Instructions to use zai-org/GLM-5.3-Flash with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use zai-org/GLM-5.3-Flash with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="zai-org/GLM-5.3-Flash")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("zai-org/GLM-5.3-Flash")
model = AutoModelForMultimodalLM.from_pretrained("zai-org/GLM-5.3-Flash", device_map="auto")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Inference
HuggingChat
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use zai-org/GLM-5.3-Flash with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "zai-org/GLM-5.3-Flash"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "zai-org/GLM-5.3-Flash",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/zai-org/GLM-5.3-Flash

SGLang

How to use zai-org/GLM-5.3-Flash with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "zai-org/GLM-5.3-Flash" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "zai-org/GLM-5.3-Flash",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "zai-org/GLM-5.3-Flash" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "zai-org/GLM-5.3-Flash",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use zai-org/GLM-5.3-Flash with Docker Model Runner:
```
docker model run hf.co/zai-org/GLM-5.3-Flash
```

SaylorTwift HF Staff commited on about 22 hours ago

Commit

2d894c6

verified ·

1 Parent(s): 84c6a6a

Add evaluation results

Browse files

# PR Description: Add Evaluation Results for zai-org/GLM-5.3-Flash

## Summary

This PR adds evaluation results extracted from the model card's benchmark graph for `zai-org/GLM-5.3-Flash` to the `.eval_results/` directory, following the [Hugging Face Hub evaluation-results specification](https://huggingface.co/docs/hub/eval-results).

## Benchmarks Added

- [Terminal-Bench 2.1](https://huggingface.co/datasets/harborframework/terminal-bench-2.1?eval_result=zai-org/GLM-5.3-Flash&leaderboard_task_id=terminalbench_2_1) — 84.3
- [DeepSWE](https://huggingface.co/datasets/datacurve/deep-swe?eval_result=zai-org/GLM-5.3-Flash&leaderboard_task_id=deep_swe) — 63.4
- [Humanity's Last Exam](https://huggingface.co/datasets/cais/hle?eval_result=zai-org/GLM-5.3-Flash&leaderboard_task_id=hle) — 55.3

## Benchmarks Skipped (Not Registered on Hub)

The following benchmarks were present in the model card but could not be added because they do not have a registered `eval.yaml` on the Hugging Face Hub:

- **Agent's Last Exam**: 26.3 — no registered `eval.yaml` found on the Hub.
- **AutomationBench v1.0.6**: 48.8 — no registered `eval.yaml` found on the Hub.
- **GDPval-AA v2**: 1773 — no registered `eval.yaml` found on the Hub.

These can be added once the benchmark authors register their `eval.yaml` on the Hub.

## Source

- Model card: https://huggingface.co/zai-org/GLM-5.3-Flash
- Note: the model card cites `arxiv:2602.15763` as "the GLM-5 Technical report", but that paper (published Feb 2026) is the original GLM-5 report and predates this model — it does not contain GLM-5.3-Flash-specific numbers, so it wasn't used as a source.

## Files Added

- `.eval_results/GLM-5.3-Flash.yaml`

## Verification

These results were extracted from the model card's published benchmark chart (`bench_53.png`, an image embedded in the README, read visually — the announcement blog is a client-rendered SPA and wasn't fetchable). No verified token is provided as these were not run via HF Jobs with inspect-ai.

---

**To upload this file to the Hub, run:**

```bash
hf upload zai-org/GLM-5.3-Flash --type model --include .eval_results/*.yaml --commit-message "Add evaluation results"
```

Files changed (1) hide show

.eval_results/GLM-5.3-Flash.yaml +28 -0

.eval_results/GLM-5.3-Flash.yaml ADDED Viewed

	@@ -0,0 +1,28 @@

+- dataset:
+    id: harborframework/terminal-bench-2.1
+    task_id: terminalbench_2_1
+  value: 84.3
+  date: "2026-08-26"
+  source:
+    url: https://huggingface.co/zai-org/GLM-5.3-Flash
+    name: "GLM-5.3-Flash model card"
+- dataset:
+    id: datacurve/deep-swe
+    task_id: deep_swe
+  value: 63.4
+  date: "2026-08-26"
+  source:
+    url: https://huggingface.co/zai-org/GLM-5.3-Flash
+    name: "GLM-5.3-Flash model card"
+  notes: "Reported as DeepSWE v1.1 on the model card, run via the mini-swe-agent harness with 400K context."
+- dataset:
+    id: cais/hle
+    task_id: hle
+  value: 55.3
+  date: "2026-08-26"
+  source:
+    url: https://huggingface.co/zai-org/GLM-5.3-Flash
+    name: "GLM-5.3-Flash model card"
+  notes: "HLE with tools (full set) and a 300K-context management strategy, not the no-tools default; judged by GPT-5.6-luna (medium)."