Instructions to use Lite-Coder/LiteCoder-Terminal-4b-sft with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Lite-Coder/LiteCoder-Terminal-4b-sft with Transformers:

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

pipe = pipeline("text-generation", model="Lite-Coder/LiteCoder-Terminal-4b-sft")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Lite-Coder/LiteCoder-Terminal-4b-sft")
model = AutoModelForCausalLM.from_pretrained("Lite-Coder/LiteCoder-Terminal-4b-sft")
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]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Lite-Coder/LiteCoder-Terminal-4b-sft with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Lite-Coder/LiteCoder-Terminal-4b-sft"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Lite-Coder/LiteCoder-Terminal-4b-sft",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Lite-Coder/LiteCoder-Terminal-4b-sft

SGLang

How to use Lite-Coder/LiteCoder-Terminal-4b-sft 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 "Lite-Coder/LiteCoder-Terminal-4b-sft" \
    --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": "Lite-Coder/LiteCoder-Terminal-4b-sft",
		"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 "Lite-Coder/LiteCoder-Terminal-4b-sft" \
        --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": "Lite-Coder/LiteCoder-Terminal-4b-sft",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Lite-Coder/LiteCoder-Terminal-4b-sft with Docker Model Runner:
```
docker model run hf.co/Lite-Coder/LiteCoder-Terminal-4b-sft
```

LiteCoder-Terminal-4b-sft / README.md

nielsr HF Staff

Add library_name, pipeline_tag and links to paper and code

fe04a0c verified 9 days ago

preview code

raw

history blame

4.05 kB

	---
	base_model:
	- Qwen/Qwen3-4B-Instruct-2507
	license: mit
	library_name: transformers
	pipeline_tag: text-generation
	---

	## LiteCoder-Terminal-4b-sft

	LiteCoder-Terminal-4b-sft is part of our latest release on lightweight code agents. The model is fine-tuned from `Qwen3-4B-Instruct-2507` on the [LiteCoder-Terminal-SFT](https://huggingface.co/datasets/Lite-Coder/LiteCoder-Terminal-SFT) dataset.

	This model was introduced in the paper [LiteCoder-Terminal: Scaling Long-Horizon Terminal Environments for Learning Language Agents](https://huggingface.co/papers/2605.29559).

	Code: [https://github.com/icip-cas/LiteCoder](https://github.com/icip-cas/LiteCoder)

	Compared to our previous preview version, we scaled up the training data from under 1,000 samples to 11,255 trajectories, incorporating a broader task taxonomy and diverse agent scaffolds. With these updates, the model shows consistent improvements across Terminal Bench evaluations.

	## Released Artifacts

	\| 2026/04/13 \| \| \|
	\| --- \| --- \| --- \|
	\| LiteCoder-Terminal-30b-a3b-sft \| Model \| [https://huggingface.co/Lite-Coder/LiteCoder-Terminal-30b-a3b-sft](https://huggingface.co/Lite-Coder/LiteCoder-Terminal-30b-a3b-sft) \|
	\| LiteCoder-Terminal-4b-sft \| Model \| [https://huggingface.co/Lite-Coder/LiteCoder-Terminal-4b-sft](https://huggingface.co/Lite-Coder/LiteCoder-Terminal-4b-sft) \|
	\| LiteCoder-Terminal-SFT \| Dataset \| [https://huggingface.co/datasets/Lite-Coder/LiteCoder-Terminal-SFT](https://huggingface.co/datasets/Lite-Coder/LiteCoder-Terminal-SFT/settings) \|
	\| LiteCoder-Terminal-World-Model-SFT \| Dataset \| [https://huggingface.co/datasets/Lite-Coder/LiteCoder-Terminal-World-Model-SFT](https://huggingface.co/datasets/Lite-Coder/LiteCoder-Terminal-World-Model-SFT) \|
	\| LiteCoder-Terminal-RL-preview \| Dataset \| [https://huggingface.co/datasets/Lite-Coder/LiteCoder-Terminal-RL-preview](https://huggingface.co/datasets/Lite-Coder/LiteCoder-Terminal-RL-preview/tree/main) \|

