Notesproduct14 min

GLLmolfar 0.9.36: a content studio and built-in models that run on your laptop

Two experiments in one release: Gemma 4 models that download into the app and run without keys or a connection, and a studio that writes pages, articles and emails from your facts. Measured on one laptop, with screenshots, timings and every invented sentence we caught.

The short answer

what
Two experimental features in 0.9.36: built-in Gemma 4 models (download, check, delete, use for every task) and a content studio for six kinds of page with eleven designs, model-free checks and one targeted fix.
why
A crawl ends with a list of pages to write or rewrite. Until now that needed a model account; small open models have become good enough to draft, if the app does the parts they are bad at.
who
People who crawl sites with GLLmolfar and want drafts written from what the crawl found, on their own computer.
where
On the person's own computer. Measured on a laptop with an AMD Ryzen 9 8945HS, integrated Radeon 780M graphics and 28.8 GB of memory.
when
GLLmolfar 0.9.36 for Windows and Mac, released 11 November 2026; every measurement here is from the same day.
how
Six local models benchmarked on the app's own tasks; the app's built-in check run on Gemma 4 12B; six page types generated the old way and through the studio, timed, and read line by line.

In plain words

GLLmolfar can now download a small AI model and run it on your own computer, so it can write without an account anywhere else. It is slower and makes more mistakes than the big paid assistants, and the app says so in a red box. It also has a new studio: you give it facts about your shop or your site, and it makes a web page, an article or an email. The model only writes the words; the app draws the page and checks that nothing was made up.

GLLmolfar 0.9.36 has two new parts, both marked experimental and both open to signed-in apps only. The first runs an AI model inside the app: you download it once, and from then on it answers on your own computer, with no key, no account elsewhere and no connection. The second is a content studio: it turns the facts you give it — a catalogue, the findings of a crawl — into a page, an article or an HTML email.

This article shows both, and measures both. Everything was run on 11 November 2026 on one ordinary laptop: an AMD Ryzen 9 8945HS with integrated Radeon 780M graphics and 28.8 GB of memory, no separate graphics card. GLLmolfar is ours, so read the claims knowing whose tool it is; the numbers are the ones we got, including the ones that do not flatter it.

Built-in models

Settings › AI models now opens with a section called Built-in models on this computer. It names the memory, the graphics card and the free disk it found, and offers three models, each on its own card. The first press downloads the engine as well — llama.cpp, about 40 MB — which runs on Vulkan on Windows (AMD, Intel and NVIDIA graphics, integrated ones included) and on Metal on Apple silicon. If the graphics card cannot take the model, the app falls back to the processor and remembers that it had to.

A download can be stopped and resumed from where it stopped, and the finished file is checked against its published size and SHA-256 before the app will use it. Delete removes the model's file; deleting the last model removes the engine too, so nothing is left behind in the folder.

GLLmolfar 0.9.36, Settings › AI models. A red-and-black box headed Experimental feature says local models run on this computer without keys or tokens but do not replace a full subscription to GPT, Claude by Anthropic, Gemini and others, and recommends OpenRouter, with a Connect OpenRouter button. Below: this computer has 28.8 GB of memory, AMD Radeon 780M Graphics, 72.9 GB free. Three cards: Gemma 4 E4B, 4.6 GB, memory from 8 GB, with a Download button; Gemma 4 12B, 6.6 GB, memory from 16 GB, marked Recommended and Installed, with four passed checks — started in 8.7 s, speed 8.2 tokens/s, answered the audit as valid JSON, English meta description of 130 characters — checked on the graphics card, last check took 0:44, and buttons Use for every task, Check on this computer and Delete; Gemma 4 26B A4B, 15.8 GB, memory from 32 GB, with a warning that this computer has less memory than the model needs.
The model cards on the test laptop. Gemma 4 12B is installed and checked; the 26B card warns before anything is downloaded.

The red-and-black box at the top is there on purpose and does not go away. Local models are slower than the large hosted ones and make more mistakes; they do not replace a subscription to GPT, Claude or Gemini, and for work that has to be right we recommend connecting a model through OpenRouter, which is one press away in the same box. The built-in models are for drafts, for work that must not leave the computer, and for trying the app's AI features before deciding on anything else.

