Instructions to use ortexvortex/Qwen3.5-4B-fnvdecomp-r1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ortexvortex/Qwen3.5-4B-fnvdecomp-r1 with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3.5-4B")
model = PeftModel.from_pretrained(base_model, "ortexvortex/Qwen3.5-4B-fnvdecomp-r1")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use ortexvortex/Qwen3.5-4B-fnvdecomp-r1 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 ortexvortex/Qwen3.5-4B-fnvdecomp-r1:Q8_0
# Run inference directly in the terminal:
llama cli -hf ortexvortex/Qwen3.5-4B-fnvdecomp-r1:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf ortexvortex/Qwen3.5-4B-fnvdecomp-r1:Q8_0
# Run inference directly in the terminal:
llama cli -hf ortexvortex/Qwen3.5-4B-fnvdecomp-r1:Q8_0

Build from source code

git clone https://github.com/ggml-org/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-app
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama serve -hf ortexvortex/Qwen3.5-4B-fnvdecomp-r1:Q8_0
# Run inference directly in the terminal:
./build/bin/llama cli -hf ortexvortex/Qwen3.5-4B-fnvdecomp-r1:Q8_0

Use Docker

docker model run hf.co/ortexvortex/Qwen3.5-4B-fnvdecomp-r1:Q8_0

Llama new
LM Studio
Jan

vLLM

How to use ortexvortex/Qwen3.5-4B-fnvdecomp-r1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ortexvortex/Qwen3.5-4B-fnvdecomp-r1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ortexvortex/Qwen3.5-4B-fnvdecomp-r1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ortexvortex/Qwen3.5-4B-fnvdecomp-r1:Q8_0

Ollama
How to use ortexvortex/Qwen3.5-4B-fnvdecomp-r1 with Ollama:
```
ollama run hf.co/ortexvortex/Qwen3.5-4B-fnvdecomp-r1:Q8_0
```
Unsloth Desktop

How to use ortexvortex/Qwen3.5-4B-fnvdecomp-r1 with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ortexvortex/Qwen3.5-4B-fnvdecomp-r1:Q8_0

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "ortexvortex/Qwen3.5-4B-fnvdecomp-r1:Q8_0"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use ortexvortex/Qwen3.5-4B-fnvdecomp-r1 with Docker Model Runner:
```
docker model run hf.co/ortexvortex/Qwen3.5-4B-fnvdecomp-r1:Q8_0
```

Lemonade

How to use ortexvortex/Qwen3.5-4B-fnvdecomp-r1 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull ortexvortex/Qwen3.5-4B-fnvdecomp-r1:Q8_0

Run and chat with the model

lemonade run user.Qwen3.5-4B-fnvdecomp-r1-Q8_0

List all available models

lemonade list

Hermes Agent

How to use ortexvortex/Qwen3.5-4B-fnvdecomp-r1 with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ortexvortex/Qwen3.5-4B-fnvdecomp-r1:Q8_0

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 ortexvortex/Qwen3.5-4B-fnvdecomp-r1:Q8_0

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use ortexvortex/Qwen3.5-4B-fnvdecomp-r1 with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ortexvortex/Qwen3.5-4B-fnvdecomp-r1:Q8_0

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 "ortexvortex/Qwen3.5-4B-fnvdecomp-r1:Q8_0" \
  --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"

Qwen3.5-4B-fnvdecomp-r1

File size: 2,146 Bytes

80310ca

{
 "ALL": {
  "greedy_raw": 0.004016064257028112,
  "greedy": 0.004016064257028112,
  "greedy+solve": 0.004016064257028112,
  "pass@1": 0.0035140562248995983,
  "pass@4": 0.013195639701663797,
  "pass@n": 0.024096385542168676,
  "any": 0.024096385542168676,
  "compiles": 0.10040160642570281,
  "n": 249
 },
 "<16": {
  "greedy_raw": 0.022727272727272728,
  "greedy": 0.022727272727272728,
  "greedy+solve": 0.022727272727272728,
  "pass@1": 0.019886363636363636,
  "pass@4": 0.07467532467532467,
  "pass@n": 0.13636363636363635,
  "any": 0.13636363636363635,
  "compiles": 0.20454545454545456,
  "n": 44
 },
 "/Od": {
  "greedy_raw": 0.011904761904761904,
  "greedy": 0.011904761904761904,
  "greedy+solve": 0.011904761904761904,
  "pass@1": 0.008928571428571428,
  "pass@4": 0.033163265306122444,
  "pass@n": 0.05952380952380952,
  "any": 0.05952380952380952,
  "compiles": 0.047619047619047616,
  "n": 84
 },
 "/O2": {
  "greedy_raw": 0.0,
  "greedy": 0.0,
  "greedy+solve": 0.0,
  "pass@1": 0.0007575757575757576,
  "pass@4": 0.0030303030303030303,
  "pass@n": 0.006060606060606061,
  "any": 0.006060606060606061,
  "compiles": 0.12727272727272726,
  "n": 165
 },
 "novel": {
  "greedy_raw": 0.0,
  "greedy": 0.0,
  "greedy+solve": 0.0,
  "pass@1": 0.0027292576419213972,
  "pass@4": 0.009981285090455396,
  "pass@n": 0.017467248908296942,
  "any": 0.017467248908296942,
  "compiles": 0.09606986899563319,
  "n": 229
 },
 "16-63": {
  "greedy_raw": 0.0,
  "greedy": 0.0,
  "greedy+solve": 0.0,
  "pass@1": 0.0,
  "pass@4": 0.0,
  "pass@n": 0.0,
  "any": 0.0,
  "compiles": 0.15789473684210525,
  "n": 57
 },
 ">=1024": {
  "greedy_raw": 0.0,
  "greedy": 0.0,
  "greedy+solve": 0.0,
  "pass@1": 0.0,
  "pass@4": 0.0,
  "pass@n": 0.0,
  "any": 0.0,
  "compiles": 0.0,
  "n": 5
 },
 "64-255": {
  "greedy_raw": 0.0,
  "greedy": 0.0,
  "greedy+solve": 0.0,
  "pass@1": 0.0,
  "pass@4": 0.0,
  "pass@n": 0.0,
  "any": 0.0,
  "compiles": 0.05343511450381679,
  "n": 131
 },
 "256-1023": {
  "greedy_raw": 0.0,
  "greedy": 0.0,
  "greedy+solve": 0.0,
  "pass@1": 0.0,
  "pass@4": 0.0,
  "pass@n": 0.0,
  "any": 0.0,
  "compiles": 0.0,
  "n": 12
 }
}