Ternary Bonsai 2 27B released: 9x smaller, 98.2% of full precision, just 5.9 GB under Apache 2.0
cephaloform · x · 2026-09-18
PrismML announced Ternary Bonsai 2 27B, a ternary-quantized model based on Qwen3.8 27B that is 9x smaller than its full-precision counterpart while retaining 98.2% of aggregate benchmark performance. Two months after the first Bonsai 27B, the 5.9 GB footprint is unchanged but quality gaps narrowed sharply, with strong gains in agentic coding, multimodal reasoning, and long-horizon tool use. Released under Apache 2.0; users are already eyeing running it locally on a 3080 and canceling API subscriptions.
Related event: PrismML's Ternary Bonsai 2 27B Shrinks to 5.9GB, Retains 98.2% Performance(20 posts)→
More from Infra
- Training-free page-sparse decode in llama.cpp: 1.72× faster 128k decoding on an RTX 5090 — topppggg · 2026-11-16
- llama.cpp offloads CI caches and runners to Hugging Face to survive 35 PRs/day — ggerganov · 2026-11-16
- India's Sarvam launches Token Factory, hosting top open models on local infra — HarveenChadha · 2026-11-16
- ZGX Fury stress-tested: 351 tok/s on Qwen3.8-Flash-Next, offline agents and local RAG demos — Sam Witteveen · 2026-11-16
- Gemini 3.5 Flash now runs on air-gapped Google Distributed Cloud, offline up to 12 months — shashib · 2026-11-16
- Gemma.c: full Gemma 1/2/3 multimodal inference in a single C file, ~72 tok/s on CPU at INT8 — This-Purchase-3325 · 2026-11-16