Instructions to use inspirebek/qwen3-4b-uzbek-v2-awq with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use inspirebek/qwen3-4b-uzbek-v2-awq with Transformers:

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

pipe = pipeline("text-generation", model="inspirebek/qwen3-4b-uzbek-v2-awq")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("inspirebek/qwen3-4b-uzbek-v2-awq")
model = AutoModelForCausalLM.from_pretrained("inspirebek/qwen3-4b-uzbek-v2-awq")
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 inspirebek/qwen3-4b-uzbek-v2-awq with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "inspirebek/qwen3-4b-uzbek-v2-awq"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "inspirebek/qwen3-4b-uzbek-v2-awq",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/inspirebek/qwen3-4b-uzbek-v2-awq

SGLang

How to use inspirebek/qwen3-4b-uzbek-v2-awq 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 "inspirebek/qwen3-4b-uzbek-v2-awq" \
    --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": "inspirebek/qwen3-4b-uzbek-v2-awq",
		"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 "inspirebek/qwen3-4b-uzbek-v2-awq" \
        --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": "inspirebek/qwen3-4b-uzbek-v2-awq",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use inspirebek/qwen3-4b-uzbek-v2-awq with Docker Model Runner:
```
docker model run hf.co/inspirebek/qwen3-4b-uzbek-v2-awq
```

inspirebek commited on Apr 20

Commit

93de1df

verified ·

1 Parent(s): 5f19f5e

docs: add model card

Browse files

Files changed (1) hide show

README.md +7 -7

README.md CHANGED Viewed

@@ -16,9 +16,9 @@ tags:
 # qwen3-4b-uzbek-v2-awq
-AWQ 4-bit activation-aware quant (~3.4 GB) of [`inspirebek/qwen3-4b-uzbek-v2`](https://huggingface.co/inspirebek/qwen3-4b-uzbek-v2). Fast GPU inference via vLLM / TGI / transformers.
-## Usage
 ```python
 from transformers import AutoModelForCausalLM, AutoTokenizer
@@ -30,19 +30,19 @@ model = AutoModelForCausalLM.from_pretrained(
 )
 ```
-With vLLM:
 ```bash
 vllm serve inspirebek/qwen3-4b-uzbek-v2-awq --quantization awq --dtype float16
 ```
-## Quantization
-- method: AWQ (`autoawq` 0.2.9, GEMM version)
 - `w_bit=4, q_group_size=128, zero_point=True`
-- calibration: 128 Uzbek samples (2048 tokens each) from `fluency.jsonl`
-## Sibling formats
 - [`inspirebek/qwen3-4b-uzbek-v2`](https://huggingface.co/inspirebek/qwen3-4b-uzbek-v2)
 - [`inspirebek/qwen3-4b-uzbek-v2-lora`](https://huggingface.co/inspirebek/qwen3-4b-uzbek-v2-lora)

 # qwen3-4b-uzbek-v2-awq
+awq 4-bit activation-aware quant (~3.4 gb) of [`inspirebek/qwen3-4b-uzbek-v2`](https://huggingface.co/inspirebek/qwen3-4b-uzbek-v2). fast gpu inference via vllm / tgi / transformers.
+## usage
 ```python
 from transformers import AutoModelForCausalLM, AutoTokenizer
 )
 ```
+with vllm:
 ```bash
 vllm serve inspirebek/qwen3-4b-uzbek-v2-awq --quantization awq --dtype float16
 ```
+## quantization
+- method: awq (`autoawq` 0.2.9, gemm version)
 - `w_bit=4, q_group_size=128, zero_point=True`
+- calibration: 128 uzbek samples (2048 tokens each) from `fluency.jsonl`
+## sibling formats
 - [`inspirebek/qwen3-4b-uzbek-v2`](https://huggingface.co/inspirebek/qwen3-4b-uzbek-v2)
 - [`inspirebek/qwen3-4b-uzbek-v2-lora`](https://huggingface.co/inspirebek/qwen3-4b-uzbek-v2-lora)