I made a Gemma 4 Mac app that names screenshots with local AI
Details
- External ID
- 48342306
- Source
- HN
- Company
- —
- Product
- I made a Gemma 4 Mac app that names screenshots with local AI
- Website domain
- snapname.app
- Launched
- May 31, 2026
- Cohort
- —
- Upvotes
- 7
- Upvotes percentile
- 0.4168012924071082
- Tags
- —
- Fetched at
- Sept. 7, 2026, 9:26 p.m.
- Updated at
- Sept. 7, 2026, 9:26 p.m.
Description
I made my first macOS utility app that ships with a bundled Gemma 4 model, specifically the Gemma E4B one. It made my app DMG have 5.3 GB in size, but I think it is a small size for the power that this free local model can provide.It runs fine on CPU, but can also run on Apple Silicon GPU, although I did not notice any performance improvements with GPU (tested on a M5 chip).I think these local lightweight and multimodal models will open multiple possibilities for new software tools where privacy is essential.
Enrichment
- Theme
- lightweight and on-device AI runtimes
- Vertical
- Horizontal
- Function
- Content generation
- Audience
- Prosumer
- AI stance
- AI-native
- Project type
- Hobby / open-source project
- Normalized one-liner
- mac app that labels screenshots with local ai
- Manually corrected
- False
Could you build this?
Yes The author literally built this by wrapping an existing runtime (llama.cpp) and open weights (Gemma) in a standard macOS app with a file system watcher.
Discussion
6 comments analyzed.
Competitors mentioned: Gemma 4, GPT-3, Llama 3.2, Qwen 2.5
Concerns raised: Requires Apple Silicon processors, Requires Apple Intelligence to be enabled, High RAM usage when running models, Multiple apps using local models consuming device resources
Feature requests: Turn off model when app is idle, relaunch only on new screenshots, Support more powerful models as they become available (e.g., Gemma 5)
Competitors
Other products that read as similar to this one — 95 launches clear the similarity bar, closest 8 shown.
Attention rank: #57 of 96 (itself plus its competitors, highest first — normalized so YC and Product Hunt are compared fairly).
Launched 214 days after the earliest competitor.
- Open-source engine running Gemma 4 26B in 2 GB RAM on any M-series Mac · hn · 2026-07-29 · 919 upvotes · similarity 0.61
- Google Gemma 4 12B · ph · 2026-06-04 · 309 upvotes · similarity 0.55
- Running Gemma-4 26B at 124 tokens/SEC on a CPU, no GPU · hn · 2026-06-30 · 10 upvotes · similarity 0.51
- Tom · ph · 2026-09-18 · 1 upvotes · similarity 0.49
- Local privacy-first Microsoft Recall alternative with Gemma 4 · hn · 2026-07-04 · 13 upvotes · similarity 0.46
- I run a vision model on every screenshot, locally, on a 4GB GPU · hn · 2026-06-13 · 36 upvotes · similarity 0.46
- Gemma 4 Multimodal Fine-Tuner for Apple Silicon · hn · 2026-04-07 · 235 upvotes · similarity 0.43
- Free, Fast Screenshot App for macOS with One-Click Screenshot Sharing · hn · 2026-08-31 · 9 upvotes · similarity 0.42
Other launches for this product
- No other launches for this product.
Same idea, different domain
Nobody's really built a content generation tool for Government yet.