Instructions to use VECTORVV1/Qwen3.6-27B-OBI with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use VECTORVV1/Qwen3.6-27B-OBI with Transformers:

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

pipe = pipeline("text-generation", model="VECTORVV1/Qwen3.6-27B-OBI")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("VECTORVV1/Qwen3.6-27B-OBI")
model = AutoModelForCausalLM.from_pretrained("VECTORVV1/Qwen3.6-27B-OBI")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.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(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

llama-cpp-python

How to use VECTORVV1/Qwen3.6-27B-OBI with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="VECTORVV1/Qwen3.6-27B-OBI",
	filename="gguf/qwen3.6-27b-obliteratus-Q4_K_M.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use VECTORVV1/Qwen3.6-27B-OBI with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf VECTORVV1/Qwen3.6-27B-OBI:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf VECTORVV1/Qwen3.6-27B-OBI:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf VECTORVV1/Qwen3.6-27B-OBI:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf VECTORVV1/Qwen3.6-27B-OBI:Q4_K_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf VECTORVV1/Qwen3.6-27B-OBI:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf VECTORVV1/Qwen3.6-27B-OBI:Q4_K_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf VECTORVV1/Qwen3.6-27B-OBI:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf VECTORVV1/Qwen3.6-27B-OBI:Q4_K_M

Use Docker

docker model run hf.co/VECTORVV1/Qwen3.6-27B-OBI:Q4_K_M

LM Studio
Jan

vLLM

How to use VECTORVV1/Qwen3.6-27B-OBI with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "VECTORVV1/Qwen3.6-27B-OBI"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "VECTORVV1/Qwen3.6-27B-OBI",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/VECTORVV1/Qwen3.6-27B-OBI:Q4_K_M

SGLang

How to use VECTORVV1/Qwen3.6-27B-OBI 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 "VECTORVV1/Qwen3.6-27B-OBI" \
    --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": "VECTORVV1/Qwen3.6-27B-OBI",
		"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 "VECTORVV1/Qwen3.6-27B-OBI" \
        --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": "VECTORVV1/Qwen3.6-27B-OBI",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use VECTORVV1/Qwen3.6-27B-OBI with Ollama:
```
ollama run hf.co/VECTORVV1/Qwen3.6-27B-OBI:Q4_K_M
```

Unsloth Studio new

How to use VECTORVV1/Qwen3.6-27B-OBI with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for VECTORVV1/Qwen3.6-27B-OBI to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for VECTORVV1/Qwen3.6-27B-OBI to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for VECTORVV1/Qwen3.6-27B-OBI to start chatting

Pi new

How to use VECTORVV1/Qwen3.6-27B-OBI with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf VECTORVV1/Qwen3.6-27B-OBI:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "VECTORVV1/Qwen3.6-27B-OBI:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use VECTORVV1/Qwen3.6-27B-OBI with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf VECTORVV1/Qwen3.6-27B-OBI:Q4_K_M

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default VECTORVV1/Qwen3.6-27B-OBI:Q4_K_M

Run Hermes

hermes

Docker Model Runner
How to use VECTORVV1/Qwen3.6-27B-OBI with Docker Model Runner:
```
docker model run hf.co/VECTORVV1/Qwen3.6-27B-OBI:Q4_K_M
```

Lemonade

How to use VECTORVV1/Qwen3.6-27B-OBI with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull VECTORVV1/Qwen3.6-27B-OBI:Q4_K_M

Run and chat with the model

lemonade run user.Qwen3.6-27B-OBI-Q4_K_M

List all available models

lemonade list

Qwen3.6-27B-OBI

File size: 2,538 Bytes

f284194

{
  "source": "cache/huggingface/hub/models--Qwen--Qwen3.6-27B/snapshots/6a9e13bd6fc8f0983b9b99948120bc37f49c13e9",
  "candidate": "outputs/qwen3.6-27b-alpha080-secondpass-n2-reg05-layercap15",
  "default_alpha": 0.895,
  "layer_alpha_rules": [],
  "key_alpha_rules": [
    {
      "pattern": "model\\.layers\\.(12|13|14|16)\\.linear_attn\\.(in_proj_a|in_proj_b|norm|conv1d|dt_bias|A_log).*",
      "alpha": 0.0
    },
    {
      "pattern": "model\\.layers\\.15\\.self_attn\\.(q_norm|k_norm)\\.weight",
      "alpha": 0.0
    },
    {
      "pattern": "model\\.layers\\.(12|13|14|15)\\.(input_layernorm|post_attention_layernorm)\\.weight",
      "alpha": 0.0
    },
    {
      "pattern": "model\\.layers\\.1\\.mlp\\.gate_proj\\.weight",
      "alpha": 0.0
    },
    {
      "pattern": "model\\.layers\\.(12|19)\\.mlp\\.up_proj\\.weight",
      "alpha": 0.0
    },
    {
      "pattern": "model\\.layers\\.(15|22)\\.mlp\\.gate_proj\\.weight",
      "alpha": 0.0
    },
    {
      "pattern": "model\\.layers\\.26\\.mlp\\.up_proj\\.weight",
      "alpha": 0.0
    },
    {
      "pattern": "model\\.layers\\.(9|16|27)\\.mlp\\.down_proj\\.weight",
      "alpha": 0.0
    }
  ],
  "formula": "source + alpha(key) * (candidate - source)",
  "source_key_prefix_translation": "model.* -> model.language_model.* when needed",
  "shards": [
    "model-00001-of-00028.safetensors",
    "model-00002-of-00028.safetensors",
    "model-00003-of-00028.safetensors",
    "model-00004-of-00028.safetensors",
    "model-00005-of-00028.safetensors",
    "model-00006-of-00028.safetensors",
    "model-00007-of-00028.safetensors",
    "model-00008-of-00028.safetensors",
    "model-00009-of-00028.safetensors",
    "model-00010-of-00028.safetensors",
    "model-00011-of-00028.safetensors",
    "model-00012-of-00028.safetensors",
    "model-00013-of-00028.safetensors",
    "model-00014-of-00028.safetensors",
    "model-00015-of-00028.safetensors",
    "model-00016-of-00028.safetensors",
    "model-00017-of-00028.safetensors",
    "model-00018-of-00028.safetensors",
    "model-00019-of-00028.safetensors",
    "model-00020-of-00028.safetensors",
    "model-00021-of-00028.safetensors",
    "model-00022-of-00028.safetensors",
    "model-00023-of-00028.safetensors",
    "model-00024-of-00028.safetensors",
    "model-00025-of-00028.safetensors",
    "model-00026-of-00028.safetensors",
    "model-00027-of-00028.safetensors",
    "model-00028-of-00028.safetensors"
  ],
  "unmatched_keys": [],
  "alpha_counts": {
    "0.895": 808,
    "0": 43
  }
}