Ternary Bonsai 2 27B is 9x smaller than Qwen3.8 27B while keeping 98.2% of its benchmark performance
alexcovo_eth · x · 2026-09-19
PrismML released Ternary Bonsai 2 27B, a ternary-quantized version of Qwen3.8 27B that is 9x smaller (5.9 GB footprint) while retaining 98.2% of the full-precision model's aggregate benchmark performance.
- Biggest change over the first Bonsai 27B (two months ago) is quality, with especially strong gains in agentic coding, multimodal reasoning, and long-horizon tool use
- Runs on 8-16GB of VRAM or 16-24GB of Mac unified memory
- Open-sourced under Apache 2.0
Related event: PrismML's Ternary Bonsai 2 27B Runs at 98.2% Performance in Just 5.9GB(17 posts)→
More from Models
- Meta Muse + Jev screens 10,000 candidates to surface top 100 unanswered immunology questions — DeryaTR_ · 2026-09-19
- Braintrust adds Jev as a judge scorer: typed decisions at up to 193.6× speed and 444.6× lower cost — multiply_matrix · 2026-09-19
- GPU price hike hits even the 1080ti, as local LLM token-speed numbers circulate — HankYeomans · 2026-09-19
- I spent $3.40 on Jev in 24 hours: it will be Jev + LLMs, not Jev vs LLMs — gaganghotra_ · 2026-09-19
- GPT-6 Astra builds a flamethrower demo in Three.js from a screen recording — techartist_ · 2026-09-19
- Databricks: shifting just 20% of coding traffic to OSS models dramatically cuts inference spend — Yuchenj_UW · 2026-09-19