README.md

---
license: apache-2.0
base_model:
  - Tongyi-MAI/Z-Image
pipeline_tag: text-to-image
library_name: diffusers
language:
  - en
  - ko
tags:
  - text-to-image
  - image-generation
  - quantized
  - bitsandbytes
  - nf4
  - 4-bit
  - on-device
  - korean
  - pocket
  - vidraft
---
> ### 🆕 **[POCKET-Qwen3.8-Flash-Next](https://huggingface.co/FINAL-Bench/POCKET-Qwen3.8-Flash-Next-GGUF)** — a **180B** model running on a **laptop with 8 GB VRAM + 32 GB RAM** · **4.17 tok/s measured**.
> [![New](https://img.shields.io/badge/🆕_NEW-POCKET--180B_on_a_laptop-6c3fd1)](https://huggingface.co/FINAL-Bench/POCKET-Qwen3.8-Flash-Next-GGUF) [![VRAM](https://img.shields.io/badge/VRAM-8_GB-1baf7a)]() [![RAM](https://img.shields.io/badge/RAM-32_GB-1baf7a)]() [![Speed](https://img.shields.io/badge/measured-4.17_tok%2Fs-243456)]() <!-- POCKET-FLASHNEXT-BADGE -->

> ### 🆕 **[POCKET-Zimage-CPU](https://huggingface.co/FINAL-Bench/POCKET-Zimage-CPU)** — photoreal **images** in **46 s** on a **CPU only**. No GPU, no CUDA, no Python.
> [![New](https://img.shields.io/badge/🆕_NEW-POCKET--Zimage--CPU-ff6b35)](https://huggingface.co/FINAL-Bench/POCKET-Zimage-CPU) [![Space](https://img.shields.io/badge/🤗_Space-try_on_CPU-ffce3a)](https://huggingface.co/spaces/FINAL-Bench/POCKET-Zimage-CPU) [![RAM](https://img.shields.io/badge/RAM-6.4_GB-1baf7a)]() <!-- POCKET-Zimage-CPU-BADGE -->


> ### 📚 Collections
> **▶ [POCKET Models](https://huggingface.co/collections/FINAL-Bench/pocket-models-6a618ee5d23eafb7e185a5c6)** — this family (on-device, no GPU)
> [Darwin Family](https://huggingface.co/collections/FINAL-Bench/darwin-family-699987b1f652864af0122193) · [Aether Foundation](https://huggingface.co/collections/FINAL-Bench/aether-foundation-model-6a5c7f2fa1a4165c0414e53a) · [VKAE Accelerated](https://huggingface.co/collections/FINAL-Bench/vkae-accelerated-6a47231d7e7999dd8227675a)

# 🖼️ POCKET-Image-Zimage — 4-bit (NF4) Z-Image for on-device

**Pick your build →** [![35B](https://img.shields.io/badge/POCKET--35B-GGUF-243456)](https://huggingface.co/FINAL-Bench/POCKET-35B-GGUF) [![26B](https://img.shields.io/badge/POCKET--26B-GGUF-2a9d8f)](https://huggingface.co/FINAL-Bench/POCKET-26B-GGUF) [![KR GGUF](https://img.shields.io/badge/POCKET--KR-GGUF-7A1F3D)](https://huggingface.co/FINAL-Bench/POCKET-KR-GGUF) [![KR MLX](https://img.shields.io/badge/POCKET--KR-MLX_(iPhone)-0f6e56)](https://huggingface.co/FINAL-Bench/POCKET-KR-MLX) [![EN GGUF](https://img.shields.io/badge/POCKET--EN-GGUF-185fa5)](https://huggingface.co/FINAL-Bench/POCKET-EN-GGUF) [![180B laptop](https://img.shields.io/badge/POCKET--180B-Qwen3.8_Flash--Next_·_laptop-6c3fd1)](https://huggingface.co/FINAL-Bench/POCKET-Qwen3.8-Flash-Next-GGUF) [![Image NF4](https://img.shields.io/badge/POCKET--Image-Z--Image_NF4-d35400)](https://huggingface.co/FINAL-Bench/POCKET-Image-Zimage) [![Image CPU](https://img.shields.io/badge/POCKET--Zimage-CPU-ff6b35)](https://huggingface.co/FINAL-Bench/POCKET-Zimage-CPU)

A **4-bit (NF4) quantized build of [Z-Image](https://huggingface.co/Tongyi-MAI/Z-Image)** (Apache-2.0),
packaged by VIDRAFT for **low-VRAM, on-device** image generation — part of the POCKET line.

