Instructions to use zai-org/GLM-5.2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use zai-org/GLM-5.2 with Transformers:

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

pipe = pipeline("text-generation", model="zai-org/GLM-5.2")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("zai-org/GLM-5.2")
model = AutoModelForCausalLM.from_pretrained("zai-org/GLM-5.2", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.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(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Inference
HuggingChat
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use zai-org/GLM-5.2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "zai-org/GLM-5.2"
# 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-5.2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/zai-org/GLM-5.2

SGLang

How to use zai-org/GLM-5.2 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-5.2" \
    --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-5.2",
		"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-5.2" \
        --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-5.2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use zai-org/GLM-5.2 with Docker Model Runner:
```
docker model run hf.co/zai-org/GLM-5.2
```

SaylorTwift HF Staff commited on 5 days ago

Commit

ae51853

verified ·

1 Parent(s): b4734de

Add Terminal-Bench 2.1 evaluation results

Browse files

# Add Evaluation Results for zai-org/GLM-5.2

## Summary

This PR adds two Terminal-Bench 2.1 evaluation results extracted from the model card
benchmark table for `zai-org/GLM-5.2` to the `.eval_results/` directory, following the
[Hugging Face Hub evaluation-results specification](https://huggingface.co/docs/hub/eval-results).
The model card reports Terminal-Bench 2.1 under two different harnesses, so both are
recorded against the same `terminalbench_2_1` task, distinguished via `notes`.

## Benchmarks Added

- [Terminal Bench 2.1](https://huggingface.co/datasets/harborframework/terminal-bench-2.1?eval_result=zai-org/GLM-5.2&leaderboard_task_id=terminalbench_2_1) — 81.0 (Terminus-2 harness)
- [Terminal Bench 2.1](https://huggingface.co/datasets/harborframework/terminal-bench-2.1?eval_result=zai-org/GLM-5.2&leaderboard_task_id=terminalbench_2_1) — 82.7 (Best reported harness: Claude Code 2.1.167)

## Benchmarks Skipped (Not Registered on Hub)

Not applicable — only Terminal-Bench 2.1 was requested for this PR.

## Source

- Model card: https://huggingface.co/zai-org/GLM-5.2
- Paper: https://arxiv.org/abs/2602.15763

## Files Added

- `.eval_results/terminal-bench-2.1.yaml`

## Verification

This result was extracted from the model card's published benchmark table (row
"Terminal Bench 2.1 (Terminus-2)"), not from independently re-run/verified eval logs.

Files changed (1) hide show

.eval_results/terminal-bench-2.1.yaml +18 -0

.eval_results/terminal-bench-2.1.yaml ADDED Viewed

	@@ -0,0 +1,18 @@

+- dataset:
+    id: harborframework/terminal-bench-2.1
+    task_id: terminalbench_2_1
+  value: 81.0
+  date: "2026-07-02"
+  source:
+    url: https://huggingface.co/zai-org/GLM-5.2
+    name: Model Card
+  notes: "Terminus-2 harness (temperature=1.0, top_p=1.0, 256K context, max_episodes=500)."
+- dataset:
+    id: harborframework/terminal-bench-2.1
+    task_id: terminalbench_2_1
+  value: 82.7
+  date: "2026-07-02"
+  source:
+    url: https://huggingface.co/zai-org/GLM-5.2
+    name: Model Card
+  notes: "Best reported harness: Claude Code 2.1.167 (temperature=1.0, top_p=0.95, max_new_tokens=131072, no wall-clock limit, averaged over 5 runs)."