Bonsai 2 27B Mac recipe: Studio & Mini
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
- dear rtx 3060 owners, and every 12gb card behind it. bonsai 2 27b dense went from 26 to… — @sudoingX
- Nimble is able to process images! — @madiator
- Woah...it claims to be open Jev. And it's 100% opensource. — @Saboo_Shubham_
- your rtx 3060 was running bonsai 2 at 26 tok/s this morning and now does 40 tok/s, i… — @sudoingX
- Meet DeepSeek-V4.1-Flash: a blazing fast image-text-to-text model. It takes both images… — @HuggingModels
- Meet Edge0-35B-A3B-preview: a 35B parameter MoE model built for edge inference. It runs… — @HuggingModels
- Putting Jeff-1 out into the world, this is an attempt at a Jev like model, built on qwen… — @DJLougen
- Train a 9M parameter language model from scratch in five minutes. — @tom_doerr
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.