[!IMPORTANT] NVFP4 quantization requires NVIDIA Blackwell architecture (GB200, RTX 5000 series, etc.). This format is not compatible with Ampere, Ada Lovelace, or Hopper GPUs. If you are running on an older GPU, please use a different quantization format.

Original model: https://huggingface.co/Qwen/Qwen3.6-27B

⚡ Deployment with vLLM

This quantized model is intended to be served using vLLM (vllm>=0.9.0 recommended).

Quick Start

bash

vllm serve NeuralNet-Hub/Qwen3.6-27B-NVFP4 \
  --quantization nvfp4 \
  --dtype bfloat16 \
  --kv-cache-dtype fp8 \
  --max-model-len 262144 \
  --reasoning-parser qwen3 \
  --enable-auto-tool-choice \
  --tool-call-parser qwen3_coder

Using a Config File

yaml

# Deploy with: vllm serve --config config.yaml

# Model config
model: NeuralNet-Hub/Qwen3.6-27B-NVFP4
dtype: bfloat16
kv-cache-dtype: fp8
gpu-memory-utilization: 0.95
max-model-len: 262144
max-num-batched-tokens: 4096
max-num-seqs: 200
max-cudagraph-capture-size: 209
enable-prefix-caching: true
trust-remote-code: true

# template parser
reasoning-parser: qwen3
enable-auto-tool-choice: true
tool-call-parser: qwen3_coder

# Optional
default-chat-template-kwargs: '{"enable_thinking": false}'
download-dir: /workspace/models
host: 0.0.0.0
port: 18000

vllm serve --config config.yaml

💬 Chat API Usage

Once you deploy your model using vLLM you can chat qwith Qwen3.6 with chat template compatible with OpenAI-format APIs. Thinking mode is enabled by default.

Thinking Mode (Default)

python

from openai import OpenAI

client = OpenAI(base_url="http://localhost:18000/v1", api_key="EMPTY")

messages = [{"role": "user", "content": "Your message here"}]

response = client.chat.completions.create(
    model="NeuralNet-Hub/Qwen3.6-27B-NVFP4",
    messages=messages,
    max_tokens=32768,
    temperature=1.0,
    top_p=0.95,
    extra_body={"top_k": 20},
)
print(response.choices[0].message.content)

Non-Thinking (Instruct) Mode

python

response = client.chat.completions.create(
    model="NeuralNet-Hub/Qwen3.6-27B-NVFP4",
    messages=messages,
    max_tokens=8192,
    temperature=0.7,
    top_p=0.8,
    presence_penalty=1.5,
    extra_body={
        "top_k": 20,
        "chat_template_kwargs": {"enable_thinking": False},
    },
)

Image Input

python

messages = [
    {
        "role": "user",
        "content": [
            {"type": "image_url", "image_url": {"url": "https://example.com/image.jpg"}},
            {"type": "text", "text": "Describe this image in detail."}
        ]
    }
]

response = client.chat.completions.create(
    model="NeuralNet-Hub/Qwen3.6-27B-NVFP4",
    messages=messages,
    max_tokens=32768,
    temperature=1.0,
    top_p=0.95,
    extra_body={"top_k": 20},
)

⚙️ Recommended Sampling Parameters

Mode	temperature	top_p	top_k	presence_penalty
Thinking — general tasks	1.0	0.95	20	0.0
Thinking — precise coding	0.6	0.95	20	0.0
Instruct (non-thinking)	0.7	0.80	20	1.5

🔧 Hardware Requirements

Component	Requirement
GPU Architecture	NVIDIA Blackwell (sm_100+)
VRAM	24 GB+ recommended
CUDA	12.8+
vLLM	0.9.0+

[!WARNING] NVFP4 is exclusively supported on NVIDIA Blackwell GPUs. Attempting to run this model on Ampere (A100), Ada Lovelace (RTX 4000), or Hopper (H100) will fail. For those architectures, use the original BF16 model or an AWQ/GPTQ quantized variant.

🌐 Contact Us

NeuralNet is a pioneering AI solutions provider that empowers businesses to harness the power of artificial intelligence.

Website: https://neuralnet.solutions
Email: info[at]neuralnet.solutions