Prism ML PrismML  · Ternary–Bonsai-27B Prism ML Ternary Bonsai 27B · Qwen3.6 27B · ternary 1.71 bpw ·
prism-ml/Ternary-Bonsai-27B-gguf : together

PRISM ML · TERNARY BONSAI 27B

type a prompt below and press Enter (Shift+Enter for newline). streaming tokens appear here.

bonsai ~ $ 
Enter to send · Shift+Enter for newline · Esc to stop

// call this model yourself

This demo runs on Hugging Face Inference Providers (OpenAI-compatible API, routed to Together). You need an HF token with the Inference Providers permission.

curl
curl https://router.huggingface.co/v1/chat/completions \
  -H "Authorization: Bearer $HF_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "prism-ml/Ternary-Bonsai-27B-gguf:together",
    "messages": [{"role": "user", "content": "Write a haiku about a bonsai tree."}],
    "stream": false
  }'
python · openai client
import os
from openai import OpenAI

client = OpenAI(
    base_url="https://router.huggingface.co/v1",
    api_key=os.environ["HF_TOKEN"],
)
resp = client.chat.completions.create(
    model="prism-ml/Ternary-Bonsai-27B-gguf:together",
    messages=[{"role": "user", "content": "Write a haiku about a bonsai tree."}],
)
print(resp.choices[0].message.content)
javascript · openai sdk
import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://router.huggingface.co/v1",
  apiKey: process.env.HF_TOKEN,
});
const res = await client.chat.completions.create({
  model: "prism-ml/Ternary-Bonsai-27B-gguf:together",
  messages: [{ role: "user", content: "Write a haiku about a bonsai tree." }],
});
console.log(res.choices[0].message.content);