Ternary Bonsai 2 9B
Ternary Bonsai 2 9B is PrismML’s compact, open-weight language model for conversational AI, reasoning, and tool use. Built on Qwen3.5, it uses ternary weights packed into 2 bits for efficient inference. It accepts text and image input. Its 262K-token context window supports long conversations and document-heavy workflows, with up to 64K output tokens per response.
prism-ml/ternary-bonsai-2-9b
- Context
- 262k tokens
- Completion cap
- 65,536
- Tools
- Yes
- JSON
- Yes
- Released
- 2026-10-16
Call it from Geek Hub
Same OpenAI SDK. Change the base URL and the model id.
curl https://api.geekhub.mx/v1/chat/completions \
-H "Authorization: Bearer $GEEKHUB_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "prism-ml/ternary-bonsai-2-9b",
"messages": [{"role": "user", "content": "Hola"}]
}'Frequently asked questions
- What is Ternary Bonsai 2 9B?
- Ternary Bonsai 2 9B is PrismML’s compact, open-weight language model for conversational AI, reasoning, and tool use. Built on Qwen3.5, it uses ternary weights packed into 2 bits for efficient inference. It accepts text and image input. Its 262K-token context window supports long conversations and document-heavy workflows, with up to 64K output tokens per response. Ternary Bonsai 2 9B runs on the Geek Hub API (OpenAI-compatible). Model id: prism-ml/ternary-bonsai-2-9b.
- Is Ternary Bonsai 2 9B free?
- No. Input is $0.0872 per 1M tokens and output is $0.1417 per 1M tokens on Geek Hub (markup included).
- What is the context length of Ternary Bonsai 2 9B?
- Ternary Bonsai 2 9B has a 262k tokens context window. It supports up to 65,536 completion tokens.
- Does Ternary Bonsai 2 9B support tool calling and structured outputs?
- Ternary Bonsai 2 9B accepts tools and tool_choice for function calling. It also supports structured outputs via a JSON schema in response_format.
- When was Ternary Bonsai 2 9B released?
- Ternary Bonsai 2 9B was released on 2026-10-16.