STILLWORKS

Ternary-Bonsai-27B-gguf

text-generation model on Hugging Face

Visit product ↗
AI tools HF Models Launched Jul 04, 2026 by prism-ml View original post ↗

Ternary-quantized Bonsai 27B for efficient local inference.

text-generation

Potential upside

  • Ternary quantization pushes 27B into surprisingly modest memory
  • Real efficiency research, not just a repack

Worth watching

  • Aggressive quantization risks quality loss that only testing reveals

A first look, not a review — this product just launched and has no user history yet. We flag what looks promising and what to check before you rely on it.

Who it's for

Local-LLM tinkerers squeezing big models onto small hardware.

More AI tools