PrismML's ternary-compressed Bonsai 2 27B lands on OpenRouter at just ~8.5GB
gajesh · x · 2026-09-19
PrismML's reasoning model Ternary Bonsai 2 27B is now live on OpenRouter. Derived from Qwen3.8-27B, it supports coding, math, tool calling, and image understanding with a 262K context window, thinking by default at xhigh reasoning effort.
Its key feature is ternary compression: language-model weights shrink to roughly 8.5GB while retaining 98.2% of the base model's average score across PrismML's 14 thinking-mode benchmarks, enabling efficient inference on consumer hardware. Pricing is $0.075/$0.50 per 1M input/output tokens.
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
- AMD MI455 beats Nvidia Rubin on raw specs, claims viral chip debate — zephyr_z9 · 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