PrismML

3 releases covered on ThursdAI

July 2026

PrismML
New ModelsOpen weights

Bonsai 27B

PrismML compresses a full 27B model to 3.9GB so it runs on a phone

PrismML released Bonsai 27B, extreme quantizations of Qwen 3.6 27B under Apache 2.0: a 1-bit build at 3.9GB keeping ~90% of full-precision quality — small enough for an iPhone 17 Pro's memory budget — and a ternary build at 5.9GB keeping ~95%. Both stay multimodal with the full 262K-token context window. Nisten demoed it live on the show running on a phone and on a 6GB GTX 1660 Ti.

3.9GB / 90% 1-bit variant size / quality retained5.9GB / 95% ternary variant size / quality retained262K context window (tokens)
Bonsai 27B (official blog) ↗Bonsai 27B on Hugging Face ↗Announcement on X ↗
🎙️ Hear our coverage →
#open-source#on-device#multimodal

May 2026

PrismML
New ModelsOpen weights

Bonsai Image 4B

PrismML's 1-bit Bonsai Image 4B runs local image gen under 1GB

PrismML released 1-bit and ternary versions of Bonsai Image 4B, a sub-1GB diffusion transformer for local image generation. The quantized model even runs in-browser via WebGPU and ships with an iOS app and a Hugging Face demo.

PrismML Bonsai Image 4B — blog ↗PrismML Bonsai on Hugging Face ↗Bonsai Image demo ↗Bonsai Studio iOS app ↗
🎙️ Hear our coverage →
#image-gen#on-device#infrastructure

April 2026

PrismML
New ModelsOpen weights

Bonsai

PrismML releases Bonsai 1-bit models, an 8B model in 1.15 GB

PrismML released Bonsai, a family of 1-bit quantized open models fitting an 8B model into 1.15 GB and claiming 10x intelligence density, built on decades of compression research. The panel discussed one-bit quantization as a cost/performance lever for cheap local inference.

Announcement (X) ↗Hugging Face ↗PrismML site ↗
🎙️ Hear our coverage →
#open-source#infrastructure#on-device