Instructions to use LostGentoo/Nanbeige4.2-3B-AWQ-W4A16-ASYM with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use LostGentoo/Nanbeige4.2-3B-AWQ-W4A16-ASYM with Transformers:

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

pipe = pipeline("text-generation", model="LostGentoo/Nanbeige4.2-3B-AWQ-W4A16-ASYM", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("LostGentoo/Nanbeige4.2-3B-AWQ-W4A16-ASYM", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use LostGentoo/Nanbeige4.2-3B-AWQ-W4A16-ASYM with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "LostGentoo/Nanbeige4.2-3B-AWQ-W4A16-ASYM"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "LostGentoo/Nanbeige4.2-3B-AWQ-W4A16-ASYM",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/LostGentoo/Nanbeige4.2-3B-AWQ-W4A16-ASYM

SGLang

How to use LostGentoo/Nanbeige4.2-3B-AWQ-W4A16-ASYM 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 "LostGentoo/Nanbeige4.2-3B-AWQ-W4A16-ASYM" \
    --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": "LostGentoo/Nanbeige4.2-3B-AWQ-W4A16-ASYM",
		"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 "LostGentoo/Nanbeige4.2-3B-AWQ-W4A16-ASYM" \
        --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": "LostGentoo/Nanbeige4.2-3B-AWQ-W4A16-ASYM",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use LostGentoo/Nanbeige4.2-3B-AWQ-W4A16-ASYM with Docker Model Runner:
```
docker model run hf.co/LostGentoo/Nanbeige4.2-3B-AWQ-W4A16-ASYM
```

Nanbeige4.2-3B AWQ W4A16_ASYM

Activation-aware 4-bit weight quantization of Nanbeige/Nanbeige4.2-3B produced with llm-compressor.

Details


Scheme	`W4A16_ASYM` (compressed-tensors / pack-quantized)
Calibration	256 samples × 1024 tokens, `HuggingFaceH4/ultrachat_200k`
Quant host	NVIDIA RTX 5060 Ti 16GB
Fork commit	`01af9909913c38fe9b77fb4be0f019573e4cfb6f` (`nanbeige42`)
Size	~3.5GB safetensors

Requires Nanbeige/vllm branch nanbeige42 — stock vLLM cannot load NanbeigeForCausalLM.

Serve

vllm serve LostGentoo/Nanbeige4.2-3B-AWQ-W4A16-ASYM \
  --host 0.0.0.0 --port 8000 \
  --tensor-parallel-size 1 \
  --gpu-memory-utilization 0.90 \
  --max-model-len 32768 \
  --enable-auto-tool-choice \
  --tool-call-parser nanbeige \
  --reasoning-parser nanbeige \
  --trust-remote-code

Downloads last month: 125

Safetensors

Model size

4B params

Tensor type

I64

I32

BF16

Model tree for LostGentoo/Nanbeige4.2-3B-AWQ-W4A16-ASYM

Base model

Nanbeige/Nanbeige4.2-3B-Base

Finetuned

Nanbeige/Nanbeige4.2-3B

Quantized

(40)

this model