Use for every task puts the installed model on all eight of the app's AI roles — topics, fixes, audit, prompts on pages, the agent, content, checks and social posts — in one press, instead of choosing it in each list. A model that passes Check on this computer is also put on every role that has no model yet, without touching the roles you already pointed somewhere else.

ModelDownloadMemory it asks forWhat it is for
Gemma 4 E4B4.6 GB8 GBAny laptop: topics, fixes, the agent, short texts
Gemma 4 12B6.6 GB16 GBTitles, descriptions, FAQ and paragraphs in five languages; recommended from 16 GB
Gemma 4 26B A4B15.8 GB32 GBThe most precise audit; needs 32 GB

Why Gemma 4: six models on the app's own tasks

Before choosing what to ship we ran six current open models through the same script, on the same laptop, once on the processor and once on the integrated graphics. The tasks were the ones the app actually gives a model: an audit of eight pages with seven planted issues, returned as JSON; a title and meta description in English, Ukrainian, Spanish, French and Polish within length limits; two small reasoning tasks; and a two-step tool call. This run used Ollama, not the app's engine, so its speeds are for comparing models with each other.

ModelTokens/s, graphics (processor)Audit, issues of 7Invented issuesReasoning, of 2Texts in limits, of 5 languages
Gemma 4 E4B17.3 (10.1)4 · 8 s025
Qwen3.5 4B19.1 (10.6)3 · 6 s022
Qwen3.5 9B11.3 (6.3)2 · 9 s022
Gemma 4 12B10.6 (9.6)6 · 16 s014
Ministral 3 8B14.1 (6.6)5 · 20 s101
Gemma 4 26B A4Bdid not start (9)7 · 39 s022

Writing speed on integrated graphics, tokens per second

Gemma 4 E4B17.3
Qwen3.5 4B19.1
Qwen3.5 9B11.3
Gemma 4 12B10.6
Ministral 3 8B14.1
Radeon 780M through Vulkan, Ollama. Gemma 4 26B A4B did not start on the integrated graphics; on the processor it wrote 9 tokens/s.

Audit without reasoning: planted issues found, of 7

Gemma 4 E4B4
Qwen3.5 4B3
Qwen3.5 9B2
Gemma 4 12B6
Ministral 3 8B5
Gemma 4 26B A4B7
Eight pages, seven planted issues: a title over 60 characters, a missing description, a linked 404, two pages sharing one title, a noindex page in the sitemap and a missing H1. Ministral 3 8B also reported an issue that was not there.

Try it on your own page

See what Voicescope finds on a page of yours

Everything above is measurable on your own work, and the check takes about a minute. Paste one address and read what comes back.

Open Voicescope

Free · no account · one at a time

What decided it:

  • Gemma 4 had the best audits. Gemma 4 12B found 6 of 7 issues in 16 seconds without reasoning; the 26B found all 7. Ministral 3 8B found 5 and invented one. Qwen3.5 9B found 2 without reasoning; with reasoning it found 6, but took 5.2 minutes.
  • Reasoning is too slow to be the default. With it switched on, Gemma 4 E4B, 12B and 26B also reached 6 of 7, in 1.5, 2.3 and 3 minutes. The app asks for answers without it.
  • Speed is not the bottleneck it looks like. Qwen3.5 4B was the fastest writer at 19.1 tokens/s, but kept only 2 of 5 texts within limits and confused what the page was about.
  • Texts: Gemma 4 E4B kept all five languages within limits, Gemma 4 12B four; read by hand, the 12B's texts were grammatically clean in all five, with a slightly promotional tone. The Qwen models and Ministral missed the limits in most languages, and Qwen3.5 9B advised deleting orphan pages when the task was to link them.

Two results were the same for all six. Every model completed the two-step tool call correctly. And no Ukrainian answer from any model contained a Russian letter — something we check mechanically in everything the app writes, because a model asked for Ukrainian can drift into Russian spellings.

