This is Space Bunny. A new stealth model in @Opencode.
This is a AI post classified by Jev as Open & local models (a model release), kept by the AI Radar because it carries real work, not commentary.
This is Space Bunny. A new stealth model in @Opencode. It made this - a voxel turtle with a city on its back. Looks pretty good, though it was insanely hard for her. This is a very, very fast model - the decoding speed in Opencode Go is just crazy, but it lacks precision. Must be quite a small model. I'm thinking something like DeepSeek v4 Flash size or something like that. I spent about 4 hours getting this piece into this shape. It sees images quite accurately, constantly checked her work by taking screenshots, and tried to fix issues. In the end, it pulled it off.
Posted by Alexey Fateev (6.4k followers) 58 min ago · 10 likes · 620 views · view the original post on X. Kept by the AI Radar as Open & local models.
More AI work like this
- Muse spark 1.4 has just been found in OpenCode — @MaaSonder
- Google Antigravity SDK now runs Gemma 4 26B locally on GPU via Google AI Edge LiteRT. — @0x0SojalSec
- Uncensored & Mythos-Class Agentic Qwen3.8-27B you can run locally on consumer hardware. — @0x0SojalSec
- You can now add usage credits for paid cloud models without an Ollama subscription. — @ollama
- Local Ai is about to enter the stratosphere 🤯🚀 — @ashxhart
- The Easiest way to start with Local AI Today? ODS, which is completely free (open-source… — @TheAhmadOsman
- Meet Sharp-Spark-X2.5-4B-GGUF: a 4B parameter text generation model built for speed and… — @HuggingModels
- Vision tower on DeepSeek-V4-Flash-Vision-Exp is 0.41B params. The whole model is 304.65B. — @cozybearlog
Every post is read and classified by Jev (TypeSafe): what it is, which market it belongs to, and whether the link is a real tool. 45.9k posts from 5k X accounts over the last 14 days, 1.9k tools, 19 markets. Collected every 5 minutes, fully re-ranked every hour — last update 2026-09-24 06:54 UTC. Full method.