Ternary Bonsai is a headless chicken
Summary
The user tested the Ternary Bonsai 2 27B AI model with a creative prompt, but it entered an infinite loop, repeating without progress for hours and causing disappointment.
Similar Articles
I hope ternary will eventually work but ... sigh
User expresses disappointment with the ternary Bonsai model from Prisml, questioning its quality despite hype, and wonders if it's just typical model overhype.
Ternary Bonsai: Top Intelligence at 1.58 Bits
A highly efficient AI model architecture using ternary weights (-1, 0, 1) that achieves competitive performance while requiring only 1.58 bits per parameter, enabling deployment on extremely constrained devices.
@HuggingModels: Meet Ternary-Bonsai-2-27B: a 27B parameter model squeezed into 2-bit ternary format. Runs on llama.cpp with CUDA and Me…
Ternary-Bonsai-2-27B is a 27B parameter AI model compressed into 2-bit ternary format, running on llama.cpp with CUDA and Metal support, facilitating lightweight on-device AI deployment.
Ternary Bonsai 2 (27B) just released on Hugging Face. At <6GB in size, it can even run locally in-browser on WebGPU.
Ternary Bonsai 2 is a 27B parameter model derived from Qwen3.8-27B that uses ternary weights to achieve a size under 6GB while retaining 98.2% of its intelligence, enabling it to run in-browser on WebGPU.
I ran Ternary-Bonsai-27B (2-bit) and Bonsai-27B (1-bit) on Terminal-Bench 2.0, in 8GB VRAM
A user tested quantized 1-bit and 2-bit versions of the 27B-parameter Bonsai model on Terminal-Bench 2.0, achieving results within 8GB VRAM.