Total runs:
533.2K
Run Growth:
-258.0K
Growth Rate:
-48.38%
Sponsored by
AdsCreator.com
FINAL-Bench / POCKET-Zimage-CPU
Model's Last Updated: September 25 2026
text-to-image
Introduction of POCKET-Zimage-CPU
Model Details of POCKET-Zimage-CPU
๐ POCKET-Qwen3.8-Flash-Next โ a 180B model running on a laptop with 8 GB VRAM + 32 GB RAM ยท 4.17 tok/s measured .
๐ Collections
โถ POCKET Models โ this family (on-device, no GPU) Darwin Family ยท Aether Foundation ยท VKAE Accelerated
POCKET-Zimage-CPU
Pick your build โ
-0f6e56){kind=icon}
Photoreal images in 46 seconds on a CPU only . No GPU. No CUDA. No Python.
๐ Try it live, no install โ
โ generating on a CPU-only box.
The POCKET lineup โ
-ff6b35){kind=icon}
Why this exists
Every image model assumes you have a GPU. Most machines don't.
POCKET-Zimage-CPU is Z-Image-Turbo packaged so that a plain office PC โ no graphics card, no CUDA, no Python environment โ produces a photoreal 512ร512 image in under a minute . One binary, three files, done.
Samples
3 steps ยท 48.6 s ยท the default we ship |
4 steps ยท 60.7 s ยท no visible gain |
Korean prompt ยท note it lost the count |
Prompt:
a red apple on a wooden table, photorealistic
โ Korean:
๋๋ฌด ํ์ ์์ ๋์ธ ๋นจ๊ฐ ์ฌ๊ณผ, ์ฌ์ค์ ์ธ ์ฌ์ง
. Same seed, CPU only.
Measured, not claimed
All numbers below are from our own runs. GPU count used: zero.
| Resolution | Time | Sampling | VAE | Peak RAM |
|---|---|---|---|---|
| 512 ร 512 | 46.4 s | 32.7 s | 12.5 s | 6.42 GB |
| 512 ร 512 (Korean prompt) | 45.3 s | 32.1 s | 12.0 s | 6.42 GB |
| 1024 ร 1024 | 192.7 s | 135.1 s | 55.8 s | 6.76 GB |
Intel Xeon Gold 6526Y ร2 (32 cores / 64 threads), 48 threads, Q4_0, 3 steps,
--fa --vae-tiling
. Single run per row.
Korean prompts cost nothing extra โ 45.3 s vs 46.4 s. Language is not a speed penalty here.
How it got 5.3ร faster
We started at 244 seconds and ended at 46. Every step is measured:
| Change | Time | Peak RAM |
|---|---|---|
| Default settings (20 steps) | 244 s | 8.16 GB |
| โ 4 steps | 62.1 s | 8.16 GB |
โ
--fa
(flash attention)
|
59.5 s | 8.18 GB |
| โ 3 steps | 48.6 s | 8.00 GB |
โ
--vae-tiling
|
46.4 s | 6.42 GB |
The big one is step count. Z-Image Turbo is distilled for few-step sampling, but the tool's default is 20. Using the default throws away 5ร for nothing.
3 steps is the floor. At 4 and 3 we cannot tell the images apart. At 2 the surface collapses โ water droplets and wood grain vanish and the texture turns cloth-like.
--vae-tiling
is free.
It cuts VAE time 16%
and
peak RAM by 1.27 GB. At 1024ร1024 it is the difference between 13.3 GB and 6.76 GB.
Do not use every thread you have. On a 32-core / 64-thread box, 48 threads took 59.5 s and 64 threads took 108.8 s โ 1.8ร slower. Hyper-threads fight each other for the same physical cores.
Files
| File | Size | What |
|---|---|---|
z_image_turbo-Q4_0-pocket.gguf
|
3.51 GB | Diffusion model, 4-bit (VIDRAFT CPU build) |
| (bring your own) Qwen3-4B-Instruct-2507-Q4_K_M | 2.58 GB | Text encoder โ download |
(bring your own)
ae.safetensors
|
0.16 GB | VAE โ download |
| Total | โ 6.25 GB |
The diffusion model here is VIDRAFT's own CPU build of Z-Image-Turbo: 3.51 GB, with no visible quality change.