	## Results

	### Terminal Bench 1.0 Performance

	\| Model \| Agent \| pass@1 \| pass@4 \|
	\| --- \| --- \| --- \| --- \|
	\| LiteCoder-Terminal-30b-a3b-sft \| Terminus 2 \| 24.38% \| 40% \|
	\| Qwen3-30B-A3B-Nex-N1 \| Openhands \| 18.44% \| 32.5% \|
	\| LiteCoder-30a3b-Terminal-preview \| Terminus 2 \| 16.56% \| 27.5% \|
	\| Qwen3-30B-A3B-Instruct \| Terminus 2 \| 16.56% \| 28.75% \|
	\| LiteCoder-Terminal-4b-sft \| Terminus 2 \| 13.44% \| 30% \|
	\| OpenThinker-Agent-v1 \| Terminus 2 \| 11.25% \| 25% \|
	\| LiteCoder-4b-Terminal-preview \| Terminus 2 \| 9.38% \| 20% \|
	\| Qwen3-4B-Instruct \| Terminus 2 \| 6.25% \| 15% \|

	### Terminal Bench 2.0 Performance

	\| Model \| Agent \| pass@1 \| pass@4 \|
	\| --- \| --- \| --- \| --- \|
	\| LiteCoder-Terminal-30b-a3b-sft \| Terminus 2 \| 12.36% \| 23.60% \|
	\| Qwen3-30B-A3B-Nex-N1 \| Openhands \| 12.36% \| 23.60% \|
	\| LiteCoder-30a3b-Terminal-preview \| Terminus 2 \| 6.18% \| 13.75% \|
	\| LiteCoder-Terminal-4b-sft \| Terminus 2 \| 5.62% \| 12.36% \|
	\| Qwen3-30B-A3B-Instruct \| Terminus 2 \| 5.34% \| 11.24% \|
	\| OpenThinker-Agent-v1 \| Terminus 2 \| 4.49% \| 10.1% \|
	\| LiteCoder-4b-Terminal-preview \| Terminus 2 \| 4.78% \| 12.36% \|
	\| Qwen3-4B-Instruct \| Terminus 2 \| 1.12% \| 3.37% \|

	### Terminal Bench Pro Performance

	\| Model \| Agent \| pass@1 \|
	\| --- \| --- \| --- \|
	\| LiteCoder-Terminal-30b-a3b-sft \| Terminus 2 \| 31.5% \|
	\| LiteCoder-30a3b-Terminal-preview \| Terminus 2 \| 22.0% \|
	\| Qwen3-30B-A3B-Nex-N1 \| Openhands \| 21.0% \|
	\| Qwen3-30B-A3B-Instruct \| Terminus 2 \| 20.5% \|
	\| OpenThinker-Agent-v1 \| Terminus 2 \| 19.5% \|
	\| LiteCoder-Terminal-4b-sft \| Terminus 2 \| 15.5% \|
	\| LiteCoder-4b-Terminal-preview \| Terminus 2 \| 15.0% \|
	\| Qwen3-4B-Instruct \| Terminus 2 \| 3.5% \|

	## Citation

	```bash
	@article{peng2026litecoderterminal,
	title={LiteCoder-Terminal: Scaling Long-Horizon Terminal Environments for Learning Language Agents},
	author={Peng, Xiaoxuan and Zhang, Kaiqi and Lu, Xinyu and Cao, Boxi and Lu, Yaojie and Lin, Hongyu and Han, Xianpei and Sun, Le},
	journal={arXiv preprint arXiv:2605.29559},
	year={2026}
	}
	```

	---
	base_model:
	- Qwen/Qwen3-4B-Instruct-2507
	license: mit
	library_name: transformers
	pipeline_tag: text-generation
	---

	## LiteCoder-Terminal-4b-sft

	LiteCoder-Terminal-4b-sft is part of our latest release on lightweight code agents. The model is fine-tuned from `Qwen3-4B-Instruct-2507` on the [LiteCoder-Terminal-SFT](https://huggingface.co/datasets/Lite-Coder/LiteCoder-Terminal-SFT) dataset.

	This model was introduced in the paper [LiteCoder-Terminal: Scaling Long-Horizon Terminal Environments for Learning Language Agents](https://huggingface.co/papers/2605.29559).

	Code: [https://github.com/icip-cas/LiteCoder](https://github.com/icip-cas/LiteCoder)

	Compared to our previous preview version, we scaled up the training data from under 1,000 samples to 11,255 trajectories, incorporating a broader task taxonomy and diverse agent scaffolds. With these updates, the model shows consistent improvements across Terminal Bench evaluations.

