Instructions to use OrionLLM/Terminus-Qwen3-8b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use OrionLLM/Terminus-Qwen3-8b with Transformers:

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

pipe = pipeline("text-generation", model="OrionLLM/Terminus-Qwen3-8b")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("OrionLLM/Terminus-Qwen3-8b")
model = AutoModelForCausalLM.from_pretrained("OrionLLM/Terminus-Qwen3-8b")
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
Local Apps Settings

vLLM

How to use OrionLLM/Terminus-Qwen3-8b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "OrionLLM/Terminus-Qwen3-8b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "OrionLLM/Terminus-Qwen3-8b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/OrionLLM/Terminus-Qwen3-8b

SGLang

How to use OrionLLM/Terminus-Qwen3-8b 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 "OrionLLM/Terminus-Qwen3-8b" \
    --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": "OrionLLM/Terminus-Qwen3-8b",
		"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 "OrionLLM/Terminus-Qwen3-8b" \
        --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": "OrionLLM/Terminus-Qwen3-8b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use OrionLLM/Terminus-Qwen3-8b with Docker Model Runner:
```
docker model run hf.co/OrionLLM/Terminus-Qwen3-8b
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Terminus

Terminus Tumb

Terminus is a model trained for terminal agentic tasks such as Terminal-Bench 2.0 and SWE-Bench, and also be efficient for use and localization with environments such as Codex and OpenCode. It was trained on the dataset:

OrionLLM/OpenAgentInstruct

Terminus was designed to improve performance in terminal-based reasoning workflows, software engineering, and tool usage over other models.

Benchmarks

Model	Harness	Terminal-Bench 2.0	SWE-Bench Verified
Qwen3-8B	Terminus-2	0.0	0.7
Terminus-Qwen3-8b	Terminus-2	4.9	15.7
Qwen3-32B	Terminus-2	1.9	5.7
Qwen/Qwen3-Coder-30B-A3B-Instruct	OpenHands	10.1	49.2

Terminus-Qwen3-8b is an open-source effort focused on building stronger agentic models through better datasets, practical training, and real benchmark evaluation.