Prism Ml/Text / LLMConsumer GPU
Ternary-Bonsai-2 packs a 27B model into 2-bit form
A ternary-quantized 27B model with hybrid attention targets on-device inference across CUDA and Metal.
Company
Prism Ml
2 models
CategoriesText / LLM
Releases
Prism Ml/Text / LLMConsumer GPU
Bonsai-27B Brings 1-Bit Quantization to Local Inference
A ternary-weight 27B model with hybrid attention aims to run large-model reasoning on everyday hardware.
