QwQ-32B-FP8-dynamic

Model Overview

• Model Architecture: Qwen2ForCausalLM
  • Input: Text
  • Output: Text
• Model Optimizations:
  • Weight quantization: FP8
  • Activation quantization: FP8
• Release Date: 3/6/2025
• Version: 1.0
• Model Developers: Neural Magic

Quantized version of Qwen/QwQ-32B.

Model Optimizations

This model was obtained by quantizing the weights and activations of Qwen/QwQ-32B to FP8 data type. This optimization reduces the number of bits per parameter from 16 to 8, reducing the disk size and GPU memory requirements by approximately 50%.

Only the weights and activations of the linear operators within transformers blocks are quantized. Weights are quantized using a symmetric per-channel scheme, whereas quantizations are quantized using a symmetric per-token scheme. LLM Compressor is used for quantization.

Use with vLLM

This model can be deployed efficiently using the vLLM backend, as shown in the example below.

from transformers import AutoTokenizer
from vllm import LLM, SamplingParams

number_gpus = 1
model_name = "neuralmagic/QwQ-32B-FP8-dynamic"

tokenizer = AutoTokenizer.from_pretrained(model_name)
sampling_params = SamplingParams(temperature=0.6, max_tokens=256, stop_token_ids=[tokenizer.eos_token_id])
llm = LLM(model=model_name, tensor_parallel_size=number_gpus, trust_remote_code=True)

messages_list = [
    [{"role": "user", "content": "Who are you? Please respond in pirate speak!"}],
]

prompt_token_ids = [tokenizer.apply_chat_template(messages, add_generation_prompt=True) for messages in messages_list]

outputs = llm.generate(prompt_token_ids=prompt_token_ids, sampling_params=sampling_params)

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

vLLM also supports OpenAI-compatible serving. See the documentation for more details.

Creation

This model was created with llm-compressor by running the code snippet below.

from transformers import AutoModelForCausalLM, AutoTokenizer
from llmcompressor.modifiers.quantization import QuantizationModifier
from llmcompressor.transformers import oneshot
import os

# Load model
model_stub = "Qwen/QwQ-32B"
model_name = model_stub.split("/")[-1]

model = AutoModelForCausalLM.from_pretrained(
    model_stub,
    torch_dtype="auto",
)

tokenizer = AutoTokenizer.from_pretrained(model_stub)

# Configure the quantization algorithm and scheme
recipe = QuantizationModifier(
    targets="Linear",
    scheme="FP8_DYNAMIC",
    ignore=["lm_head"],
)

# Apply quantization
oneshot(
    model=model,
    recipe=recipe,
)

# Save to disk in compressed-tensors format
save_path = model_name + "-FP8-dynamic
model.save_pretrained(save_path)
tokenizer.save_pretrained(save_path)
print(f"Model and tokenizer saved to: {save_path}")

Accuracy

Category	Metric	Qwen/QwQ-32B	neuralmagic/QwQ-32B-FP8-dynamic	Recovery
Reasoning	AIME 2024 (pass@1)	78.66	79.40	100.94%
	MATH-500 (pass@1)	97.39	97.44	100.05%
	GPQA Diamond (pass@1)	64.72	63.21	97.66%
	Average Score	80.25	80.05	99.75%