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. Ternary compression shrinks the language-model weights to roughly 8.5 GB while retaining 98.2% of the base model's average score across PrismML's 14 thinking-mode benchmarks, enabling efficient inference on consumer hardware. The model thinks by default and defaults to xhigh reasoning effort.

ChatPrism-ml262k tokens$0.0818 / $0.545 · 1M

prism-ml/ternary-bonsai-2-27b

Context
262k tokens
Completion cap
32,768
Tools
Yes
JSON
Yes
Released
2026-09-18

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-2-27b",
    "messages": [{"role": "user", "content": "Hola"}]
  }'
Get an API key

Frequently asked questions

What is 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. Ternary compression shrinks the language-model weights to roughly 8.5 GB while retaining 98.2% of the base model's average score across PrismML's 14 thinking-mode benchmarks, enabling efficient inference on consumer hardware. The model thinks by default and defaults to xhigh reasoning effort. Ternary Bonsai 2 27B runs on the Geek Hub API (OpenAI-compatible). Model id: prism-ml/ternary-bonsai-2-27b.
Is Ternary Bonsai 2 27B free?
No. Input is $0.0818 per 1M tokens and output is $0.545 per 1M tokens on Geek Hub (markup included).
What is the context length of Ternary Bonsai 2 27B?
Ternary Bonsai 2 27B has a 262k tokens context window. It supports up to 32,768 completion tokens.
Does Ternary Bonsai 2 27B support tool calling and structured outputs?
Ternary Bonsai 2 27B 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 27B released?
Ternary Bonsai 2 27B was released on 2026-09-18.