	## Released Artifacts

	\| 2026/04/13 \| \| \|
	\| --- \| --- \| --- \|
	\| LiteCoder-Terminal-30b-a3b-sft \| Model \| [https://huggingface.co/Lite-Coder/LiteCoder-Terminal-30b-a3b-sft](https://huggingface.co/Lite-Coder/LiteCoder-Terminal-30b-a3b-sft) \|
	\| LiteCoder-Terminal-4b-sft \| Model \| [https://huggingface.co/Lite-Coder/LiteCoder-Terminal-4b-sft](https://huggingface.co/Lite-Coder/LiteCoder-Terminal-4b-sft) \|
	\| LiteCoder-Terminal-SFT \| Dataset \| [https://huggingface.co/datasets/Lite-Coder/LiteCoder-Terminal-SFT](https://huggingface.co/datasets/Lite-Coder/LiteCoder-Terminal-SFT/settings) \|
	\| LiteCoder-Terminal-World-Model-SFT \| Dataset \| [https://huggingface.co/datasets/Lite-Coder/LiteCoder-Terminal-World-Model-SFT](https://huggingface.co/datasets/Lite-Coder/LiteCoder-Terminal-World-Model-SFT) \|
	\| LiteCoder-Terminal-RL-preview \| Dataset \| [https://huggingface.co/datasets/Lite-Coder/LiteCoder-Terminal-RL-preview](https://huggingface.co/datasets/Lite-Coder/LiteCoder-Terminal-RL-preview/tree/main) \|

	## Results

	### Terminal Bench 1.0 Performance

	\| Model \| Agent \| pass@1 \| pass@4 \|
	\| --- \| --- \| --- \| --- \|
	\| LiteCoder-Terminal-30b-a3b-sft \| Terminus 2 \| 24.38% \| 40% \|
	\| Qwen3-30B-A3B-Nex-N1 \| Openhands \| 18.44% \| 32.5% \|
	\| LiteCoder-30a3b-Terminal-preview \| Terminus 2 \| 16.56% \| 27.5% \|
	\| Qwen3-30B-A3B-Instruct \| Terminus 2 \| 16.56% \| 28.75% \|
	\| LiteCoder-Terminal-4b-sft \| Terminus 2 \| 13.44% \| 30% \|
	\| OpenThinker-Agent-v1 \| Terminus 2 \| 11.25% \| 25% \|
	\| LiteCoder-4b-Terminal-preview \| Terminus 2 \| 9.38% \| 20% \|
	\| Qwen3-4B-Instruct \| Terminus 2 \| 6.25% \| 15% \|

	### Terminal Bench 2.0 Performance

	\| Model \| Agent \| pass@1 \| pass@4 \|
	\| --- \| --- \| --- \| --- \|
	\| LiteCoder-Terminal-30b-a3b-sft \| Terminus 2 \| 12.36% \| 23.60% \|
	\| Qwen3-30B-A3B-Nex-N1 \| Openhands \| 12.36% \| 23.60% \|
	\| LiteCoder-30a3b-Terminal-preview \| Terminus 2 \| 6.18% \| 13.75% \|
	\| LiteCoder-Terminal-4b-sft \| Terminus 2 \| 5.62% \| 12.36% \|
	\| Qwen3-30B-A3B-Instruct \| Terminus 2 \| 5.34% \| 11.24% \|
	\| OpenThinker-Agent-v1 \| Terminus 2 \| 4.49% \| 10.1% \|
	\| LiteCoder-4b-Terminal-preview \| Terminus 2 \| 4.78% \| 12.36% \|
	\| Qwen3-4B-Instruct \| Terminus 2 \| 1.12% \| 3.37% \|

	### Terminal Bench Pro Performance

	\| Model \| Agent \| pass@1 \|
	\| --- \| --- \| --- \|
	\| LiteCoder-Terminal-30b-a3b-sft \| Terminus 2 \| 31.5% \|
	\| LiteCoder-30a3b-Terminal-preview \| Terminus 2 \| 22.0% \|
	\| Qwen3-30B-A3B-Nex-N1 \| Openhands \| 21.0% \|
	\| Qwen3-30B-A3B-Instruct \| Terminus 2 \| 20.5% \|
	\| OpenThinker-Agent-v1 \| Terminus 2 \| 19.5% \|
	\| LiteCoder-Terminal-4b-sft \| Terminus 2 \| 15.5% \|
	\| LiteCoder-4b-Terminal-preview \| Terminus 2 \| 15.0% \|
	\| Qwen3-4B-Instruct \| Terminus 2 \| 3.5% \|

	## Citation

	```bash
	@article{peng2026litecoderterminal,
	title={LiteCoder-Terminal: Scaling Long-Horizon Terminal Environments for Learning Language Agents},
	author={Peng, Xiaoxuan and Zhang, Kaiqi and Lu, Xinyu and Cao, Boxi and Lu, Yaojie and Lin, Hongyu and Han, Xianpei and Sun, Le},
	journal={arXiv preprint arXiv:2605.29559},
	year={2026}
	}
	```