AI Radar
Support
LiveUpdated 2026-09-19 18:08 UTC

Bonsai 2 27B Mac recipe: Studio & Mini

Bonsai 2 27B Mac recipe: Studio & Mini PrismML's ternary quant of Qwen3.8-27B, 1.72 bits/weight. Measured today, same…

This is a AI post classified by Jev as Open & local models (a model release), kept by the AI Radar because it carries real work, not commentary.

Bonsai 2 27B Mac recipe: Studio & Mini PrismML's ternary quant of Qwen3.8-27B, 1.72 bits/weight. Measured today, same harness as my full-size Qwen3.8-27B recipe: Mac Studio M4 Max 128 GB • 34.5 tok/s prose, 34.3 code, 242 tok/s prefill • Spark Bench 82.4/100, grade B Mac mini M4 24 GB (base, 10-core GPU) • 11.0 tok/s decode, 33 tok/s prefill • Same score trajectory as the Studio The 3.1× decode gap is exactly the memory-bandwidth ratio. Full Qwen3.8-27B on the Studio does 53/72 tok/s at ~90 TrueScore in 17 GB, so Bonsai is ~65% of the speed, ~90% of the score, 42% of the size. Recipe + r

Posted by Wësche (2.9k followers) 1 days ago · 28 likes · 1.9k views · view the original post on X. Kept by the AI Radar as Open & local models. Tools mentioned: bonsai-2-27b-mac.

More AI work like this

Every post is read and classified by Jev (TypeSafe): what it is, which market it belongs to, and whether the link is a real tool. 27.2k posts from 4.8k X accounts over the last 14 days, 1.2k tools, 19 markets. Collected every 5 minutes, fully re-ranked every hour — last update 2026-09-19 18:08 UTC. Full method.