Instructions to use eewer/OpenThinkerAgent-32B-AWQ-Int4-Terminus2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use eewer/OpenThinkerAgent-32B-AWQ-Int4-Terminus2 with Transformers:

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

pipe = pipeline("text-generation", model="eewer/OpenThinkerAgent-32B-AWQ-Int4-Terminus2")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("eewer/OpenThinkerAgent-32B-AWQ-Int4-Terminus2")
model = AutoModelForCausalLM.from_pretrained("eewer/OpenThinkerAgent-32B-AWQ-Int4-Terminus2", 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]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use eewer/OpenThinkerAgent-32B-AWQ-Int4-Terminus2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "eewer/OpenThinkerAgent-32B-AWQ-Int4-Terminus2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "eewer/OpenThinkerAgent-32B-AWQ-Int4-Terminus2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/eewer/OpenThinkerAgent-32B-AWQ-Int4-Terminus2

SGLang

How to use eewer/OpenThinkerAgent-32B-AWQ-Int4-Terminus2 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 "eewer/OpenThinkerAgent-32B-AWQ-Int4-Terminus2" \
    --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": "eewer/OpenThinkerAgent-32B-AWQ-Int4-Terminus2",
		"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 "eewer/OpenThinkerAgent-32B-AWQ-Int4-Terminus2" \
        --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": "eewer/OpenThinkerAgent-32B-AWQ-Int4-Terminus2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use eewer/OpenThinkerAgent-32B-AWQ-Int4-Terminus2 with Docker Model Runner:
```
docker model run hf.co/eewer/OpenThinkerAgent-32B-AWQ-Int4-Terminus2
```

OpenThinkerAgent-32B-AWQ-Int4-Terminus2

File size: 1,752 Bytes

f1f1905

---

base_model: open-thoughts/OpenThinkerAgent-32B
model_name: eewer/OpenThinkerAgent-32B-AWQ-Int4-Terminus2
library_name: transformers
pipeline_tag: text-generation
tags:
- qwen3
- openthinker-agent
- awq
- 4-bit
- areal-teacher
---

# OpenThinkerAgent-32B AWQ Int4

This repository contains an AWQ quantized checkpoint of
`open-thoughts/OpenThinkerAgent-32B` prepared for OPD/KDRL teacher-logprob use in AReaL.

## Quantization

- Source model: `open-thoughts/OpenThinkerAgent-32B`
- Source revision: `65d8a62b87c8d3d34bc45108a7ad87635318db9f`
- Dataset: `/wbl-fast/usrs/ee/clean-20260619/terminal-agent-rl/areal_runs/terminal-agent-demo/data/skill_based_medium.even.terminus2.slime_messages.jsonl`
- Calibration samples: 128
- Calibration seed: 7
- Max calibration token window per sample: 2048
- AutoAWQ `max_calib_seq_len`: 2048
- AutoAWQ `n_parallel_calib_samples`: 1
- AutoAWQ `max_chunk_memory`: 256 MiB
- Quantization: W4A16, group size 128, zero point True, version `GEMM`
- Modules left unquantized: `lm_head`
- `duo_scaling`: True
- `apply_clip`: True
- Torch: `2.11.0+cu128`
- CUDA: `12.8`
- AutoAWQ: `0.2.9`
- Started: `2026-06-24T22:09:24.999975+00:00`
- Finished: `2026-06-25T01:31:16.596143+00:00`
- Elapsed seconds: `12111.596`

Calibration text is rendered from the Terminus-2 medium SFT messages with the
Qwen3 chat template and `enable_thinking=True`, so thinking spans are preserved.
The quantization keeps `lm_head` unquantized for quality.

## AReaL Teacher Config

```yaml
teacher:
  path: <this checkpoint>
  quantization_config:
    method: awq
    bits: 4
    group_size: 128
    zero_point: true
    version: gemm
```

The AReaL worker environment needs `autoawq` importable only when this quantized
teacher path is used.