PrismML releases ternary Bonsai 2 27B: 9x smaller, keeps 98.2% of Qwen3.8 27B performance
pcuenq · 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 (about 5.9 GB) while retaining 98.2% of the parent model's aggregate benchmark performance.
- Two months after the first Bonsai 27B, the biggest change is quality: the gap to full precision narrowed materially, with strong gains in agentic coding, multimodal reasoning, and long-horizon tool use
- Runs at 55 tok/s on an M5 Max at under 6 GB
- Released today under Apache 2.0
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