IM

POCKET Zimage CPU

ImageGGUF by FINAL-BenchUpdated 2026-09-25
Download on Hugging Face
Parameters6.15B
Context—
Layers—
Architecture—
Smallest quant3.5 GB
Quick answer

POCKET Zimage CPU needs about 4.4 GB of memory at Q4_0 (a 3.5 GB file) with an 8K context window, so it fits on a 6 GB GPU.

POCKET Zimage CPU – 6B image model running on a CPU only

POCKET Zimage CPU is a 6.15B parameter image generation model based on Z-Image-Turbo. It is packaged for plain office PCs without GPU, CUDA, or Python. The model produces 512×512 photorealistic images in under a minute on a CPU.

Good at

  • Fast CPU inference
  • Photorealistic 512×512 images
  • Bilingual text rendering

Limits

  • No GPU required, but CPU only
  • Requires 4.4 GB VRAM estimate at 8k context
  • No vision or other modalities

Best for

  • On-device image generation
  • Low‑resource photorealistic rendering
  • Simple prompt‑based image creation

Who it’s for. Developers and users who need image generation without a GPU. Ideal for office PCs or servers with only CPU resources. Suitable for quick prototyping and low‑budget deployments.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_03.5 GB 4.4 GB
Fits Get file →

The Q4_0 quantization is available at 3.51 GB. It requires an estimated 4.4 GB VRAM at 8k context. For tighter memory budgets, consider a higher‑quantization variant if available. The file size and memory estimate are approximate.

What GPU do you need for POCKET Zimage CPU?

These figures add the file size, an fp16 KV cache at an 8K context window and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.

  • 4 GB VRAM: no quant fits at an 8K context.
  • 6 GB VRAM: the best quant that fits is Q4_0 (3.5 GB file, about 4.4 GB in use).

Which POCKET Zimage CPU quant should you choose?

Q4_0 (3.5 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Parameters6.15B

Source

Quantized byFINAL-Bench
FamilyImage
Licenseapache-2.0
Downloads (HF)2,200
Last updated2026-09-25

Frequently asked questions about POCKET Zimage CPU

How much VRAM does POCKET Zimage CPU need?

About 4.4 GB at Q4_0 with an 8K context window. That is the 3.5 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.

Can I run POCKET Zimage CPU on an 8 GB GPU?

Yes, with Q4_0: the 3.5 GB file needs about 4.4 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of POCKET Zimage CPU GGUF?

It depends on the quant: Q4_0 is 3.5 GB.

Where can I download POCKET Zimage CPU GGUF?

The files are on Hugging Face in the FINAL-Bench/POCKET-Zimage-CPU repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does POCKET Zimage CPU use?

Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Can I run POCKET Zimage CPU on a laptop with 8 GB VRAM?

Yes, the Q4_0 quantization requires an estimated 4.4 GB VRAM at 8k context, which fits within 8 GB VRAM.

Does this model support text‑to‑image on a CPU?

Yes, it generates photorealistic 512×512 images on a CPU only, without CUDA or Python.

What is the context length for this model?

The model uses an 8k token context length for inference.

Other GGUFs of Z-Image-Turbo

Similar models

Browse all →

More from FINAL-Bench

All by FINAL-Bench →

More Image models

All Image →

Other small models

All small models →