dramabox

Updated
21.08.2026
Tools
Thinking
Run

Run DramaBox locally with Atomic Chat: offline, private, and free. No cloud, no usage limits.

At a glance

  • License: Apache 2.0, free for commercial use
  • Context length: 128K tokens
  • Languages: 29 languages, English-optimized
  • Minimum hardware: 16 GB RAM, runs on Apple Silicon
  • Strengths: reasoning, coding and multilingual document understanding

What is dramabox?

DramaBox is an open model you can download and run locally in Atomic Chat, fully offline and private.

  • Parameters: 0.4B
  • Context length: 256K tokens
  • Input: text and images
  • Runs: locally on your own hardware, no cloud
  • Cost: free, no API keys, no usage limits

dramabox highlights

  • Runs locally: download once and use it fully offline in Atomic Chat.
  • Private by default: prompts and data never leave your device.
  • No usage limits: no API keys, no per-token fees.
  • One-click setup: install from the Atomic Chat catalog and start chatting.

How to run dramabox locally

Open DramaBox in Atomic Chat and it downloads with one click, then runs entirely on your machine, no account and no internet connection required after the download.

Get the weights from Hugging Face

atomic run Qwen/minicpm-v-4.6
curl https://api.atomic.chat/v1/run \
  -H "Authorization: Bearer $ATOMIC_KEY" \
  -d '{"model": "Qwen/minicpm-v-4.6", "prompt": "Hello"}'
from atomic import load_model

model = load_model("Qwen/minicpm-v-4.6")
output = model.run("Your prompt here")
print(output)
import { loadModel } from "atomic";

const model = await loadModel("Qwen/minicpm-v-4.6");
const output = await model.run("Your prompt here");
console.log(output);
Desktop
macOS
(M1 or better)
Download
Windows
(x64)
Download
Linux
(x86_64)
Download

Frequently asked questions

Yes. Once the weights are downloaded the model runs entirely on your device. No internet connection, API key or account is required, and no data leaves the machine.

The model runs on consumer hardware: a recent laptop or desktop with enough memory is enough. Quantized builds lower the requirement further, and a discrete GPU speeds up generation but is optional.