The check on this computer

A benchmark on our laptop says little about yours, so every card has Check on this computer. It starts the model, measures how fast it writes, asks for a small audit as JSON and for a meta description, and shows each step as it happens, with a clock and the engine's own log — how many layers went to the graphics card, what it is loading — so a long first start does not look like a hang. The check always runs in English, whatever the interface language, so its results compare across machines; the card says so under the button.

On the test laptop Gemma 4 12B passed all four steps on the graphics card: started in 8.7 s, wrote 8.2 tokens per second, returned valid JSON and a 130-character English meta description; the whole check took 44 seconds. The very first start, with the model not yet in memory, took 33 s. This is the app's own engine, llama.cpp on Vulkan, so its speed is not directly comparable with the Ollama run above.

Gemma 4 12B in the app: seconds to start

First start, cold33.0
Next start8.7
GLLmolfar 0.9.36, Check on this computer, Radeon 780M. The first start reads 6.6 GB from disk; later starts find it in memory.

The content studio

The studio is a new section in the left rail, also experimental. It makes six things: an article, a home page, a product list, a product page, an alternatives page and an HTML email. You give it the site or brand, the search query the page is for, the audience, the goal, the language and — the part that matters — the facts the model may use. It writes with whichever model the content role uses: a built-in one, Ollama or LM Studio on the same computer, or a hosted model through OpenRouter.

The GLLmolfar content studio. Under the heading Content studio, a line explains that the model writes only the words while GLLmolfar's templates draw the page and its checks catch invented numbers, contacts and repeats. A red-and-black Experimental feature box says local and inexpensive models write drafts, not finished pages, and asks to read the result before publishing. Below: six tabs (Article, Home page, Product list, Product page, Alternatives, HTML email) with Product list selected; a Design row of eleven theme swatches from Studio to Midnight Galaxy and a field to take the style from a page; fields for site or brand (Біг і Крок), main search query, language (Ukrainian), audience, goal and the facts the model may use, starting with the shop's catalogue.
The brief for a product list of a running-shoe shop: six products with prices, categories, delivery and returns.

The way it works is the release's real change. The first version of this feature asked the model for a whole HTML page, and small models are poor at that: the design varied from page to page, and they filled the footer and the copy with things nobody gave them. Now the model returns only the content, as JSON — a heading, an introduction, the products with their notes, the FAQ — and GLLmolfar's templates draw the page. Then come checks that need no model at all:

  • every number in the text must appear in the facts ("2 480" and "2,480" count as the same number);
  • every phone, email address and year must appear in the facts;
  • claims about the business that the facts do not make — "we developed", "our specialists" — are flagged;
  • repeated passages are found by overlapping three-word sequences;
  • lengths of titles and descriptions are measured, and Russian letters are flagged in Ukrainian.

Whatever the checks find goes back to the model once, as a targeted fix of those fields only, not as "rewrite it". Anything still wrong is listed above the result, so the draft arrives with its own review.

Articles get one more step. A long piece written in one call by a small model loses its line; written section by section, each section repeats the last. The studio writes an outline, then each section seeing what has already been said, what comes later and the text so far, then the FAQ.

A studio result in GLLmolfar: the product list written by Gemma 4 12B. Above it, two lines flagged by the checks: faq[1].a repeats what was already said about free delivery from 2 000 UAH, and faq[2].a repeats that a product can be returned within 14 days. Buttons Copy HTML and Save HTML. Below, the rendered page of the Біг і Крок shop: the heading Кросівки для бігу, an introduction, three numbered tips (choosing a model, size, returns), filter links for asphalt, trail, women's, men's and under 3000 UAH, and product cards beginning.
A real result: Gemma 4 12B, local. The two repeats in the FAQ were not fixed, so the studio lists them above the page.

The design is a choice of eleven themes. One is the studio's own; ten are adapted from the theme-factory skill that Anthropic publishes under Apache-2.0, with fonts that carry Cyrillic. Or press Use my site's style: the app opens the page you name in a hidden window, reads its background, text and button colours, its fonts and the rounding of its buttons, darkens or lightens any text or accent colour that would fail contrast, and offers the result as one more theme. The HTML email has its own template — tables, 600 pixels wide, styles inline — because email programs do not render the layouts a browser does.

