R
Sep 20, 2026Run Qwen3.8 27B on Your Laptop, They Said. It Will Be FUN, They Said.
PrismML released Bonsai 2 27Bthis week: Qwen3.8-27B distilled to ternary weights, 5.9 GB in its...
Sep 20, 20268 min read0 reactions0 comments
Back to articles 
Jul 15, 2026
Tag archive
#bonsai
H
Aug 4, 2026How Prism ML Squeezed a 27B Model Into 3.9 GB
How Prism ML Squeezed a 27B Model Into 3.9 GB Most of us assume that useful AI needs a...
Aug 4, 20263 min read0 reactions0 comments
Bonsai 27B: A 27B Model on Your Phone — and the One Benchmark That Collapses (2026)
PrismML shipped 1-bit and ternary builds of Qwen3.6-27B on July 14, 2026 — 5.9 GB for ternary, 3.9 GB for 1-bit, running at 163 tok/s on an RTX 5090 and 11 tok/s on an iPhone 17 Pro. Every writeup lea
Jul 15, 20261 min read0 reactions0 comments
5
Aug 4, 20265 Coding Models You Can Actually Run on a Laptop in 2026
5 Local Coding Models I Keep Installed in 2026 I still use cloud APIs for genuinely hard...
Aug 4, 20265 min read0 reactions1 comments
C
Nov 10, 2023Conversations with Computers: Coding as an Art Form
To picture the computer as a living entity; the computer is ready to be put into motion. The list of possible commands is vast and ever changing.
Nov 10, 20232 min read0 reactions1 comments