Quality
Quality · LMArena · text-to-image
LMArena 2026-10-07 · human-preference rating · higher is better · this model outlined
- Color = publisher
Source: LMArena 2026-10-07 · collected 2026-10-25 · dataset · CC BY 4.0 · models without a rating are not drawn (no rating ≠ 0)
1,012 ± 9 · LMArena · text-to-image · Confidence interval 1,003–1,021 · 4,854 votes
Artificial Analysis is excluded: its free tier is internal use only.
Reported by the publisher
- CVTG-2K · Word Accuracy
- 0.912Text Rendering
- CVTG-2K · NED
- 0.956Text Rendering
- CVTG-2K · CLIPScore
- 0.788Text Rendering
- LongText-Bench · AVG
- 0.966Text Rendering
- LongText-Bench · EN
- 0.952Text Rendering
- LongText-Bench · ZH
- 0.979Text Rendering
- OneIG-Bench · EN
- 0.528Text-to-Image
- OneIG-Bench · ZH
- 0.511Text-to-Image
Every reported result
Values as printed on the card, with the publisher's own settings (card section: Model Performance › Text Rendering; Model Performance › Text-to-Image); column “GLM-Image”. Not comparable across publishers and not used in any ranking. Model card
Quality × memory
No comparable quality × memory pair
Image, video and audio models have no shared quality scale, and their memory comes from the publisher's documented minimum path, so quality is not charted against memory.
Consider GLM-Image from Z AI for the text-to-image task (16B parameters).
The catalog lists the publisher's documented memory path under Runs on and has not reviewed other configurations. Actual memory depends on precision, resolution, duration and offload; consult the official source.
Runs on
Enough memory 22
A publisher documents a path within this memory, on this platform (CUDA or Apple MPS). Conditional paths need offload or quantization.
Show all 22
One memory tier short 16
The same machines with the next memory size up would have enough.
Show all 16
Hardware profiles grouped by the publisher's documented minimum memory path and platform. Not a measured run.
Measured speed
No published measurement for this checkpoint
Generation time per image is shown only when a source publishes it with hardware, build and setup. It is never estimated.
How to run
Publisher-documented memory path: Official CPU-offload path. Actual memory depends on precision, resolution, duration and offload; consult the official source. Official hardware evidence
Documented ways to run it
Copied as printed in the linked source (read 2026-10-18); not run by this site.
pip install git+https://github.com/huggingface/transformers.git
pip install git+https://github.com/huggingface/diffusers.gitimport torch
from diffusers.pipelines.glm_image import GlmImagePipeline
pipe = GlmImagePipeline.from_pretrained("zai-org/GLM-Image", torch_dtype=torch.bfloat16, device_map="cuda")
prompt = "A beautifully designed modern food magazine style dessert recipe illustration, themed around a raspberry mousse cake. The overall layout is clean and bright, divided into four main areas: the top left features a bold black title 'Raspberry Mousse Cake Recipe Guide', with a soft-lit close-up photo of the finished cake on the right, showcasing a light pink cake adorned with fresh raspberries and mint leaves; the bottom left contains an ingredient list section, titled 'Ingredients' in a simple font, listing 'Flour 150g', 'Eggs 3', 'Sugar 120g', 'Raspberry puree 200g', 'Gelatin sheets 10g', 'Whipping cream 300ml', and 'Fresh raspberries', each accompanied by minimalist line icons (like a flour bag, eggs, sugar jar, etc.); the bottom right displays four equally sized step boxes, each containing high-definition macro photos and corresponding instructions, arranged from top to bottom as follows: Step 1 shows a whisk whipping white foam (with the instruction 'Whip egg whites to stiff peaks'), Step 2 shows a red-and-white mixture being folded with a spatula (with the instruction 'Gently fold in the puree and batter'), Step 3 shows pink liquid being poured into a round mold (with the instruction 'Pour into mold and chill for 4 hours'), Step 4 shows the finished cake decorated with raspberries and mint leaves (with the instruction 'Decorate with raspberries and mint'); a light brown information bar runs along the bottom edge, with icons on the left representing 'Preparation time: 30 minutes', 'Cooking time: 20 minutes', and 'Servings: 8'. The overall color scheme is dominated by creamy white and light pink, with a subtle paper texture in the background, featuring compact and orderly text and image layout with clear information hierarchy."
image = pipe(
prompt=prompt,
height=32 * 32,
width=36 * 32,
num_inference_steps=50,
guidance_scale=1.5,
generator=torch.Generator(device="cuda").manual_seed(42),
).images[0]
image.save("output_t2i.png")pip install "sglang[diffusion] @ git+https://github.com/sgl-project/sglang.git#subdirectory=python"
pip install git+https://github.com/huggingface/transformers.git
pip install git+https://github.com/huggingface/diffusers.gitsglang serve --model-path zai-org/GLM-Image
curl http://localhost:30000/v1/images/generations \
-H "Content-Type: application/json" \
-d '{
"model": "zai-org/GLM-Image",
"prompt": "a beautiful girl with glasses.",
"n": 1,
"response_format": "b64_json",
"size": "1024x1024"
}' | python3 -c "import sys, json, base64; open('output_t2i.png', 'wb').write(base64.b64decode(json.load(sys.stdin)['data'][0]['b64_json']))"Evidence level: Publisher documentation linked; no execution reproduced by this site.
Before downloading
- Check the exact checkpoint and license linked here.
- Confirm a compatible runtime and precision or quantization for your platform.
- Allow for context, batch size and any extra media components beyond the weights.
Technical details
What the source and the catalog store for this checkpoint. Missing fields are left out, never zero.
- Checkpoint / version
- zai-org/GLM-Image
- Task and modality
- text-to-image · image
- Count and basis
- 16B · sum of published parts
- Released
- zai-org/GLM-Image commit history (GitHub), commit d2c8289 "Update README.md" adding the Download table (Hugging Face zai-org/GLM-Image, ModelScope) · read 2026-10-19source
- Published repository size
- 35.8 GBNot runtime memory or a minimum download.files
- Published components
- Technical details pending review
- Runtime and precision
- No local execution verified.
- Commercial use
- Allowed MIT license text (SPDX) · read 2026-10-18license text
Every stored field
- Revision checked
- 2c433cc0cbc293bde2ac8ca9624f279b5d23fcf4
- Library
- diffusers
- Hub task tag
- text-to-image
- Formats
- safetensors
- Repository created
- 2026-01-08creation is not the model's release
- Repository updated
- 2026-01-15a commit is not a release date
- Hub downloads (30 days) · likes
- 4,997 · 1,124this repository only · read 2026-10-25
- Read from the Hub page
- task, task tags, file formatsHub overview and file listing · read 2026-10-18
- Catalog state
- Hub config or weights found; no inventory benchmark link
License, parameter count and release date come from the publisher's sources listed on this page (a date no source states is left empty). The hardware requirement has not been reviewed, so memory is a labelled estimate. The repository size, when shown, is the full published download.
Sources
Identity and published specifications come from the checkpoint page. Benchmark scores belong to the named release and do not measure speed on your computer.
- Publisher checkpoint and model card
- Weight license and use terms
- Quality benchmark source · Artificial Analysis image · excluded (free tier is internal use only)
- Publisher hardware documentation
Catalog reviewed: 2026-09-22.






























