PrismML Releases Bonsai 27B: 1-bit and Ternary Builds of Qwen3.6-27B That Run on Laptops and Phones
MarkTechPost Asif Razzaq
PrismML released Bonsai 27B, a quantized version of Qwen3.6-27B using 1-bit and ternary weight compression. The ternary variant achieves 5.9GB model size while retaining 94.6% of FP16 baseline performance, and the 1-bit variant reaches 3.9GB with 89.5% retention. These models enable running 27B-class quality inference on laptops and phones with practical memory constraints and improved throughput on resource-limited devices.
Why it matters
PrismML just released Bonsai 27B. It is a low-bit representation of Qwen3.6-27B, not a new pretrain. The architecture is unchanged. Two variants ship under Apache 2.0. Ternary Bonsai 27B uses {−1, 0, +1} weights at a true 1.71 bits per weight. Its ideal size is 5.9GB. 1-bit Bonsai 27B uses binary {−1, +1} weights at […] The post PrismML Releases Bonsai 27B: 1-bit and Ternary Builds of Qwen3.6-27B That Run on Laptops and Phones appeared first on MarkTechPost.
Related stories
Deploying a 1-Bit Bonsai-27B Model with PrismML llama.cpp and OpenAI-Compatible Local Inference Workflows
MarkTechPost · 1 month ago ·
33
Qwen 3.6 27B is the sweet spot for local development
Quesma · 2 months ago ·
28