Instructions to use philbert440/ThinkingCap-Qwen3.6-27B-Uncensored-Medium-W4A16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use philbert440/ThinkingCap-Qwen3.6-27B-Uncensored-Medium-W4A16 with Transformers:

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

pipe = pipeline("image-text-to-text", model="philbert440/ThinkingCap-Qwen3.6-27B-Uncensored-Medium-W4A16")
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("philbert440/ThinkingCap-Qwen3.6-27B-Uncensored-Medium-W4A16")
model = AutoModelForMultimodalLM.from_pretrained("philbert440/ThinkingCap-Qwen3.6-27B-Uncensored-Medium-W4A16", 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 philbert440/ThinkingCap-Qwen3.6-27B-Uncensored-Medium-W4A16 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "philbert440/ThinkingCap-Qwen3.6-27B-Uncensored-Medium-W4A16"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "philbert440/ThinkingCap-Qwen3.6-27B-Uncensored-Medium-W4A16",
		"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/philbert440/ThinkingCap-Qwen3.6-27B-Uncensored-Medium-W4A16

SGLang

How to use philbert440/ThinkingCap-Qwen3.6-27B-Uncensored-Medium-W4A16 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 "philbert440/ThinkingCap-Qwen3.6-27B-Uncensored-Medium-W4A16" \
    --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": "philbert440/ThinkingCap-Qwen3.6-27B-Uncensored-Medium-W4A16",
		"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 "philbert440/ThinkingCap-Qwen3.6-27B-Uncensored-Medium-W4A16" \
        --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": "philbert440/ThinkingCap-Qwen3.6-27B-Uncensored-Medium-W4A16",
		"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 philbert440/ThinkingCap-Qwen3.6-27B-Uncensored-Medium-W4A16 with Docker Model Runner:
```
docker model run hf.co/philbert440/ThinkingCap-Qwen3.6-27B-Uncensored-Medium-W4A16
```

ThinkingCap Qwen3.6 27B Uncensored Medium W4A16

Sharpest uncensored tier: gsm8k 0.94, factual 1.0, in W4A16-AWQ.

Part of the Qwen3.6-27B Uncensored — ThinkingCap collection — abliterated (Heretic) Qwen3.6 vision-language models served on Tesla V100 via 1Cat-vLLM.

What this is

Medium — gentle abliteration: the sharpest, best-calibrated tier (gsm8k 0.94–0.95, factual 1.0) with more selective openness.

W4A16-AWQ — 4-bit weight-only (AWQ, compressed-tensors), FP16 activations. Runs on 1Cat-vLLM's SM70 TurboMind path (Tesla V100) and on stock vLLM (Ampere+).

Base model: philbert440/ThinkingCap-Qwen3.6-27B-Uncensored-Medium

Benchmarks

7-axis battery on 2× V100. Higher is better except Confab (↓). Openness/Confab are small-N probes; gsm8k is n=100.

gsm8k	Factual	Confab ↓	Openness	tok/s (c1)
0.94	1.0	0.13	0.167	46.8

Serving

# 1Cat-vLLM on 2x Tesla V100 (SM70): W4A16-AWQ + MTP. (Also runs on stock vLLM, Ampere+.)
export VLLM_SM70_FLASH_ATTN_V100=1 VLLM_SM70_QUANT_BACKEND=turbomind
python -m vllm.entrypoints.openai.api_server \
  --model philbert440/ThinkingCap-Qwen3.6-27B-Uncensored-Medium-W4A16 --trust-remote-code --dtype half \
  --attention-backend FLASH_ATTN_V100 --tensor-parallel-size 2 \
  --kv-cache-dtype fp8_e5m2 --max-num-seqs 6 \
  --speculative-config '{"method":"mtp","num_speculative_tokens":4,"attention_backend":"FLASH_ATTN_V100","draft_sample_method":"greedy"}' \
  --compilation-config '{"cudagraph_mode":"full_and_piecewise","cudagraph_capture_sizes":[1,2,4,8]}'

Openness

Openness profile (honest): abliteration opens up hacking / malware / lock-picking / NSFW / disinformation prompts; weapons, drugs, political persuasion, surveillance, and extremism stay refused across all tiers. "Uncensored" here means cyber/NSFW-permissive, not unconditionally open.

Variants

See the Qwen3.6-27B Uncensored — ThinkingCap collection for all tiers and formats (BF16 / W4A16-AWQ / NVFP4).

Abliteration removes safety refusals; you are responsible for lawful, ethical use.

Changelog

2026-08-15 — tokenizer fix. tokenizer.json / tokenizer_config.json were re-serialized by the llm-compressor calibration run and shipped with an active truncation block (max_length 1024/2048) plus a drifted pre-tokenizer regex (and, on the Qwen3.6-based repos, 7 phantom audio/TTS special tokens the base model does not define). That broke image inputs larger than the limit under transformers 5 / vLLM (Mismatch in image token count, surfacing as an HTTP 400 Failed to apply Qwen3VLProcessor). Both files are now byte-identical to the upstream base model's (vocab/merges/added tokens were always identical — this is a metadata-only restore). If you downloaded before this date, re-fetch those two files. Thanks to @elBuffo for the report.