Eleven versions of the same generated product list, one per theme: Studio, Ocean Depths, Sunset Boulevard, Forest Canopy, Modern Minimalist, Golden Hour, Arctic Frost, Desert Rose, Tech Innovation, Botanical Garden and Midnight Galaxy. The words and products are identical; colours, fonts and backgrounds change, and three of the themes are dark.
One content, eleven themes. The model wrote the words once; switching the theme redraws the page without calling it again.

Before and after, on the same model

To see what the pipeline is worth we generated all six types twice with the same local model, Gemma 4 12B, on the same brief: once the old way, with the model writing the whole HTML page, and once through the studio. Then we ran the studio once more on a small hosted model, DeepSeek V4.1 Flash through OpenRouter, to show where a fast connection takes it. Times are per page, from the first call to the finished page, including the fix.

PageBefore: Gemma 4 12B writes HTMLStudio: Gemma 4 12BFasterStudio: DeepSeek V4.1 Flash
Article4:363:391.3×0:45
Home page3:332:211.5×0:16
Product list3:532:461.4×0:08
Product page2:501:561.5×0:22
Alternatives4:181:282.9×0:14
HTML email2:430:285.8×0:07

How much faster the studio wrote each page on Gemma 4 12B, times

Article1.3
Home page1.5
Product list1.4
Product page1.5
Alternatives2.9
HTML email5.8
Same model, same laptop, same facts. The email gains most: twenty lines of content instead of a whole table-based HTML document.

Speed is the smaller half. The larger one is what the old pages contained that nobody had given the model:

  • a copyright line with © 2023 on the home page, the product list and the alternatives page;
  • "our specialists will help" on the product list — the shop has no specialists in its facts;
  • "We developed this model" and "high wear resistance" on the product page — the shop sells the shoes, it did not make them, and the facts say nothing about wear;
  • three words that do not exist in Ukrainian in the article.

Through the studio none of those remained. One slipped through on the product page — "Ми створили", "we created" — and the claims check now catches that phrasing too. On the home page the fix call mixed up an FAQ question and its answer, which the result list did not catch; that is the weakest point we know of, and the next check to add is that each answer belongs to its question. DeepSeek through the studio invented nothing on any of the six pages.

Two product pages for Runner X side by side. Left, Before, Gemma 4 12B writing the whole HTML in 2:50: an orange blob instead of a product picture, four ticks including Висока зносостійкість, a specifications box, a Про товар section that begins Ми розробили цю модель, an FAQ and related products. Right, Studio, Gemma 4 12B in 1:56: the studio template with a neutral box mark instead of a photo, price 2 899 грн, four facts (240 g, daily runs, sizes 36–46, 8 mm drop), a Купити button, a description, a specifications table, a collapsible FAQ and three related product cards.
Product page, same model. Left: "high wear resistance" and "we developed this model" are not in the facts. Right: specifications come only from the facts.
Three product lists for the same shop. Left, Before, Gemma 4 12B in 3:53: identical round blobs for six products, an FAQ, related categories and a dark footer reading © 2023. Middle, Studio, Gemma 4 12B in 2:46: a heading, an introduction, three tips, filter links, six product cards with tags and prices, a collapsible FAQ. Right, Studio, DeepSeek V4.1 Flash through OpenRouter in 0:08: the same template with different words and tips about weight, fit and surface.
The product list three ways. The template is the same in the two studio columns, so the difference between them is only the words.
Three HTML emails announcing Tempo Lite and Night Run. Left, Before, Gemma 4 12B in 2:43: a colourful email built from divs with two product cards and the full range listed. Middle, Studio, Gemma 4 12B in 0:28: a table-based 600-pixel email with a heading, three numbered items and a button. Right, Studio, DeepSeek V4.1 Flash in 0:07: the same template, three items including delivery and returns, and a button to the new models.
The email template is plainer than the old free-form one, and it holds together in email programs. Making it richer is on the list.

