Instructions to use ramankrishna10/npc-agentic-7b-v3-gptq-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ramankrishna10/npc-agentic-7b-v3-gptq-4bit with Transformers:

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

pipe = pipeline("text-generation", model="ramankrishna10/npc-agentic-7b-v3-gptq-4bit")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ramankrishna10/npc-agentic-7b-v3-gptq-4bit")
model = AutoModelForCausalLM.from_pretrained("ramankrishna10/npc-agentic-7b-v3-gptq-4bit")
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 ramankrishna10/npc-agentic-7b-v3-gptq-4bit with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ramankrishna10/npc-agentic-7b-v3-gptq-4bit"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ramankrishna10/npc-agentic-7b-v3-gptq-4bit",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ramankrishna10/npc-agentic-7b-v3-gptq-4bit

SGLang

How to use ramankrishna10/npc-agentic-7b-v3-gptq-4bit 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 "ramankrishna10/npc-agentic-7b-v3-gptq-4bit" \
    --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": "ramankrishna10/npc-agentic-7b-v3-gptq-4bit",
		"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 "ramankrishna10/npc-agentic-7b-v3-gptq-4bit" \
        --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": "ramankrishna10/npc-agentic-7b-v3-gptq-4bit",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use ramankrishna10/npc-agentic-7b-v3-gptq-4bit with Docker Model Runner:
```
docker model run hf.co/ramankrishna10/npc-agentic-7b-v3-gptq-4bit
```

NPC Agentic 7B — GPTQ 4-bit

W4A16 GPTQ-quantized build of ramankrishna10/npc-agentic-7b-v3 for fast, memory-efficient inference (loads in ~5 GB VRAM, ideal for vLLM serving).

See the FP16 reference card for the full training recipe, eval numbers, and known limitations (particularly the GSM8K regression vs base — use base Qwen2.5 or Qwen2.5-Math-7B for math-heavy workflows).

Quantization details

Method: GPTQ via llm-compressor
Scheme: W4A16 (4-bit weights, fp16 activations)
Group size: 128
Desc-act: true
Symmetric: false
Calibration: 512 samples from the training set, 2048 tokens each
Ignored layers: lm_head (kept in full precision)
Size on disk: ~4.5 GB

Inference (vLLM)

from vllm import LLM, SamplingParams
llm = LLM(model="ramankrishna10/npc-agentic-7b-v3-gptq-4bit", dtype="float16")
out = llm.generate(
    ["Design an event-sourced microservice with exactly-once command handling."],
    SamplingParams(max_tokens=1024, temperature=0.7, top_p=0.9),
)
print(out[0].outputs[0].text)

Citation

If you use NPC Agentic 7B in your work, please cite:

@misc{bachu2026npcagentic7b,
  title        = {NPC Agentic 7B: A Single-GPU QLoRA Recipe for a Laptop-Scale Conversational Model},
  author       = {Bachu, Rama Krishna},
  year         = {2026},
  month        = may,
  publisher    = {Zenodo},
  version      = {v1},
  doi          = {10.5281/zenodo.19954103},
  url          = {https://doi.org/10.5281/zenodo.19954103},
  note         = {Preprint}
}

Paper: https://doi.org/10.5281/zenodo.19954103