Instructions to use Blackfrost-AI/PINQWEN-3.6-27B-NVFP4-ABLITERATED with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Blackfrost-AI/PINQWEN-3.6-27B-NVFP4-ABLITERATED with Transformers:

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

pipe = pipeline("text-generation", model="Blackfrost-AI/PINQWEN-3.6-27B-NVFP4-ABLITERATED")
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("Blackfrost-AI/PINQWEN-3.6-27B-NVFP4-ABLITERATED")
model = AutoModelForMultimodalLM.from_pretrained("Blackfrost-AI/PINQWEN-3.6-27B-NVFP4-ABLITERATED")
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 Blackfrost-AI/PINQWEN-3.6-27B-NVFP4-ABLITERATED with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Blackfrost-AI/PINQWEN-3.6-27B-NVFP4-ABLITERATED"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Blackfrost-AI/PINQWEN-3.6-27B-NVFP4-ABLITERATED",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Blackfrost-AI/PINQWEN-3.6-27B-NVFP4-ABLITERATED

SGLang

How to use Blackfrost-AI/PINQWEN-3.6-27B-NVFP4-ABLITERATED 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 "Blackfrost-AI/PINQWEN-3.6-27B-NVFP4-ABLITERATED" \
    --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": "Blackfrost-AI/PINQWEN-3.6-27B-NVFP4-ABLITERATED",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "Blackfrost-AI/PINQWEN-3.6-27B-NVFP4-ABLITERATED" \
        --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": "Blackfrost-AI/PINQWEN-3.6-27B-NVFP4-ABLITERATED",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Blackfrost-AI/PINQWEN-3.6-27B-NVFP4-ABLITERATED with Docker Model Runner:
```
docker model run hf.co/Blackfrost-AI/PINQWEN-3.6-27B-NVFP4-ABLITERATED
```

PINQWEN-3.6-27B-NVFP4-ABLITERATED

Blackfrost internal archive. Agentic / tool-calling specialist — Qwen3.6-27B fine-tuned on the The Void (v3) corpus, then quantized to NVFP4 (nvidia-modelopt) for fast serving on Blackwell (SM120).

At a glance

Field	Value
Base	`huihui-ai/Huihui-Qwen3.6-27B-abliterated` (Qwen3.6-27B — hybrid Gated-DeltaNet + attention, abliterated)
Params	~27 B (hybrid dense, 64-layer + 1 MTP)
Fine-tune data	The Void (v3) — 5,025 records (3,132 knowledge/CoT + 1,893 agentic ReAct, 38% agentic)
Method	unsloth QLoRA, rank 32, α 32, all 7 proj targets, multi-turn masking, length-grouped
Schedule	3 epochs, 474 steps, lr 2e-4 linear, bsz 2 × accum 2 × 8 GPU (eff 32)
Hardware	8× RTX PRO 6000 Blackwell (`g4-standard-384`), ~1.5 h wall
Quant	NVFP4 (`nvidia-modelopt` `NVFP4_DEFAULT_CFG`), text-only, MTP grafted
Serves on	vLLM, Blackwell SM120
Trained	2026-07-08 · Blackfrost-AI

Benchmark — `agent_benchmark.py` (vs. base, identical battery)

Metric	Base (abliterated)	VEGA-27B
Tool-calling accuracy	7 / 8	8 / 8
Avg latency / response	10.5 s	6.2 s (−41%)
Avg tokens / response (verbosity)	267	158 (−41%)
Multi-turn drivability	2 / 2	1 / 2 (mock-tool keyword artifact — not a real regression; needs a live tool to score)

Takeaway: the The Void (v3) training made an already-strong base more accurate at tool selection, ~40% faster, and ~40% more concise.

Quantization details (why this one serves, unlike a naive convert)

Tool: nvidia-modelopt (NVFP4_DEFAULT_CFG) — the fast SM120 path. llm-compressor/compressed-tensors NVFP4 null-outputs on SM120 + vLLM for this hybrid family, so modelopt is required.
Arch kept: Qwen3_5ForConditionalGeneration + language_model_only: true. vLLM has no text-only class for the Qwen3.5 hybrid family, so the full class + this flag is how a text model loads.
Kept in bf16 (quant ignore list): linear_attn.conv1d (the Gated-DeltaNet conv), lm_head, vision tower, MTP head.
MTP head (15 tensors) grafted back in bf16 → working speculative-decoding draft path.
Vision tower stripped → text-only, smaller + faster than the VLM variant.
Recipe: lna-lab/GGUF-to-NVFP4-SM120 qwen36_27b_text_mtp.py.

Serving (vLLM on Blackwell)

vllm serve Blackfrost-AI/VEGA-27B-NVFP4 \
  --trust-remote-code \
  --enable-auto-tool-choice --tool-call-parser qwen3_xml \
  --max-model-len 131072

No --quantization flag — vLLM auto-detects the modelopt NVFP4 checkpoint. Tool calls use Qwen3's XML format (<function=name><parameter=x>…), parsed by qwen3_xml.

Downloads last month: 356

Safetensors

Model size

17B params

Tensor type

BF16

F8_E4M3

Model tree for Blackfrost-AI/PINQWEN-3.6-27B-NVFP4-ABLITERATED

Base model

Qwen/Qwen3.6-27B

Finetuned

huihui-ai/Huihui-Qwen3.6-27B-abliterated

Quantized

(27)

this model

Collection including Blackfrost-AI/PINQWEN-3.6-27B-NVFP4-ABLITERATED

PINQWEN SERIES

Collection

THE QWEN FAMILY FINE-TUNED MODELS IN THE VOID • 5 items • Updated 2 days ago