Qwen3-30B-A3B-FP8-block

Model Overview

• Model Architecture: Qwen3MoeForCausalLM
  • Input: Text
  • Output: Text
• Model Optimizations:
  • Weight quantization: FP8
  • Activation quantization: FP8
• Release Date:
• Version: 1.0
• Model Developers:: Red Hat

Quantized version of Qwen/Qwen3-30B-A3B.

Model Optimizations

This model was obtained by quantizing the weights and activations of Qwen/Qwen3-30B-A3B 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 of the language model are quantized.

Deployment

Use with vLLM

1. Initialize vLLM server:

vllm serve nm-testing/Qwen3-30B-A3B-FP8-block --tensor_parallel_size 4

2. Send requests to the server:

from openai import OpenAI

# Modify OpenAI's API key and API base to use vLLM's API server.
openai_api_key = "EMPTY"
openai_api_base = "http://<your-server-host>:8000/v1"

client = OpenAI(
    api_key=openai_api_key,
    base_url=openai_api_base,
)

model = "nm-testing/Qwen3-30B-A3B-FP8-block"

messages = [
    {"role": "user", "content": "Explain quantum mechanics clearly and concisely."},
]

outputs = client.chat.completions.create(
    model=model,
    messages=messages,
)

generated_text = outputs.choices[0].message.content
print(generated_text)

Creation

This model was quantized using the llm-compressor library as shown below.

Creation details

from transformers import AutoProcessor, Qwen3MoeForCausalLM

from llmcompressor import oneshot
from llmcompressor.modeling import replace_modules_for_calibration
from llmcompressor.modifiers.quantization import QuantizationModifier

MODEL_ID = "Qwen/Qwen3-30B-A3B"

# Load model.
model = Qwen3ForCausalLM.from_pretrained(MODEL_ID, dtype="auto")
processor = AutoProcessor.from_pretrained(MODEL_ID)
model = replace_modules_for_calibration(model)

# Configure the quantization algorithm and scheme.
# In this case, we:
#   * quantize the weights to fp8 with per-block quantization
#   * quantize the activations to fp8 with dynamic token activations
recipe = QuantizationModifier(
    targets="Linear",
    scheme="FP8_BLOCK",
    ignore=["lm_head"],
)

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

# Save to disk in compressed-tensors format.
SAVE_DIR = MODEL_ID.rstrip("/").split("/")[-1] + "-FP8-block"
model.save_pretrained(SAVE_DIR)
processor.save_pretrained(SAVE_DIR)

Evaluation

The model was evaluated on the OpenLLM leaderboard task, using lm-evaluation-harness. vLLM was used for all evaluations.

Evaluation details

Openllm V1

lm_eval \
  --model vllm \
  --model_args pretrained="nm-testing/Qwen3-30B-A3B-FP8-block",dtype=auto,add_bos_token=True,max_model_len=16384,tensor_parallel_size=4,gpu_memory_utilization=0.9,enable_chunked_prefill=True,trust_remote_code=True \
  --tasks openllm \
  --write_out \
  --batch_size auto \
  --show_config

Openllm V2

lm_eval \
  --model vllm \
  --model_args pretrained="nm-testing/Qwen3-30B-A3B-FP8-block",dtype=auto,add_bos_token=False,max_model_len=16384,tensor_parallel_size=4,gpu_memory_utilization=0.7,disable_log_stats=True,enable_chunked_prefill=True,trust_remote_code=True \
  --tasks leaderboard \
  --apply_chat_template \
  --fewshot_as_multiturn \
  --write_out \
  --batch_size auto \
  --show_config

Coding Benchmarks

evalplus.evaluate --model "nm-testing/Qwen3-30B-A3B-FP8-block" \
                  --dataset "humaneval" \
                  --backend vllm \
                  --tp 4 \
                  --greedy

evalplus.evaluate --model "nm-testing/Qwen3-30B-A3B-FP8-block" \
                --dataset "mbpp" \
                --backend vllm \
                --tp 4 \
                --greedy

Accuracy