P
Ternary Bonsai 2 27B
Bonsai 2 27B is a 27B-parameter reasoning model from PrismML derived from Qwen3.8-27B. It supports coding, mathematics, tool calling, and image understanding with a 262K-token context window.
Specifications
| Lab | PrismML |
|---|---|
| Context window | 262.1K tokens |
| Input price | $0.08/1M |
| Output price | $0.50/1M |
| Release | Sep 2026 |
Strengths
- Ternary weights reduce memory footprint and improve local throughput
- Reasoning, coding, mathematics, and tool calling support
- 262K-token context with text and image input
Weaknesses
- Smaller lab and ecosystem than the Qwen base model
- Ternary compression may reduce peak accuracy on demanding tasks
- OpenRouter availability and benchmarks are still limited
Best for
- Local deployment under tight memory limits
- Coding and mathematical reasoning
- Long-context multimodal assistants
In Depth: Ternary Bonsai 2 27B
Summary
Ternary Bonsai 2 27B is an AI model from PrismML.
Released in Sep 2026. It takes text and image input and produces text output, with a context window of 262.1K tokens. Input pricing is $0.08 per 1M tokens and output is $0.50 per 1M tokens on OpenRouter.