Instructions to use islameissa/Qwen3.6-27B_IQ4_GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use islameissa/Qwen3.6-27B_IQ4_GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="islameissa/Qwen3.6-27B_IQ4_GGUF",
	filename="Qwen3.6-27b-IQ4_NL.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use islameissa/Qwen3.6-27B_IQ4_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 islameissa/Qwen3.6-27B_IQ4_GGUF:IQ4_NL
# Run inference directly in the terminal:
llama cli -hf islameissa/Qwen3.6-27B_IQ4_GGUF:IQ4_NL

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf islameissa/Qwen3.6-27B_IQ4_GGUF:IQ4_NL
# Run inference directly in the terminal:
llama cli -hf islameissa/Qwen3.6-27B_IQ4_GGUF:IQ4_NL

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 islameissa/Qwen3.6-27B_IQ4_GGUF:IQ4_NL
# Run inference directly in the terminal:
./llama-cli -hf islameissa/Qwen3.6-27B_IQ4_GGUF:IQ4_NL

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 islameissa/Qwen3.6-27B_IQ4_GGUF:IQ4_NL
# Run inference directly in the terminal:
./build/bin/llama-cli -hf islameissa/Qwen3.6-27B_IQ4_GGUF:IQ4_NL

Use Docker

docker model run hf.co/islameissa/Qwen3.6-27B_IQ4_GGUF:IQ4_NL

LM Studio
Jan
Ollama
How to use islameissa/Qwen3.6-27B_IQ4_GGUF with Ollama:
```
ollama run hf.co/islameissa/Qwen3.6-27B_IQ4_GGUF:IQ4_NL
```

Unsloth Studio

How to use islameissa/Qwen3.6-27B_IQ4_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 islameissa/Qwen3.6-27B_IQ4_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 islameissa/Qwen3.6-27B_IQ4_GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for islameissa/Qwen3.6-27B_IQ4_GGUF to start chatting

How to use islameissa/Qwen3.6-27B_IQ4_GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf islameissa/Qwen3.6-27B_IQ4_GGUF:IQ4_NL

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": "islameissa/Qwen3.6-27B_IQ4_GGUF:IQ4_NL"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use islameissa/Qwen3.6-27B_IQ4_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 islameissa/Qwen3.6-27B_IQ4_GGUF:IQ4_NL

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 islameissa/Qwen3.6-27B_IQ4_GGUF:IQ4_NL

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use islameissa/Qwen3.6-27B_IQ4_GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf islameissa/Qwen3.6-27B_IQ4_GGUF:IQ4_NL

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 "islameissa/Qwen3.6-27B_IQ4_GGUF:IQ4_NL" \
  --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 islameissa/Qwen3.6-27B_IQ4_GGUF with Docker Model Runner:
```
docker model run hf.co/islameissa/Qwen3.6-27B_IQ4_GGUF:IQ4_NL
```

Lemonade

How to use islameissa/Qwen3.6-27B_IQ4_GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull islameissa/Qwen3.6-27B_IQ4_GGUF:IQ4_NL

Run and chat with the model

lemonade run user.Qwen3.6-27B_IQ4_GGUF-IQ4_NL

List all available models

lemonade list

Qwen 3.6-27B Custom Imatrix Quants (IE-Series)

This repository provides highly optimized GGUF quantizations of Qwen 3.6-27B using advanced imatrix (Importance Matrix) calibration.

While the initial Q4_0-IE provided a solid baseline, the newly developed Q4H variant represents a significant jump in quality, outperforming standard Q4_K_M and Q4_1 quants in both perplexity and stability (KLD P99).

Methodology: The ActivEnergy "IE" Calibration

These quants were generated using a custom-curated calibration dataset. I began with the Bartowski Calibration v5 text as a foundation and integrated modifications designed to better capture high-precision logic and nuanced language patterns.

Tool: llama.cpp / llama-quantize
Calibration: Hybrid IE-Custom + some of Bartowski v5 calibration text
Primary Objective: Minimize KLD (Kullback–Leibler Divergence) outliers, particularly in the P99 range, to ensure model stability during long-form generation.

Performance & Compatibility

Speed: Tested on RTX 5090, achieving approximately 60 TPS.
Agents: Fully compatible with multi-agent frameworks like OpenClaw.

Evaluation Report: ActivEnergy Quantizer

The following metrics were derived using the Qwen 3.6-27B architecture as the base. The IE-Q4H variant is the current top recommendation for users seeking the best balance between size and logical fidelity.

Comparison Table

Rank	Variant	File Size	Mean PPL	KLD Mean	KLD Median	KLD P99
--	F16 Baseline	50.1 GB	2.0878	N/A	N/A	N/A
1	IE-Qwen36-27b-Q4H	16.9 GB	2.0844	0.010602	0.002350	0.084462
2	Unsloth-UD-Q4_K_XL	16.4 GB	2.0716	0.008079	0.002192	0.146924
3	IE-IQ4_NL	14.7 GB	2.1352	0.019256	0.002533	0.175252
4	IE-IQ4_XS	14.0 GB	2.1263	0.018374	0.002328	0.184353
5	Bartowski-Q4_1	16.4 GB	2.0844	0.012945	0.002636	0.219050

Happy Inference! Please leave a comment with your results or any testing data.

Downloads last month: 137

GGUF

Model size

27B params

Architecture

qwen35

Hardware compatibility

4-bit

View +1 variant

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for islameissa/Qwen3.6-27B_IQ4_GGUF

Base model

Qwen/Qwen3.6-27B

Quantized

(590)

this model