Files read on Hugging Face: 2026-10-24

Z-Image-Turbo GGUF files and Mac RAM

Turbo checkpoint of the 6B Z-Image family, released under Apache 2.0. The card example makes a 1024 x 1024 image in 9 scheduler steps, which run 8 DiT forwards, with guidance 0.

Tongyi-MAI · Updated 2026-10-24
Answer

No published Mac run with a GGUF build yet. The smallest complete GGUF download is 13.23 GB; a download that fits in memory does not prove the model runs.

Smallest Mac with a published run
none yetunknown below
Smallest complete download
13.23 GBQ4_K_M GGUF
Files read
2026-10-24Hugging Face

Apache 2.0. Commercial use: allowed. Excluded territories: none listed.

Table 1

Which exact GGUF files make a complete build?

Only builds with every required component and an exact probed file size are shown.

Q4_K_M GGUF

gguf · Q4_K_M · 13.23 GB complete

Mac routes: stable-diffusion.cpp

Exact component files for Q4_K_M GGUF
FileComponentRequiredDownloadSource
z-image-turbo-Q4_K_M.ggufunsloth/Z-Image-Turbo-GGUFZ-Image transformerditYes5.02 GBHugging FaceRead 2026-10-24
text_encoder/model-00001-of-00003.safetensorsTongyi-MAI/Z-Image-TurboQwen3 text encodertext_encoderYes3.96 GBHugging FaceRead 2026-10-24
text_encoder/model-00002-of-00003.safetensorsTongyi-MAI/Z-Image-TurboQwen3 text encodertext_encoderYes3.99 GBHugging FaceRead 2026-10-24
text_encoder/model-00003-of-00003.safetensorsTongyi-MAI/Z-Image-TurboQwen3 text encodertext_encoderYes0.10 GBHugging FaceRead 2026-10-24
vae/diffusion_pytorch_model.safetensorsTongyi-MAI/Z-Image-TurboVAEvaeYes0.17 GBHugging FaceRead 2026-10-24

Build sources: Z-Image-Turbo GGUF card · stable-diffusion.cpp README.

Q8_0 GGUF

gguf · Q8_0 · 15.44 GB complete

Mac routes: stable-diffusion.cpp

Exact component files for Q8_0 GGUF
FileComponentRequiredDownloadSource
z-image-turbo-Q8_0.ggufunsloth/Z-Image-Turbo-GGUFZ-Image transformerditYes7.22 GBHugging FaceRead 2026-10-24
text_encoder/model-00001-of-00003.safetensorsTongyi-MAI/Z-Image-TurboQwen3 text encodertext_encoderYes3.96 GBHugging FaceRead 2026-10-24
text_encoder/model-00002-of-00003.safetensorsTongyi-MAI/Z-Image-TurboQwen3 text encodertext_encoderYes3.99 GBHugging FaceRead 2026-10-24
text_encoder/model-00003-of-00003.safetensorsTongyi-MAI/Z-Image-TurboQwen3 text encodertext_encoderYes0.10 GBHugging FaceRead 2026-10-24
vae/diffusion_pytorch_model.safetensorsTongyi-MAI/Z-Image-TurboVAEvaeYes0.17 GBHugging FaceRead 2026-10-24

Build sources: Z-Image-Turbo GGUF card · stable-diffusion.cpp README.

Table 2

Does it fit your Mac's RAM?

Published names the exact measured machine. est. is a memory calculation. unknown means the run verdict is not established, not that the model fails.

Run verdicts by Mac memory tier
Mac RAMComplete buildDownloadRun verdictBasis
8 GBQ4_K_M GGUFQ4_K_M · stable-diffusion.cpp13.23 GBDoes not fitest.
16 GBQ4_K_M GGUFQ4_K_M · stable-diffusion.cpp13.23 GBunknownunknown
24 GBQ4_K_M GGUFQ4_K_M · stable-diffusion.cpp13.23 GBunknownunknown
32 GBQ4_K_M GGUFQ4_K_M · stable-diffusion.cpp13.23 GBunknownunknown
48 GBQ4_K_M GGUFQ4_K_M · stable-diffusion.cpp13.23 GBunknownunknown
64 GBQ4_K_M GGUFQ4_K_M · stable-diffusion.cpp13.23 GBunknownunknown
96 GBQ4_K_M GGUFQ4_K_M · stable-diffusion.cpp13.23 GBunknownunknown
128 GBQ4_K_M GGUFQ4_K_M · stable-diffusion.cpp13.23 GBunknownunknown

How does it rank in blind votes?

#59 of 82 in text to image blind votes, from 24,808 votes.

Quality: blind human votes from z-image-turbo (arena.ai), CC BY 4.0, snapshot 2026-10-07. Scores are for the Arena checkpoint, not your local quantized build.

Which Mac software routes are listed?

  • stable-diffusion.cpp

    Official

    Formats: gguf, safetensors. Memory policy: component stages stay resident.

    C/C++ runner with Metal on Mac and CUDA on NVIDIA. It reads GGUF and safetensors, and its docs keep a page per model family. Resident size is the sum of the weights, an upper bound.

    Sources: stable-diffusion.cpp README, backends

What does the official configuration say?

"The card says the model fits comfortably within 16G VRAM consumer devices. This is a GPU statement for the Z-Image family, not a Mac minimum."

Source: Z-Image-Turbo model card · Read 2026-10-24.

What known issues should you check?

  • Known issue 1

    The only Mac run is a pre-release test in an mflux pull request, made before mflux changed its default float32 stream. Treat it as one data point.

    Source: mflux pull request 820 · Read 2026-10-24

Sources