qwen3.8 27B (needs 22.7 GB, runs well) | Qwen3.8 27B (needs 22.7 GB, runs well) | Ming-Image 0.1 Design (needs 24 GB, runs well) |
| 128 | Qwen3.8 27B (needs 22.7 GB, runs well) | Qwen3.8 27B (needs 22.7 GB, runs well) | Ming-Image 0.1 Design (needs 24 GB, runs well) |
| 192 | Qwen3.8-Flash-Next (125B-A6B) (needs 140 GB, runs, but tight) | Qwen3.8 27B (needs 22.7 GB, runs well) | Ming-Image 0.1 Design (needs 24 GB, runs well) |
| 256 | Qwen3.8-Flash-Next (125B-A6B) (needs 140 GB, runs well) | Qwen3.8 27B (needs 22.7 GB, runs well) | Ming-Image 0.1 Design (needs 24 GB, runs well) |
| 512 | Qwen3.8-Flash-Next (125B-A6B) (needs 140 GB, runs well) | Qwen3.8 27B (needs 22.7 GB, runs well) | Ming-Image 0.1 Design (needs 24 GB, runs well) | 

How each part is picked:
- Drafter: Writes the first draft of many small things: summaries, title options, reply drafts. Rule: The smartest chat model that fits your usable memory and has an Ollama download (the same model the /do recipes install). (models.json)
- Decider (Local Jev): Answers typed questions about each item: pick one, give a score, or yes/no. It never writes. Rule: The smartest chat model with an Ollama download that needs no more than a third of your usable memory. Smaller models answer sooner, and a decider only picks a label. If no model is that small, the drafter's model decides too. (models.json)
- Image maker: Draws rough thumbnail ideas from a short prompt. Rule: The best-rated image model that fits and whose license allows commercial use. A YouTube thumbnail is commercial use. (images.json)
- Fit: We count 75% of your memory as usable for AI. The rest is for the system and your apps. Runs well: the model fits in usable memory with at least 10% to spare. Runs, but tight: it fits, but less than 10% of usable memory is left. Close other apps first. Needs N GB+: it does not fit. N is the smallest memory size it fits in. Size unknown: we do not know how much memory it needs.

## Steps

1. **Claude writes the brief** (Claude; stage id `brief`): The angle, the viewer, three rules for titles. A few hundred words, once per video.
2. **Draft 40 titles** (Your machine, Drafter; stage id `titles`): The drafter writes 40 title options that follow the brief.
3. **Score every title** (Your machine, Decider (Local Jev); stage id `score`): Local Jev scores each title for clarity and curiosity, and asks: does it promise something the video does not deliver (yes/no)? Those are dropped.
4. **Sketch thumbnail ideas** (Your machine, Image maker; stage id `images`): The image model draws rough ideas from 3 prompts. Ideas only: the final thumbnail is yours.
5. **Claude picks the shortlist** (Claude; stage id `choose`): 3 titles and 2 thumbnail ideas, each with a one-line reason.
6. **Make it yours** (You; stage id `yours`): Make the real thumbnail with your own face or footage. Never use a title the video does not deliver.
7. **Share your run (optional)** (You; stage id `share`): At the end, the script shows exactly what it would upload: your chip, memory, the models, how long each stage took and the token counts. No prompts, no outputs, no file names. Say yes and it goes to our review queue. Nothing is public until we approve it.

## Make it yours

- A title must match the video. Misleading titles and thumbnails break YouTube's rules.
- Use the AI sketches as ideas, then make the real thumbnail yourself.

## Receipts

- Claude tokens, this recipe: not run yet
- Claude tokens, all in Claude: not run yet
- Local minutes: not run yet
- Claude dollars (estimate): not run yet

No approved runs yet. Blueprints now, numbers later. We run every recipe on a 128 GB Mac Studio from 10 Nov 2026, then publish the receipts.

## Share your run

Opt-in. The script shows exactly what it would upload and asks first. It sends: Your chip, memory, graphics card and operating system; The recipe and the models you used; How long each stage took; Token counts: Claude in and out, local in and out; How many items came out; Tool versions; A fingerprint (SHA-256) of the log and up to 15 cleaned log lines; A handle you pick (not your name or email). Never: Your prompts or the model's answers; Your files, file names or folder paths; Emails, links, keys or IP addresses (the server rejects any upload that has one); Your IP address in plain form: we keep a scrambled copy for rate limits only. Nothing is public until a person approves it. Agents can submit with the `submit_run` tool of https://insidethemachine.ai/mcp.

Privacy: https://insidethemachine.ai/privacy.md