Instructions to use kleinpanic93/Nemotron-Terminal-32B-NVFP4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use kleinpanic93/Nemotron-Terminal-32B-NVFP4 with Transformers:

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

pipe = pipeline("text-generation", model="kleinpanic93/Nemotron-Terminal-32B-NVFP4")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("kleinpanic93/Nemotron-Terminal-32B-NVFP4")
model = AutoModelForCausalLM.from_pretrained("kleinpanic93/Nemotron-Terminal-32B-NVFP4")
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

vLLM

How to use kleinpanic93/Nemotron-Terminal-32B-NVFP4 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "kleinpanic93/Nemotron-Terminal-32B-NVFP4"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "kleinpanic93/Nemotron-Terminal-32B-NVFP4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/kleinpanic93/Nemotron-Terminal-32B-NVFP4

SGLang

How to use kleinpanic93/Nemotron-Terminal-32B-NVFP4 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 "kleinpanic93/Nemotron-Terminal-32B-NVFP4" \
    --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": "kleinpanic93/Nemotron-Terminal-32B-NVFP4",
		"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 "kleinpanic93/Nemotron-Terminal-32B-NVFP4" \
        --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": "kleinpanic93/Nemotron-Terminal-32B-NVFP4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use kleinpanic93/Nemotron-Terminal-32B-NVFP4 with Docker Model Runner:
```
docker model run hf.co/kleinpanic93/Nemotron-Terminal-32B-NVFP4
```

Nemotron-Terminal-32B NVFP4

NVFP4 quantization of nvidia/Nemotron-Terminal-32B
Produced by self-quantization on an NVIDIA DGX Spark (GB10 Blackwell) using NVIDIA Model Optimizer.

Model Description

Nemotron-Terminal-32B is NVIDIA's official Qwen3-32B-based model tuned for autonomous terminal tasks, bash scripting, and agentic workflows.

This repo contains a Blackwell-native NVFP4 quantized checkpoint (~20GB), reducing the original ~64GB BF16 footprint by ~70% while preserving quality.

Quantization Details

Property	Value
Base model	nvidia/Nemotron-Terminal-32B
Source precision	BF16
Quantization	NVFP4 (attention: BF16, experts: NVFP4)
Tool	NVIDIA Model Optimizer (nvidia-modelopt 0.41.0)
Calibration	512 samples, synthetic random
Hardware	NVIDIA GB10 Blackwell (DGX Spark)
Output size	~20GB (vs ~64GB BF16)

Usage with vLLM

vllm serve kleinpanic93/Nemotron-Terminal-32B-NVFP4 \
  --quantization modelopt_fp4 \
  --max-model-len 32768 \
  --gpu-memory-utilization 0.72 \
  --trust-remote-code \
  --enable-chunked-prefill \
  --enable-prefix-caching

Note: NVFP4 kernels require NVIDIA Blackwell (GB10/GB200) or newer hardware. Does not run on Hopper (H100) or older.

Provenance

{
  "source_model": "nvidia/Nemotron-Terminal-32B",
  "quantization": "NVFP4",
  "tool": "nvidia-modelopt",
  "hardware": "NVIDIA GB10 (Blackwell)",
  "attention_dtype": "bfloat16"
}