Instructions to use CoNDeNse-AI/Claude4.6-Qwen3-1.7B-CoNDeNse-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use CoNDeNse-AI/Claude4.6-Qwen3-1.7B-CoNDeNse-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="CoNDeNse-AI/Claude4.6-Qwen3-1.7B-CoNDeNse-GGUF",
	filename="Q2_K/Claude4.6-Qwen3-1.7B-CoNDeNse.Q2_K.gguf",
)

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

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use CoNDeNse-AI/Claude4.6-Qwen3-1.7B-CoNDeNse-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf CoNDeNse-AI/Claude4.6-Qwen3-1.7B-CoNDeNse-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf CoNDeNse-AI/Claude4.6-Qwen3-1.7B-CoNDeNse-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf CoNDeNse-AI/Claude4.6-Qwen3-1.7B-CoNDeNse-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf CoNDeNse-AI/Claude4.6-Qwen3-1.7B-CoNDeNse-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 CoNDeNse-AI/Claude4.6-Qwen3-1.7B-CoNDeNse-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf CoNDeNse-AI/Claude4.6-Qwen3-1.7B-CoNDeNse-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 CoNDeNse-AI/Claude4.6-Qwen3-1.7B-CoNDeNse-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf CoNDeNse-AI/Claude4.6-Qwen3-1.7B-CoNDeNse-GGUF:Q4_K_M

Use Docker

docker model run hf.co/CoNDeNse-AI/Claude4.6-Qwen3-1.7B-CoNDeNse-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use CoNDeNse-AI/Claude4.6-Qwen3-1.7B-CoNDeNse-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "CoNDeNse-AI/Claude4.6-Qwen3-1.7B-CoNDeNse-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": "CoNDeNse-AI/Claude4.6-Qwen3-1.7B-CoNDeNse-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/CoNDeNse-AI/Claude4.6-Qwen3-1.7B-CoNDeNse-GGUF:Q4_K_M

Ollama
How to use CoNDeNse-AI/Claude4.6-Qwen3-1.7B-CoNDeNse-GGUF with Ollama:
```
ollama run hf.co/CoNDeNse-AI/Claude4.6-Qwen3-1.7B-CoNDeNse-GGUF:Q4_K_M
```

Unsloth Studio

How to use CoNDeNse-AI/Claude4.6-Qwen3-1.7B-CoNDeNse-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 CoNDeNse-AI/Claude4.6-Qwen3-1.7B-CoNDeNse-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 CoNDeNse-AI/Claude4.6-Qwen3-1.7B-CoNDeNse-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for CoNDeNse-AI/Claude4.6-Qwen3-1.7B-CoNDeNse-GGUF to start chatting

How to use CoNDeNse-AI/Claude4.6-Qwen3-1.7B-CoNDeNse-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf CoNDeNse-AI/Claude4.6-Qwen3-1.7B-CoNDeNse-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": "CoNDeNse-AI/Claude4.6-Qwen3-1.7B-CoNDeNse-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use CoNDeNse-AI/Claude4.6-Qwen3-1.7B-CoNDeNse-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf CoNDeNse-AI/Claude4.6-Qwen3-1.7B-CoNDeNse-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 CoNDeNse-AI/Claude4.6-Qwen3-1.7B-CoNDeNse-GGUF:Q4_K_M

Run Hermes

hermes

Docker Model Runner
How to use CoNDeNse-AI/Claude4.6-Qwen3-1.7B-CoNDeNse-GGUF with Docker Model Runner:
```
docker model run hf.co/CoNDeNse-AI/Claude4.6-Qwen3-1.7B-CoNDeNse-GGUF:Q4_K_M
```

Lemonade

How to use CoNDeNse-AI/Claude4.6-Qwen3-1.7B-CoNDeNse-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull CoNDeNse-AI/Claude4.6-Qwen3-1.7B-CoNDeNse-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Claude4.6-Qwen3-1.7B-CoNDeNse-GGUF-Q4_K_M

List all available models

lemonade list

Claude4.6-Qwen3-1.7B-CoNDeNse-GGUF

GGUF quantizations of Claude4.6-Qwen3-1.7B-CoNDeNse by CoNDeNse-AI

Available Quantizations

Quant	File Type	Recommended Use
Q2_K	Ultra-small	Maximum speed / very low RAM
Q3_K_M	Lightweight	Good quality-to-size ratio
Q4_K_M	Balanced	Best general-use quant
Q5_K_M	High quality	Strong reasoning retention
Q6_K	Near-lossless	Best quality while staying quantized

Model Details

Base Model: Qwen3-1.7B
Architecture: Qwen3
Fine-tuned by: CoNDeNse-AI
Format: GGUF
Compatibility:
- LM Studio
- llama.cpp
- Ollama
- KoboldCpp
- Jan
- Text Generation WebUI

Quantization Overview

Q2_K

Optimized for extremely low memory usage and fast inference on weak hardware.

Q3_K_M

Recommended lightweight daily-driver quant with solid quality retention.

Q4_K_M

Best balance between reasoning quality, speed, and size.

Q5_K_M

High-quality quant with noticeably stronger reasoning and response consistency.

Q6_K

Near-full precision experience with excellent output quality while remaining efficient.

Example llama.cpp Usage

./llama-cli \
  -m Claude4.6-Qwen3-1.7B-Q6_K.gguf \
  -p "Explain quantum tunneling like I'm 12."

Recommended Settings

Setting	Value
Temperature	0.6 - 0.8
Top-p	0.9
Context Length	8k+
Repeat Penalty	1.05

Notes

This model is optimized for:

reasoning
search-aware responses
compact inference
edge deployment
efficient local usage

Performance may vary depending on backend, prompt format, and quantization level.

Credits

License

Please follow the original Qwen license and usage terms.

Downloads last month: 682

GGUF

Model size

2B params

Architecture

qwen3

Hardware compatibility

2-bit

3-bit

4-bit

5-bit

6-bit

Model tree for CoNDeNse-AI/Claude4.6-Qwen3-1.7B-CoNDeNse-GGUF

Base model

Qwen/Qwen3-1.7B-Base

Finetuned

Qwen/Qwen3-1.7B

Quantized

(281)

this model

Collection including CoNDeNse-AI/Claude4.6-Qwen3-1.7B-CoNDeNse-GGUF

Claude CoNDeNses

Collection

3 items • Updated 13 days ago • 1