Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive-NVFP4

Instructions to use will1208/Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive-NVFP4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use will1208/Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive-NVFP4 with Transformers:

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

pipe = pipeline("image-text-to-text", model="will1208/Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive-NVFP4")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("will1208/Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive-NVFP4")
model = AutoModelForMultimodalLM.from_pretrained("will1208/Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive-NVFP4", device_map="auto")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.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(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use will1208/Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive-NVFP4 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "will1208/Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive-NVFP4"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "will1208/Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive-NVFP4",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/will1208/Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive-NVFP4

SGLang

How to use will1208/Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive-NVFP4 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 "will1208/Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive-NVFP4" \
    --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": "will1208/Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive-NVFP4",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

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 "will1208/Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive-NVFP4" \
        --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": "will1208/Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive-NVFP4",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Docker Model Runner
How to use will1208/Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive-NVFP4 with Docker Model Runner:
```
docker model run hf.co/will1208/Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive-NVFP4
```

Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive-NVFP4

NVFP4 quantized version of HauhauCS/Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive.

Conservative profile: linear_attn (30 DeltaNet/Mamba layers) and MTP kept in bf16 for best quality. Follows AEON-7/RedHatAI approach.

Spec	Value
Base model	HauhauCS/Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive (Q8_K_P GGUF)
Original model	Qwen/Qwen3.6-35B-A3B
Architecture	Qwen3.5 MoE — 35B total, 3B active, 256 experts (8 routed + 1 shared)
Quantization	NVFP4 W4A4 (conservative: linear_attn + MTP in bf16)
Format	`compressed-tensors` (native vLLM support)
Size	~22 GB
Max context (text-only)	131K+ on RTX 5090
Requires	NVIDIA Blackwell GPU (SM 120)

Quantization Recipe

recipe = QuantizationModifier(
    targets="Linear", scheme="NVFP4",
    ignore=["lm_head", "re:.*visual.*", "re:.*mlp.gate$",
            "re:.*mlp.shared_expert_gate$", "re:.*linear_attn.*", "re:^mtp.*"],
)
oneshot(model=model, dataset=ds, recipe=recipe,
        max_seq_length=1024, num_calibration_samples=128,
        moe_calibrate_all_experts=True, pipeline="basic")

Calibration: HuggingFaceH4/ultrachat_200k, 128 samples × 1024 tokens
MTP tensors copied from Qwen/Qwen3.6-35B-A3B (not present in GGUF)

Deployment (vLLM)

Vision + text smoke-tested on RTX 5090

This repository has been smoke-tested locally on an RTX 5090 with vllm/vllm-openai:v0.21.0-cu130-local, compressed-tensors, NVFP4 Marlin GEMM, FP8 KV cache, and a real image chat.completions request.

VLLM_USE_FLASHINFER_MOE_FP4=0 \
VLLM_NVFP4_GEMM_BACKEND=marlin \
vllm serve ./Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive-NVFP4 \
  --served-model-name qwen36-35b-a3b-hauhaucs-nvfp4 \
  --quantization compressed-tensors \
  --kv-cache-dtype fp8 \
  --gpu-memory-utilization 0.90 \
  --max-model-len 4096 \
  --max-num-seqs 1 \
  --max-num-batched-tokens 1024 \
  --trust-remote-code

For short non-thinking answers, pass chat_template_kwargs at the top level of the OpenAI-compatible request:

{
  "chat_template_kwargs": {"enable_thinking": false}
}

Text-only long context

VLLM_USE_FLASHINFER_MOE_FP4=0 \
VLLM_NVFP4_GEMM_BACKEND=marlin \
vllm serve ./Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive-NVFP4 \
  --quantization compressed-tensors \
  --kv-cache-dtype fp8 \
  --gpu-memory-utilization 0.95 \
  --max-model-len 100000 \
  --max-num-seqs 1 \
  --reasoning-parser qwen3 \
  --language-model-only \
  --trust-remote-code

Pipeline

Converted using li-yifei/gguf-to-nvfp4:

Q8_K_P GGUF → step1_convert_qwen36_moe.py → HF bf16 → step2_quantize_qwen36_moe.py → NVFP4

Also See

lyf/Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive-NVFP4-100K — Aggressive variant (linear_attn + MTP also NVFP4, smaller footprint for vision+long context)

Acknowledgments

HauhauCS for the uncensored GGUF source
Qwen for the base model and MTP weights
AEON-7 and RedHatAI for conservative quantization approach reference

Downloads last month: 138

Safetensors

Model size

21B params

Tensor type

F32

BF16

F8_E4M3

Model tree for will1208/Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive-NVFP4

Base model

Qwen/Qwen3.6-35B-A3B

Quantized

HauhauCS/Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive

Quantized

(34)

this model