Liquid Crow Released: Squeezing Physical Cognition into a 450M-Parameter Micro-World Model
helloiamleonie · x · 2026-08-12
The developer has quietly released Liquid Crow, a Micro-World Model. The project explores how much physical world cognition can be squeezed into an extremely small footprint of 450M parameters. According to the creator, the model learned from frontier models to describe and simulate the physical world. It is now available on Hugging Face.
More from Models
- With $1.2T Valuation and Upcoming IPO, Users Frustrated by Claude Opus Being 'Lazy' — kimmonismus · 2026-08-12
- MOSS-VL Quantized Models Run Locally on 24GB VRAM for Multimodal Tasks — huggingface · 2026-08-12
- ACE-Step 1.5 Japanese Denpa Fine-Tuned Weights Released, Full Fine-Tune Not LoRA — MuziqueComfyUI · 2026-08-12
- Report: Ilya Sutskever's SSI Pivots to Test-Time Training for New Reasoning Engine — iruletheworldmo · 2026-08-12
- Meta vs NVIDIA 30B Agent Models: Local Execution vs Cloud Routing — eyishazyer · 2026-08-12
- Too RAM-Hungry? Devs Discuss Best SLMs to Run Locally on 16GB Machines — elie2222 · 2026-08-12