Instructions to use rtj1/Qwen2.5-0.5B-AWQ-FP8-Dynamic with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use rtj1/Qwen2.5-0.5B-AWQ-FP8-Dynamic with Transformers:

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

pipe = pipeline("text-generation", model="rtj1/Qwen2.5-0.5B-AWQ-FP8-Dynamic")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("rtj1/Qwen2.5-0.5B-AWQ-FP8-Dynamic")
model = AutoModelForCausalLM.from_pretrained("rtj1/Qwen2.5-0.5B-AWQ-FP8-Dynamic", device_map="auto")
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 rtj1/Qwen2.5-0.5B-AWQ-FP8-Dynamic with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "rtj1/Qwen2.5-0.5B-AWQ-FP8-Dynamic"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "rtj1/Qwen2.5-0.5B-AWQ-FP8-Dynamic",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/rtj1/Qwen2.5-0.5B-AWQ-FP8-Dynamic

SGLang

How to use rtj1/Qwen2.5-0.5B-AWQ-FP8-Dynamic 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 "rtj1/Qwen2.5-0.5B-AWQ-FP8-Dynamic" \
    --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": "rtj1/Qwen2.5-0.5B-AWQ-FP8-Dynamic",
		"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 "rtj1/Qwen2.5-0.5B-AWQ-FP8-Dynamic" \
        --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": "rtj1/Qwen2.5-0.5B-AWQ-FP8-Dynamic",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use rtj1/Qwen2.5-0.5B-AWQ-FP8-Dynamic with Docker Model Runner:
```
docker model run hf.co/rtj1/Qwen2.5-0.5B-AWQ-FP8-Dynamic
```

Qwen2.5-0.5B-Instruct AWQ + FP8_DYNAMIC

This is a quantized version of Qwen/Qwen2.5-0.5B-Instruct using AWQ + FP8_DYNAMIC quantization scheme.

Model Details

Base Model: Qwen2.5-0.5B-Instruct
Quantization: AWQ + FP8_DYNAMIC
Size: 0.92 GB (1.2x compression from original 1.1GB)
Precision: FP8 (E4M3)
Parameters: 0.6B

Performance

Evaluated on GSM8K benchmark:

Metric	Score
Strict Match	22.67%
Flexible Extract	30.78%

This outperforms the FP8_BLOCK quantization scheme (17.97% strict match) by ~5% while maintaining the same model size.

Usage

Loading with Transformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained(
    "rtj1/Qwen2.5-0.5B-AWQ-FP8-Dynamic",
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("rtj1/Qwen2.5-0.5B-AWQ-FP8-Dynamic")

prompt = "What is 25 * 4?"
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
outputs = model.generate(**inputs, max_new_tokens=100)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

Loading with vLLM

from vllm import LLM, SamplingParams

llm = LLM(model="rtj1/Qwen2.5-0.5B-AWQ-FP8-Dynamic")
sampling_params = SamplingParams(temperature=0.0, max_tokens=100)

prompts = ["What is 25 * 4?"]
outputs = llm.generate(prompts, sampling_params)

for output in outputs:
    print(output.outputs[0].text)

Quantization Details

Created using llm-compressor with the FP8_DYNAMIC scheme:

from llmcompressor.modifiers.quantization import QuantizationModifier
from llmcompressor.transformers import oneshot

recipe = QuantizationModifier(
    targets="Linear",
    scheme="FP8_DYNAMIC",
    ignore=["lm_head"]
)

oneshot(
    model="Qwen/Qwen2.5-0.5B-Instruct",
    recipe=recipe,
    output_dir="Qwen2.5-0.5B-Instruct-awq-fp8-dynamic"
)

Quantization time: ~5 minutes on L4 GPU

Evaluation

Benchmarked using lm-evaluation-harness:

lm_eval \
  --model hf \
  --model_args pretrained=rtj1/Qwen2.5-0.5B-AWQ-FP8-Dynamic,dtype=auto \
  --tasks gsm8k \
  --batch_size 16

Evaluation time: ~71 minutes on L4 GPU

Related Work

FP8_BLOCK variant - Alternative quantization scheme (17.97% GSM8K strict match)
llm-compressor PR #2330 - Evaluation comparison and reproducible workflow

Hardware Requirements

GPU: Any GPU with FP8 support (L4, A100, H100)
VRAM: ~1GB minimum for inference
Works with Google Colab L4 (22.5GB VRAM)

Citation

@misc{qwen2.5-awq-fp8-dynamic,
  author = {Tharun Jagarlamudi},
  title = {Qwen2.5-0.5B-Instruct AWQ + FP8_DYNAMIC},
  year = {2026},
  publisher = {HuggingFace},
  url = {https://huggingface.co/rtj1/Qwen2.5-0.5B-AWQ-FP8-Dynamic}
}

License

Same as base model: Qwen License

Downloads last month: 13

Safetensors

Model size

0.6B params

Tensor type

BF16

F8_E4M3

Model tree for rtj1/Qwen2.5-0.5B-AWQ-FP8-Dynamic

Base model

Qwen/Qwen2.5-0.5B

Finetuned

Qwen/Qwen2.5-0.5B-Instruct

Quantized

(269)

this model

Dataset used to train rtj1/Qwen2.5-0.5B-AWQ-FP8-Dynamic

Evaluation results

Strict Match on GSM8K
self-reported

22.670
Flexible Extract on GSM8K
self-reported

30.780