Run it
Get a
stable-diffusion.cpp
binary (
releases
), then:
sd-cli \
--diffusion-model z_image_turbo-Q4_0-pocket.gguf \
--vae ae.safetensors \
--llm Qwen3-4B-Instruct-2507-Q4_K_M.gguf \
-p "a red apple on a wooden table, photorealistic" \
--cfg-scale 1.0 --steps 3 --fa --vae-tiling \
-t 8 -H 512 -W 512 -o out.png
Set
-t
to your physical core count โ
not
your thread count.
Honest limits
- It cannot render text. Any words inside the image come out garbled, in every language. If you need accurate text in an image, this is the wrong tool.
- Korean prompts lose count. "A red apple" gives one apple in English and five or six in Korean. Korean has no articles, so the singular signal is weak for the encoder. Reproduced at both 20 and 3 steps, so it is the encoder, not the step count.
- 1024 ร 1024 takes 3 minutes on the machine above. Slower CPUs scale accordingly.
- Measured on a server CPU. Laptop and mini-PC numbers are not in yet.
Credits and licensing
| Component | License | Author |
|---|---|---|
| Z-Image-Turbo (diffusion) | Apache-2.0 | Tongyi-MAI / Hangzhou Tongyi Laboratory |
| Qwen3-4B-Instruct (text encoder) | Apache-2.0 | Qwen, Alibaba |
| GGUF conversion (upstream) | Apache-2.0 | leejet |
| stable-diffusion.cpp (runtime) | MIT | leejet |
This repository redistributes a re-quantized copy of Z-Image-Turbo and keeps the original copyright notices. We did not train this model. What is ours is the CPU packaging, the 3-step setting, the re-quantization, and the measurements on this page.
Related
| Runs on | Strength | |
|---|---|---|
| POCKET-Image-Zimage | GPU (Python) | Faster, renders Korean text via glyph-init |
| POCKET-Zimage-CPU (this) | CPU only | No GPU, single binary |
Different jobs. Use the first if you have a graphics card, this one if you don't.
๐งฉ The POCKET Family โ On-device AI by VIDRAFT
Big models, small hardware. No GPU, no cloud.
Models
- ๐ฆ POCKET-35B-GGUF โ flagship, PC / server, no GPU
- ๐ฆ POCKET-26B-GGUF โ compact 26B
- ๐ฐ๐ท POCKET-KR-GGUF โ Korean, Android
- ๐ POCKET-KR-MLX โ Korean, iPhone / Mac
- ๐ POCKET-EN-GGUF โ English, phone / PC
- ๐ป POCKET-Qwen3.8-Flash-Next-GGUF โ 180B on a laptop (8 GB VRAM + 32 GB RAM)
- ๐ผ๏ธ POCKET-Image-Zimage โ character-perfect text in any image
- ๐ฅ๏ธ POCKET-Zimage-CPU โ photoreal images on a CPU only
Demos & tools (Spaces)
- ๐จ POCKET-Image Studio โ text-in-image, generate in-page
- ๐ฅ๏ธ POCKET-35B-CPU โ 35B answering on a CPU
- ๐ฅ๏ธ POCKET-26B-CPU โ 26B on a CPU
- ๐ผ๏ธ POCKET-Zimage-CPU โ image generation on a CPU
Runs of FINAL-Bench POCKET-Zimage-CPU on huggingface.co
2.0K
Total runs
571
24-hour runs
1.0K
3-day runs
1.4K
7-day runs
2.0K
30-day runs
More Information About POCKET-Zimage-CPU huggingface.co Model
Url of POCKET-Zimage-CPU
POCKET-Zimage-CPU huggingface.co Url
Provider of POCKET-Zimage-CPU huggingface.co
Other API from FINAL-Bench
Updated:September 25 2026
Total runs:
271.4K
Run Growth:
-61.7K
Growth Rate:
-22.74%
Total runs:
71.0K
Run Growth:
71.0K
Growth Rate:
