Qwen3-Next-80B-A3B-Thinking-quantized.w4a16

Qwen3-Next-80B-A3B-Thinking-quantized.w4a16

Model Overview

• Model Architecture: Qwen3NextForCausalLM
  • Input: Text
  • Output: Text
• Model Optimizations:
  • Weight quantization: INT4
• Version: 1.0
• Model Developers: RedHat (Neural Magic)

Model Optimizations

This model was obtained by quantizing the weights of Qwen/Qwen3-Next-80B-A3B-Thinking to INT4 data type. This optimization reduces the number of bits per parameter from 16 to 4, reducing the disk size and GPU memory requirements by approximately 75%.

Only the weights of the linear operators within transformers blocks are quantized. Weights are quantized using a symmetric per-group scheme, with group size 128. The GPTQ algorithm is applied for quantization, as implemented in the llm-compressor library.

Deployment

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

from vllm import LLM, SamplingParams
from transformers import AutoTokenizer

model_id = "RedHatAI/Qwen3-Next-80B-A3B-Thinking-quantized.w4a16"
number_gpus = 1
sampling_params = SamplingParams(temperature=0.6, top_p=0.95, top_k=20, min_p=0, max_tokens=256)

messages = [
    {"role": "user", "content": prompt}
]

tokenizer = AutoTokenizer.from_pretrained(model_id)

messages = [{"role": "user", "content": "Give me a short introduction to large language model."}]

prompts = tokenizer.apply_chat_template(messages, add_generation_prompt=True, tokenize=False)

llm = LLM(model=model_id, tensor_parallel_size=number_gpus)

outputs = llm.generate(prompts, sampling_params)

generated_text = outputs[0].outputs[0].text
print(generated_text)

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

Creation

<details> <summary>Creation details</summary> This model was created with [llm-compressor](https://github.com/vllm-project/llm-compressor) by running the code snippet below.

from datasets import load_dataset
from transformers import AutoModelForCausalLM, AutoTokenizer

from llmcompressor import oneshot
from llmcompressor.modifiers.quantization import QuantizationModifier
from llmcompressor.utils import dispatch_for_generation
from llmcompressor.modifiers.quantization import GPTQModifier

# NOTE: Requires a minimum of transformers 4.57.0

MODEL_ID = "Qwen/Qwen3-Next-80B-A3B-Thinking"

# Load model.
model = AutoModelForCausalLM.from_pretrained(MODEL_ID, torch_dtype="auto")
tokenizer = AutoTokenizer.from_pretrained(MODEL_ID)

# Select calibration dataset.
DATASET_ID = "HuggingFaceH4/ultrachat_200k"
DATASET_SPLIT = "train_sft"

# Select number of samples. 512 samples is a good place to start.
# Increasing the number of samples can improve accuracy.
NUM_CALIBRATION_SAMPLES = 512
MAX_SEQUENCE_LENGTH = 2048

# Load dataset and preprocess.
ds = load_dataset(DATASET_ID, split=f"{DATASET_SPLIT}[:{NUM_CALIBRATION_SAMPLES}]")
ds = ds.shuffle(seed=42)


def preprocess(example):
  return {
      "text": tokenizer.apply_chat_template(
          example["messages"],
          tokenize=False,
      )
  }


ds = ds.map(preprocess)


# Tokenize inputs.
def tokenize(sample):
  return tokenizer(
      sample["text"],
      padding=False,
      max_length=MAX_SEQUENCE_LENGTH,
      truncation=True,
      add_special_tokens=False,
  )


ds = ds.map(tokenize, remove_columns=ds.column_names)

# Configure the quantization algorithm to run.
#   * quantize the weights to 4 bit with GPTQ with a group size 128
recipe = GPTQModifier(targets="Linear", scheme="W4A16", 
  ignore=[
      "lm_head",
      "re:.*mlp.gate$",
      "re:.*mlp.shared_expert_gate$",
      "re:.*linear_attn.*",
  ],
)

# Apply algorithms.
oneshot(
  model=model,
  dataset=ds,
  recipe=recipe,
  max_seq_length=MAX_SEQUENCE_LENGTH,
  num_calibration_samples=NUM_CALIBRATION_SAMPLES,
)

# Confirm generations of the quantized model look sane.
print("\n\n")
print("========== SAMPLE GENERATION ==============")
dispatch_for_generation(model)
sample = tokenizer("Describe Large Language Model", return_tensors="pt")
sample = {key: value.to(model.device) for key, value in sample.items()}
output = model.generate(**sample, max_new_tokens=100)
print(tokenizer.decode(output[0]))
print("==========================================\n\n")

# Save to disk compressed.
SAVE_DIR = MODEL_ID.rstrip("/").split("/")[-1] + "-W4A16-G128"
model.save_pretrained(SAVE_DIR, save_compressed=True)
tokenizer.save_pretrained(SAVE_DIR)

</details>

Evaluation

The model was evaluated on the OpenLLM leaderboard tasks versions 2, using lm-evaluation-harness, and on reasoning tasks using lighteval. vLLM was used for all evaluations.

<details> <summary>Evaluation details</summary>

lm-evaluation-harness

lm_eval \
  --model vllm \
  --model_args pretrained="RedHatAI/Qwen3-Next-80B-A3B-Thinking-quantized.w4a16",dtype=auto,gpu_memory_utilization=0.5,max_model_len=15000,enable_chunk_prefill=True,tensor_parallel_size=1 \
  --tasks openllm \
  --apply_chat_template\
  --fewshot_as_multiturn \
  --batch_size auto

lm_eval \
  --model vllm \
  --model_args pretrained="RedHatAI/Qwen3-Next-80B-A3B-Thinking-quantized.w4a16",dtype=auto,gpu_memory_utilization=0.5,max_model_len=15000,enable_chunk_prefill=True,tensor_parallel_size=1 \
  --tasks mgsm \
  --apply_chat_template\
  --batch_size auto

lm_eval \
  --model vllm \
  --model_args pretrained="RedHatAI/Qwen3-Next-80B-A3B-Thinking-quantized.w4a16",dtype=auto,gpu_memory_utilization=0.5,max_model_len=15000,enable_chunk_prefill=True,tensor_parallel_size=1 \
  --tasks leaderboard \
  --apply_chat_template\
  --fewshot_as_multiturn \
  --batch_size auto

lighteval

lighteval_model_arguments.yaml

model_parameters:
  model_name: RedHatAI/Qwen3-Next-80B-A3B-Thinking-quantized.w4a16
  dtype: auto
  gpu_memory_utilization: 0.9
  max_model_length: 40960
  generation_parameters:
    temperature: 0.6
    top_k: 20
    min_p: 0.0
    top_p: 0.95
    max_new_tokens: 32000

lighteval vllm \
  --model_args lighteval_model_arguments.yaml \
  --tasks lighteval|aime25|0|0 \
  --use_chat_template = true

lighteval vllm \
  --model_args lighteval_model_arguments.yaml \
  --tasks lighteval|math_500|0|0 \
  --use_chat_template = true

lighteval vllm \
  --model_args lighteval_model_arguments.yaml \
  --tasks lighteval|gpqa:diamond|0|0 \
  --use_chat_template = true

lighteval vllm \
  --model_args lighteval_model_arguments.yaml \
  --tasks extended|lcb:codegeneration \
  --use_chat_template = true

</details>

Accuracy