Instructions to use giganeko/Qwopus3.6-27B-v2-AutoRound-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use giganeko/Qwopus3.6-27B-v2-AutoRound-GGUF with Transformers:

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

pipe = pipeline("image-text-to-text", model="giganeko/Qwopus3.6-27B-v2-AutoRound-GGUF")
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 AutoModel
model = AutoModel.from_pretrained("giganeko/Qwopus3.6-27B-v2-AutoRound-GGUF", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use giganeko/Qwopus3.6-27B-v2-AutoRound-GGUF with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf giganeko/Qwopus3.6-27B-v2-AutoRound-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf giganeko/Qwopus3.6-27B-v2-AutoRound-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf giganeko/Qwopus3.6-27B-v2-AutoRound-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf giganeko/Qwopus3.6-27B-v2-AutoRound-GGUF: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 giganeko/Qwopus3.6-27B-v2-AutoRound-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf giganeko/Qwopus3.6-27B-v2-AutoRound-GGUF: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 giganeko/Qwopus3.6-27B-v2-AutoRound-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf giganeko/Qwopus3.6-27B-v2-AutoRound-GGUF:Q4_K_M

Use Docker

docker model run hf.co/giganeko/Qwopus3.6-27B-v2-AutoRound-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use giganeko/Qwopus3.6-27B-v2-AutoRound-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "giganeko/Qwopus3.6-27B-v2-AutoRound-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "giganeko/Qwopus3.6-27B-v2-AutoRound-GGUF",
		"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/giganeko/Qwopus3.6-27B-v2-AutoRound-GGUF:Q4_K_M

SGLang

How to use giganeko/Qwopus3.6-27B-v2-AutoRound-GGUF 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 "giganeko/Qwopus3.6-27B-v2-AutoRound-GGUF" \
    --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": "giganeko/Qwopus3.6-27B-v2-AutoRound-GGUF",
		"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 "giganeko/Qwopus3.6-27B-v2-AutoRound-GGUF" \
        --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": "giganeko/Qwopus3.6-27B-v2-AutoRound-GGUF",
		"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"
						}
					}
				]
			}
		]
	}'

Ollama
How to use giganeko/Qwopus3.6-27B-v2-AutoRound-GGUF with Ollama:
```
ollama run hf.co/giganeko/Qwopus3.6-27B-v2-AutoRound-GGUF:Q4_K_M
```

Unsloth Studio

How to use giganeko/Qwopus3.6-27B-v2-AutoRound-GGUF 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 giganeko/Qwopus3.6-27B-v2-AutoRound-GGUF 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 giganeko/Qwopus3.6-27B-v2-AutoRound-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for giganeko/Qwopus3.6-27B-v2-AutoRound-GGUF to start chatting

How to use giganeko/Qwopus3.6-27B-v2-AutoRound-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf giganeko/Qwopus3.6-27B-v2-AutoRound-GGUF: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": "giganeko/Qwopus3.6-27B-v2-AutoRound-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

OpenClaw new

How to use giganeko/Qwopus3.6-27B-v2-AutoRound-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf giganeko/Qwopus3.6-27B-v2-AutoRound-GGUF:Q4_K_M

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "giganeko/Qwopus3.6-27B-v2-AutoRound-GGUF:Q4_K_M" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

Docker Model Runner
How to use giganeko/Qwopus3.6-27B-v2-AutoRound-GGUF with Docker Model Runner:
```
docker model run hf.co/giganeko/Qwopus3.6-27B-v2-AutoRound-GGUF:Q4_K_M
```

Lemonade

How to use giganeko/Qwopus3.6-27B-v2-AutoRound-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull giganeko/Qwopus3.6-27B-v2-AutoRound-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Qwopus3.6-27B-v2-AutoRound-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use giganeko/Qwopus3.6-27B-v2-AutoRound-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf giganeko/Qwopus3.6-27B-v2-AutoRound-GGUF: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 giganeko/Qwopus3.6-27B-v2-AutoRound-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

Qwopus3.6-27B-v2 - AutoRound Q4_K_M GGUF

Quantized with Intel AutoRound (SignRound optimization) and exported to GGUF for llama.cpp.

Files

File	Method	Description
`Qwopus3.6-27B-v2-Q4_K_M-iter0.gguf`	AutoRound RTN	Round-to-nearest, no optimization
`Qwopus3.6-27B-v2-Q4_K_M-iter100.gguf`	AutoRound iter=100	100 rounds of SignRound SGD optimization

Generation Commands

Iter 0 (RTN, fast)

AR_DISABLE_COPY_MTP_WEIGHTS=1 auto-round \
    --model Jackrong/Qwopus3.6-27B-v2 \
    --scheme W4A16 \
    --format "gguf:q4_k_m" \
    --iters 0 \
    --output_dir ./output

Iter 100 (SignRound optimized, ~1h on RTX PRO 6000)

AR_DISABLE_COPY_MTP_WEIGHTS=1 auto-round \
    --model Jackrong/Qwopus3.6-27B-v2 \
    --scheme W4A16 \
    --format "gguf:q4_k_m" \
    --iters 100 \
    --output_dir ./output

KL Divergence Evaluation

Tested on wikitext-2-raw-v1 (145 chunks, ctx=2048, batch=2048, ngl=99, Blackwell CUDA).

Metric	Q8_0 (Ref)	Jackrong Q4_K_M	AR iter=0	AR iter=100
PPL	6.180	6.380	6.344	6.207
PPL vs Q8_0	—	+3.24%	+2.66%	+0.44%
Mean KL Divergence	—	0.0494	0.0483	0.0435
Median KL Divergence	—	0.0083	0.0080	0.0075
RMS Δp	—	5.51%	5.45%	5.13%
Same Top-p	—	93.57%	93.61%	93.93%
Model Size	27 GB	16 GB	16 GB	16 GB

Key finding: AutoRound iter=100 achieves near-lossless Q4_K_M quantization with only 0.44% PPL degradation vs Q8_0, significantly outperforming standard llama.cpp Q4_K_M (3.24% degradation).

KL Divergence Commands

# Step 1: Generate base logits (Q8_0)
llama-perplexity -m Q8_0.gguf -f wiki.test.raw \
    --save-all-logits q8_0_base.logits -ngl 99 -c 2048 -b 2048

# Step 2: Compute KL divergence
llama-perplexity -m Q4_K_M.gguf -f wiki.test.raw \
    --kl-divergence --kl-divergence-base q8_0_base.logits \
    -ngl 99 -c 2048 -b 2048

Original README from Jackrong/Qwopus3.6-27B-v2-GGUF

(Content below is from the original model card.)

🪐 Qwopus3.6-27B-v2

SFT Release

Reasoning-Enhanced Dense Language Model Fine-Tuned on Qwen3.6-27B

🧬 Trace Inversion & Negentropy 🧠 27B Parameters 🔥 3-Stage Curriculum SFT 🛠️ Vision & Tool-use Support

💡 What is Qwopus3.6-27B-v2?

🪐 Qwopus3.6-27B-v2 is a reasoning-enhanced dense language model built on Qwen3.6-27B-base via the Trace Inversion & Negentropy framework. It's trained on ~14K highly informative samples derived from Claude Opus 4.x reasoning traces, following a 3-stage curriculum spanning context expansion (32K→128K), reasoning strengthening, and tool-use integration.

Downloads last month: 16

GGUF

Model size

27B params

Architecture

qwen35

Hardware compatibility

4-bit

Model tree for giganeko/Qwopus3.6-27B-v2-AutoRound-GGUF

Base model

Jackrong/Qwopus3.6-27B-v2

Quantized

(59)

this model