- 📦 **~6 GB on disk** (transformer + text encoder in NF4, VAE in fp16)
- ⚡ **Runs from ~8.6 GB VRAM** (≈**4.5 GB** with CPU offload) — vs **23.3 GB** for bf16
- 🎯 ~2.7–5× smaller footprint, quality on par with the bf16 base

## Usage
```python
import torch
from diffusers import ZImagePipeline   # or ZImageImg2ImgPipeline / ZImageInpaintPipeline

pipe = ZImagePipeline.from_pretrained(
    "FINAL-Bench/POCKET-Image-Zimage", torch_dtype=torch.bfloat16
).to("cuda")
img = pipe("a serene mountain lake at sunrise, photorealistic", num_inference_steps=20).images[0]
img.save("out.png")
```
Requires **`bitsandbytes`** (CUDA). Measured reload + generate peak: ~10.9 GB VRAM.
For Apple Silicon / CPU, an `optimum-quanto` int8 build (~13.4 GB) is the portable option.

## 🎨 The full POCKET-Image system
This repo hosts the **quantized base model** only. The headline **character-perfect Korean &
multilingual text** feature is delivered by the POCKET-Image *pipeline*, not by these weights alone.
Try the full system here:

- **🎨 Studio (generate here):** https://huggingface.co/spaces/FINAL-Bench/POCKET-Image-Studio

Base model: [Tongyi-MAI/Z-Image](https://huggingface.co/Tongyi-MAI/Z-Image) (Apache-2.0) · Quantization: bitsandbytes NF4 · By VIDRAFT.

<!-- POCKET-FAMILY -->

---

## 🧩 The POCKET Family — On-device AI by VIDRAFT

*Big models, small hardware. No GPU, no cloud.*

**Models**
- 📦 [POCKET-35B-GGUF](https://huggingface.co/FINAL-Bench/POCKET-35B-GGUF) — flagship, PC / server, no GPU
- 📦 [POCKET-26B-GGUF](https://huggingface.co/FINAL-Bench/POCKET-26B-GGUF) — compact 26B
- 🇰🇷 [POCKET-KR-GGUF](https://huggingface.co/FINAL-Bench/POCKET-KR-GGUF) — Korean, Android
- 🍎 [POCKET-KR-MLX](https://huggingface.co/FINAL-Bench/POCKET-KR-MLX) — Korean, iPhone / Mac
- 🌍 [POCKET-EN-GGUF](https://huggingface.co/FINAL-Bench/POCKET-EN-GGUF) — English, phone / PC
- 💻 [POCKET-Qwen3.8-Flash-Next-GGUF](https://huggingface.co/FINAL-Bench/POCKET-Qwen3.8-Flash-Next-GGUF) — **180B on a laptop** (8 GB VRAM + 32 GB RAM)
- 🖼️ [POCKET-Image-Zimage](https://huggingface.co/FINAL-Bench/POCKET-Image-Zimage) — character-perfect text in any image
- 🖥️ [POCKET-Zimage-CPU](https://huggingface.co/FINAL-Bench/POCKET-Zimage-CPU) — photoreal images on a CPU only

**Demos & tools (Spaces)**
- 🎨 [POCKET-Image Studio](https://huggingface.co/spaces/FINAL-Bench/POCKET-Image-Studio) — text-in-image, generate in-page
- 🖥️ [POCKET-35B-CPU](https://huggingface.co/spaces/FINAL-Bench/POCKET-35B-CPU) — 35B answering on a CPU
- 🖥️ [POCKET-26B-CPU](https://huggingface.co/spaces/FINAL-Bench/POCKET-26B-CPU) — 26B on a CPU
- 🖼️ [POCKET-Zimage-CPU](https://huggingface.co/spaces/FINAL-Bench/POCKET-Zimage-CPU) — image generation on a CPU

📚 [Full POCKET collection](https://huggingface.co/collections/FINAL-Bench/pocket-models-6a618ee5d23eafb7e185a5c6)

<!-- /POCKET-FAMILY -->