What a local model is good for here

On this laptop Gemma 4 12B through the studio needs one to four minutes a page and produces a draft that has to be read: the checks and the one fix catch most of what goes wrong, not all of it, and the style leans formal. That is useful when the facts must not leave the computer, when you want twenty drafts overnight, or when there is no account to connect. DeepSeek V4.1 Flash through OpenRouter wrote the same six pages ten to twenty times faster and invented nothing, which makes a small hosted model the better everyday choice. We also had Claude Opus write the same six contents once for the same templates, outside the app and untimed: it was the densest and the most candid — it said "no weight data" where the facts had none — and is worth it where a text goes to a client unedited.

The studio does not decide that for you. It shows which model wrote the page beside the result, and the same brief can be run again on a different one.

Trying it

Update GLLmolfar to 0.9.36 on Windows or Mac and sign in; both features are open to signed-in apps while they are experiments. The models are in Settings › AI models; the studio is in the left rail. A model is a few gigabytes, so download it on a connection you do not mind using for that. After the download, the built-in model works without one. We measured on Windows only; on Apple silicon the engine is the same build on Metal, and we have no numbers from a Mac yet.

One change to what the app sends: the anonymous usage statistics now include which built-in models are installed, as catalogue names only (for example gemma4-12b), so we can see which sizes people actually keep. The settings screen and the GLLmolfar page list it with everything else the app sends; it never includes a site address, a prompt or anything a model wrote.

Questions people ask

Do the built-in models replace ChatGPT, Claude or Gemini?

No, and the app says so in the red box above the models. They are slower and make more mistakes. For work that has to be right, connect a model through OpenRouter; the built-in ones are for drafts and for data that must stay on the computer.

Which model should I download?

Gemma 4 12B if the computer has 16 GB of memory or more — it wrote the cleanest text in five languages in our tests, and the app marks it as recommended. Gemma 4 E4B on 8 GB. Gemma 4 26B A4B was the most precise auditor, but asks for 32 GB.

Does anything leave my computer when I use a built-in model?

The model and the engine are downloaded once. After that the model answers locally and the studio's checks run locally. The usage statistics say which built-in models are installed, by catalogue name, and nothing about what they wrote.

Why does the check run in English?

So that its results mean the same thing on every computer and in every interface language. Writing in your language is what the studio and the other features then use the model for.

Can I publish what the studio writes without reading it?

We would not. The checks catch invented numbers, contacts, years and claims, and repeats, but not every mistake: on one page in our tests the fix call swapped an FAQ question and answer. Treat the result as a draft.

How this was measured

One laptop: AMD Ryzen 9 8945HS, Radeon 780M integrated graphics through Vulkan, 28.8 GB of memory, Windows, 11 November 2026. Model choice: Ollama, one script, six models, processor and graphics runs saved as JSON per model. In-app check: GLLmolfar 0.9.36, llama.cpp build b12284, the values stored by the check and shown on the card. Studio: one brief for a running-shoe shop with six products, Gemma 4 12B Q4_K_M in Ollama on the graphics card, and deepseek/deepseek-v4.1-flash through OpenRouter, wall time per page. Invented content was found by reading every page against the facts and confirmed by searching the saved HTML. The screenshots are of GLLmolfar 0.9.36 with an isolated profile holding the real model file and check result, and of the pages the runs produced.

Related: GLLmolfar, What's new in GLLmolfar: four releases, 2–3 November 2026.

The product

Watch it on every page, every day

One reading tells you where a page stands today. The product asks the same questions of the same assistants continuously, so a change is something you are told about rather than something you go looking for.

Request an invitation

Invite-only while we keep the readings honest

On this topic

Is my page ready for AI search?

Every day Crawls with the Vectorscope reading beside every page, re-checked after each fix. How the product works

Author

Olexandrauthor

15+ years in marketing and SEO. Dozens of products, mostly the US market. Research and measurement.

LinkedIn

Pass it on

Read in your language

Opens a browser translation of this English article. The original source stays in English.