Instructions to use shaban2024/Qwen3.5-9B-BOS-Q8-NonThinking with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use shaban2024/Qwen3.5-9B-BOS-Q8-NonThinking 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 shaban2024/Qwen3.5-9B-BOS-Q8-NonThinking
# Run inference directly in the terminal:
llama cli -hf shaban2024/Qwen3.5-9B-BOS-Q8-NonThinking

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf shaban2024/Qwen3.5-9B-BOS-Q8-NonThinking
# Run inference directly in the terminal:
llama cli -hf shaban2024/Qwen3.5-9B-BOS-Q8-NonThinking

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 shaban2024/Qwen3.5-9B-BOS-Q8-NonThinking
# Run inference directly in the terminal:
./llama-cli -hf shaban2024/Qwen3.5-9B-BOS-Q8-NonThinking

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 shaban2024/Qwen3.5-9B-BOS-Q8-NonThinking
# Run inference directly in the terminal:
./build/bin/llama-cli -hf shaban2024/Qwen3.5-9B-BOS-Q8-NonThinking

Use Docker

docker model run hf.co/shaban2024/Qwen3.5-9B-BOS-Q8-NonThinking

LM Studio
Jan

vLLM

How to use shaban2024/Qwen3.5-9B-BOS-Q8-NonThinking with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "shaban2024/Qwen3.5-9B-BOS-Q8-NonThinking"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "shaban2024/Qwen3.5-9B-BOS-Q8-NonThinking",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/shaban2024/Qwen3.5-9B-BOS-Q8-NonThinking

Ollama
How to use shaban2024/Qwen3.5-9B-BOS-Q8-NonThinking with Ollama:
```
ollama run hf.co/shaban2024/Qwen3.5-9B-BOS-Q8-NonThinking
```
Unsloth Desktop

How to use shaban2024/Qwen3.5-9B-BOS-Q8-NonThinking with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf shaban2024/Qwen3.5-9B-BOS-Q8-NonThinking

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": "shaban2024/Qwen3.5-9B-BOS-Q8-NonThinking"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use shaban2024/Qwen3.5-9B-BOS-Q8-NonThinking with Docker Model Runner:
```
docker model run hf.co/shaban2024/Qwen3.5-9B-BOS-Q8-NonThinking
```

Lemonade

How to use shaban2024/Qwen3.5-9B-BOS-Q8-NonThinking with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull shaban2024/Qwen3.5-9B-BOS-Q8-NonThinking

Run and chat with the model

lemonade run user.Qwen3.5-9B-BOS-Q8-NonThinking-{{QUANT_TAG}}

List all available models

lemonade list

Hermes Agent

How to use shaban2024/Qwen3.5-9B-BOS-Q8-NonThinking with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf shaban2024/Qwen3.5-9B-BOS-Q8-NonThinking

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 shaban2024/Qwen3.5-9B-BOS-Q8-NonThinking

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use shaban2024/Qwen3.5-9B-BOS-Q8-NonThinking with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf shaban2024/Qwen3.5-9B-BOS-Q8-NonThinking

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 "shaban2024/Qwen3.5-9B-BOS-Q8-NonThinking" \
  --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"

AgentMujo Q8 9B (joint-01 u toku) — najveći bosanski Linux agent

Cilj: baza Qwen3.5-9B (multimodalna, text tower ~9B) + LoRA joint SFT (QLoRA 4bit, mix v0.32) + GGUF Q8_0. Jedan GGUF za oba profila (think: true/false).

Baza: Qwen/Qwen3.5-9B @ c20223623 (Apache-2.0; text: hidden 4096, 32 sloja, vocab 248320, ctx 262k; + vision tower)
Trening: QLoRA r16/alpha32, Kaggle T4; joint-01 u toku (1191 uzoraka, seq 4096, 1 epoha); framework repo
Status: repo kreiran 2026-09-29; v0.1 (prvi Q8) stiže nakon joint-01 treninga + mergea + kvantizacije + bench gatea. Do tada ovdje nema model fajla — samo kartica.

Upotreba (Ollama, kad v0.1 stigne)

ollama create agentmujo-9b-q8 -f Modelfile
ollama run agentmujo-9b-q8 "Radi li nginx servis?"

Benchmark

Po AgentMujo-Bench v0.5 gateu prije svakog releasea (kao 2B/4B trag). Rezultati stižu sa v0.1.

Ograničenja

Poznata prije v0.1: merge 9B bf16 traži ~36GB RAM (rješenje u toku), multimodalni GGUF convert neprovjeren u llama.cpp.

Licenca

Apache-2.0 (baza + framework).

Downloads last month: 1,081

GGUF

Model size

9B params

Architecture

qwen35

Hardware compatibility

We're not able to determine the quantization variants.

View all variants

Model tree for shaban2024/Qwen3.5-9B-BOS-Q8-NonThinking

Base model

Qwen/Qwen3.5-9B-Base

Finetuned

Qwen/Qwen3.5-9B

Quantized

(543)

this model