Instructions to use najabba/4bit_quantized with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use najabba/4bit_quantized with Transformers:

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

pipe = pipeline("text-generation", model="najabba/4bit_quantized")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("najabba/4bit_quantized")
model = AutoModelForCausalLM.from_pretrained("najabba/4bit_quantized")
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 najabba/4bit_quantized with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/najabba/4bit_quantized

SGLang

How to use najabba/4bit_quantized 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 "najabba/4bit_quantized" \
    --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": "najabba/4bit_quantized",
		"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 "najabba/4bit_quantized" \
        --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": "najabba/4bit_quantized",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use najabba/4bit_quantized with Docker Model Runner:
```
docker model run hf.co/najabba/4bit_quantized
```

najabba commited on Jun 9, 2025

Commit

8719f0e

verified ·

1 Parent(s): 8a9ca41

Upload Qwen3ForCausalLM

Browse files

Files changed (2) hide show

config.json +3 -3
model.safetensors +2 -2

config.json CHANGED Viewed

@@ -20,10 +20,10 @@
   "quantization_config": {
     "_load_in_4bit": true,
     "_load_in_8bit": false,
-    "bnb_4bit_compute_dtype": "float32",
     "bnb_4bit_quant_storage": "uint8",
-    "bnb_4bit_quant_type": "fp4",
-    "bnb_4bit_use_double_quant": false,
     "llm_int8_enable_fp32_cpu_offload": false,
     "llm_int8_has_fp16_weight": false,
     "llm_int8_skip_modules": null,

   "quantization_config": {
     "_load_in_4bit": true,
     "_load_in_8bit": false,
+    "bnb_4bit_compute_dtype": "bfloat16",
     "bnb_4bit_quant_storage": "uint8",
+    "bnb_4bit_quant_type": "nf4",
+    "bnb_4bit_use_double_quant": true,
     "llm_int8_enable_fp32_cpu_offload": false,
     "llm_int8_has_fp16_weight": false,
     "llm_int8_skip_modules": null,

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:89da0c16dfc84bfdbcd61989f2d19308925425267f37266a8869fe790e8ec9e5
-size 559156248

 version https://git-lfs.github.com/spec/v1
+oid sha256:dd34634f97c4d10ece899563ab64913bb9471954922a5dcb9455e9a3befc1eca
+size 538883407