Instructions to use qwertt2005/Qwen3.5-9B-FineTuned with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use qwertt2005/Qwen3.5-9B-FineTuned 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 qwertt2005/Qwen3.5-9B-FineTuned:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf qwertt2005/Qwen3.5-9B-FineTuned:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf qwertt2005/Qwen3.5-9B-FineTuned:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf qwertt2005/Qwen3.5-9B-FineTuned: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 qwertt2005/Qwen3.5-9B-FineTuned:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf qwertt2005/Qwen3.5-9B-FineTuned: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 qwertt2005/Qwen3.5-9B-FineTuned:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf qwertt2005/Qwen3.5-9B-FineTuned:Q4_K_M

Use Docker

docker model run hf.co/qwertt2005/Qwen3.5-9B-FineTuned:Q4_K_M

LM Studio
Jan

vLLM

How to use qwertt2005/Qwen3.5-9B-FineTuned with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "qwertt2005/Qwen3.5-9B-FineTuned"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "qwertt2005/Qwen3.5-9B-FineTuned",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/qwertt2005/Qwen3.5-9B-FineTuned:Q4_K_M

Ollama
How to use qwertt2005/Qwen3.5-9B-FineTuned with Ollama:
```
ollama run hf.co/qwertt2005/Qwen3.5-9B-FineTuned:Q4_K_M
```
Unsloth Desktop

How to use qwertt2005/Qwen3.5-9B-FineTuned with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf qwertt2005/Qwen3.5-9B-FineTuned:Q4_K_M

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": "qwertt2005/Qwen3.5-9B-FineTuned:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use qwertt2005/Qwen3.5-9B-FineTuned with Docker Model Runner:
```
docker model run hf.co/qwertt2005/Qwen3.5-9B-FineTuned:Q4_K_M
```

Lemonade

How to use qwertt2005/Qwen3.5-9B-FineTuned with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull qwertt2005/Qwen3.5-9B-FineTuned:Q4_K_M

Run and chat with the model

lemonade run user.Qwen3.5-9B-FineTuned-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use qwertt2005/Qwen3.5-9B-FineTuned with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf qwertt2005/Qwen3.5-9B-FineTuned: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 qwertt2005/Qwen3.5-9B-FineTuned:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use qwertt2005/Qwen3.5-9B-FineTuned with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf qwertt2005/Qwen3.5-9B-FineTuned: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 "qwertt2005/Qwen3.5-9B-FineTuned: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"

Qwen3.5-9B Fine-Tuned (GGUF & LoRA)

Fine-tuned version of Qwen3.5-9B trained on NVIDIA H100 80GB across 159,082 curated samples blending reasoning, conversational alignment, and domain knowledge.

📊 Training Mixture (159,082 samples)

HuggingFaceTB/smoltalk (50,000 samples) - Conversational & Alignment SFT
open-r1/OpenR1-Math-220k (49,999 samples) - Step-by-step mathematical reasoning ( traces)
HuggingFaceFW/fineweb (19,995 samples) - High-quality web corpus
OpenAssistant/oasst2 (14,088 samples) - Human-rated RLHF multi-turn data
teknium/OpenHermes-2.5 (25,000 samples) - GPT-4 quality instruction following

🚀 Quick Start with Ollama

Run directly on your local machine:

📦 Files Included

(5.4 GB) - Fast 4-bit Medium quantization
(9.2 GB) - High precision 8-bit quantization
(18.0 GB) - Full 16-bit precision GGUF
- PEFT LoRA adapter files

Downloads last month: 96

GGUF

Model size

9B params

Architecture

qwen35

Hardware compatibility

4-bit

8-bit

16-bit

Model tree for qwertt2005/Qwen3.5-9B-FineTuned

Base model

Qwen/Qwen3.5-9B-Base

Finetuned

Qwen/Qwen3.5-9B

Finetuned

unsloth/Qwen3.5-9B

Quantized

(32)

this model