We handed the same one-line prompt to seven AI models — four running locally on a single desktop, three in the cloud — and asked each to build a rotating, textured 3D Earth. Only three produced a working render. Two of them ran on the box on our desk, for nothing.
"Build a realistic 3D Earth that rotates continuously — Three.js, textured sphere, sunlight, a starfield, standalone in a browser."
| Model | Where | Time | Result | |
|---|---|---|---|---|
| 1 | Ornith 35B | local | 10.0s | works — cleanest of all seven |
| 2 | Chadrock 35B | local | 13.0s | works — custom atmosphere shader + clouds |
| 3 | MiniMax M3 | cloud · nvidia | 237s | works — best-looking, but ~4 minutes |
| — | Gemma 26B | local | 8.8s | broke — invented an npm package (404) |
| — | Qwen 30B | local | 14.7s | broke — missing one config line → blank |
| — | Kimi K2.6 | cloud · nvidia | 25.4s | broke — one garbled line → syntax error |
| — | GLM 5.1 | cloud · canopy wave | — | broke — wrong texture in the cloud slot |
Local coding models went 2-for-2. Cloud went 1-for-3.
Local models ran on one desktop via llama.cpp. Cloud models were served on the free NVIDIA API (Kimi K2.6, MiniMax M3) and Canopy Wave (GLM 5.1) — hosted, not local. Even the free cloud tier didn't change the outcome.
It wasn't a clean sweep, and pretending it was would be a lie. Here's the honest split:
The only render with real weather — a proper cloud layer, atmospheric glow, a soft day/night terminator. It genuinely looks like a photo from orbit. It also thought for four minutes on someone else's machine to get there.
A correct, clean, photorealistic Earth — same base texture, ocean highlight, atmosphere glow, starfield. Written in 945 tokens, ten seconds, no bill, no data leaving the building.
The entire visual gap between them was one cloud layer. Same base Earth, same continents, same glow. Strip MiniMax's clouds and they're near-twins — and that single layer of extra polish cost 24× the time and a rented datacenter.
Not one of the seven failed on the actual 3D graphics. Every model knew the concept cold — scene, lighting, sphere, animation loop, all correct. The four that broke tripped on a detail: a made-up dependency, a missing line, one stuttered token, a mis-wired asset. The winners weren't smarter about graphics. They were more careful.
And the sharper point is the price tag on polish. The best render came from the cloud — but a 4-bit model on one desktop got 90% of the way there instantly, for free, with nothing leaving the room. The question isn't whether local beats the cloud. It's this: when local is good enough, instant, and free, the cloud has to justify its bill on every single query.
7 models, 1 identical prompt, 3 clean renders.
Best value: Ornith, local — a correct Earth in 10 seconds for $0.
The cloud's prettier render took ~4 minutes — 24× the time — for one extra cloud layer.
Cloud models went 1-for-3. Local coding models went 2-for-2.
No model failed on the graphics — every failure was a small precision slip.
Hardware: one 128 GB desktop, models running at ~4.3 bits per weight.
The fine print, because receipts beat hype: one task, graphics only — don't read it as "model X beats model Y at everything." One cloud model (GLM) ran through an agent harness rather than a direct prompt, so its conditions differed. And all four failures are fixable one-liners — these models are one token from working, not incapable. The story isn't that the cloud is bad. It's that local is now genuinely in the fight.
← Back to Alpha Ranch