100.00%
Total runs:
3.6K
Run Growth:
3.5K
Growth Rate:
98.04%
Total runs:
2.5K
Run Growth:
2.5K
Growth Rate:
100.00%
Total runs:
2.2K
Run Growth:
1.9K
Growth Rate:
86.96%
Total runs:
1.5K
Run Growth:
1.4K
Growth Rate:
97.81%
Total runs:
1.4K
Run Growth:
1.4K
Growth Rate:
100.00%
Total runs:
1.0K
Run Growth:
1.0K
Growth Rate:
100.00%
Total runs:
995
Run Growth:
605
Growth Rate:
60.80%
Total runs:
971
Run Growth:
-78
Growth Rate:
-8.03%
Total runs:
912
Run Growth:
497
Growth Rate:
54.50%
Total runs:
806
Run Growth:
535
Growth Rate:
66.38%
Total runs:
600
Run Growth:
-122
Growth Rate:
-20.33%
Total runs:
491
Run Growth:
322
Growth Rate:
65.58%
Total runs:
471
Run Growth:
465
Growth Rate:
98.73%
Total runs:
432
Run Growth:
432
Growth Rate:
100.00%
Total runs:
428
Run Growth:
428
Growth Rate:
100.00%
Total runs:
401
Run Growth:
239
Growth Rate:
59.60%
Total runs:
385
Run Growth:
49
Growth Rate:
12.73%
Total runs:
377
Run Growth:
355
Growth Rate:
94.16%
Total runs:
346
Run Growth:
260
Growth Rate:
75.14%
Total runs:
319
Run Growth:
102
Growth Rate:
31.97%
Total runs:
305
Run Growth:
60
Growth Rate:
19.67%
Total runs:
258
Run Growth:
-55
Growth Rate:
-21.32%
Total runs:
253
Run Growth:
253
Growth Rate:
100.00%
Total runs:
191
Run Growth:
191
Growth Rate:
100.00%
Total runs:
178
Run Growth:
-8
Growth Rate:
-4.49%
Total runs:
162
Run Growth:
89
Growth Rate:
54.94%
Total runs:
161
Run Growth:
-50
Growth Rate:
-31.06%
Total runs:
154
Run Growth:
-24
Growth Rate:
-15.58%
Total runs:
153
Run Growth:
-82
Growth Rate:
-53.59%
Total runs:
133
Run Growth:
57
Growth Rate:
42.86%
Total runs:
127
Run Growth:
114
Growth Rate:
89.76%
Total runs:
118
Run Growth:
73
Growth Rate:
61.86%
Total runs:
107
Run Growth:
107
Growth Rate:
100.00%
Total runs:
89
Run Growth:
73
Growth Rate:
82.02%
Total runs:
72
Run Growth:
-180
Growth Rate:
-250.00%
Total runs:
67
Run Growth:
14
Growth Rate:
20.90%
Total runs:
63
Run Growth:
37
Growth Rate:
58.73%
Total runs:
61
Run Growth:
61
Growth Rate:
100.00%
Total runs:
60
Run Growth:
60
Growth Rate:
100.00%
Total runs:
60
Run Growth:
17
Growth Rate:
28.33%
Total runs:
52
Run Growth:
52
Growth Rate:
100.00%
Total runs:
52
Run Growth:
52
Growth Rate:
100.00%
Total runs:
51
Run Growth:
51
Growth Rate:
100.00%
Total runs:
50
Run Growth:
50
Growth Rate:
100.00%
Total runs:
48
Run Growth:
48
Growth Rate:
100.00%
Total runs:
47
Run Growth:
16
Growth Rate:
34.04%
Total runs:
46
Run Growth:
46
Growth Rate:
100.00%
Total runs:
46
Run Growth:
46
Growth Rate:
100.00%
Total runs:
43
Run Growth:
43
Growth Rate:
100.00%
Total runs:
40
Run Growth:
40
Growth Rate:
100.00%
Total runs:
31
Run Growth:
22
Growth Rate:
70.97%
Total runs:
13
Run Growth:
6
Growth Rate:
46.15%
Total runs:
0
Run Growth:
0
Growth Rate:
0.00%
Total runs:
0
Run Growth:
0
Growth Rate:
0.00%
Total runs:
0
Run Growth:
0
Growth Rate:
0.00%
Total runs:
0
Run Growth:
0
Growth Rate:
0.00%
Total runs:
0
Run Growth:
0
Growth Rate:
0.00%
Total runs:
0
Run Growth:
0
Growth Rate:
0.00%