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

Notebooks
Google Colab
Kaggle
Local Apps Settings

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

Install from WinGet (Windows)

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

Use Docker

docker model run hf.co/batiai/Qwen3.5-9B-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use batiai/Qwen3.5-9B-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "batiai/Qwen3.5-9B-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": "batiai/Qwen3.5-9B-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/batiai/Qwen3.5-9B-GGUF:Q4_K_M

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

How to use batiai/Qwen3.5-9B-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf batiai/Qwen3.5-9B-GGUF: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": "batiai/Qwen3.5-9B-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

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

Lemonade

How to use batiai/Qwen3.5-9B-GGUF with Lemonade:

Pull the model

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

Run and chat with the model

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

List all available models

lemonade list

Hermes Agent

How to use batiai/Qwen3.5-9B-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 batiai/Qwen3.5-9B-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 batiai/Qwen3.5-9B-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use batiai/Qwen3.5-9B-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf batiai/Qwen3.5-9B-GGUF: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 "batiai/Qwen3.5-9B-GGUF: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-GGUF / README.md

hero775

Add M4 Max 128GB measured benchmarks

17a2b12 verified 5 months ago

preview code

Raw History Blame Contribute Delete

2.78 kB

	---
	language:
	- en
	- ko
	- ja
	- zh
	license: apache-2.0
	tags:
	- gguf
	- qwen
	- quantized
	- apple-silicon
	- ollama
	- batiai
	- on-device
	- 9b
	base_model: Qwen/Qwen3.5-9B
	pipeline_tag: text-generation
	library_name: llama.cpp
	---

	# Qwen 3.5 9B GGUF — Quantized by BatiAI

	<p align="center">
	<a href="https://flow.bati.ai"><img src="https://img.shields.io/badge/BatiFlow-macOS%20AI%20Automation-blue?style=for-the-badge&logo=apple" alt="BatiFlow"></a>
	<a href="https://ollama.com/batiai/qwen3.5-9b"><img src="https://img.shields.io/badge/Ollama-batiai%2Fqwen3.5--9b-green?style=for-the-badge" alt="Ollama"></a>
	</p>

	> Quantizations of Qwen 3.5 9B for on-device AI on Mac.
	> Built and verified by [BatiAI](https://bati.ai) for [BatiFlow](https://flow.bati.ai).

	## Why Qwen 3.5 9B?

	- Strong tool calling and JSON structured output
	- Multilingual (en, ko, ja, zh) — solid Korean
	- Apache 2.0 — commercial-friendly
	- Fits 16GB Mac with Q4

	## Quick Start

	```bash
	ollama pull batiai/qwen3.5-9b:q4
	```

	## Available Quantizations

	\| Quant \| Size \| VRAM target \| Recommended For \|
	\|-------\|------\|-------------\|-----------------\|
	\| Q4_K_M \| 5.2GB \| ~7GB \| 16GB Mac \|
	\| Q6_K \| 7.5GB \| ~10GB \| 24GB+ Mac \|

	## RAM Requirements

	\| Your Mac RAM \| Q4 (5.2GB) \| Q6 (7.5GB) \|
	\|-------------\|-----------\|-----------\|
	\| 16GB \| ✅ Recommended \| ⚠️ Tight \|
	\| 24GB+ \| ✅ \| ✅ Headroom \|

	## Model Comparison

	\| Your Mac \| Best Pick \|
	\|----------\|-----------\|
	\| 16GB \| `batiai/qwen3.5-9b:q4` (this) or `batiai/gemma4-e4b:q4` \|
	\| 24GB \| `batiai/gemma4-26b:iq4` \|
	\| 32GB \| `batiai/nemotron3-nano:iq4` \|
	\| 36GB+ \| `batiai/qwen3.6-35b:iq4` \|

	## Why BatiAI?

	- Quantized from [official Qwen weights](https://huggingface.co/Qwen/Qwen3.5-9B)
	- Verified on real Mac hardware
	- BatiAI metadata signed (`general.author=BatiAI`)
	- Tool calling + Korean validated

	## Technical Details

	- Original Model: [Qwen/Qwen3.5-9B](https://huggingface.co/Qwen/Qwen3.5-9B)
	- License: Apache 2.0
	- Quantized with: [llama.cpp](https://github.com/ggml-org/llama.cpp)
	- Quantized by: [BatiAI](https://bati.ai)

	## About BatiFlow

	[BatiFlow](https://flow.bati.ai) — free, on-device AI automation for Mac. 5MB app, 100% local, unlimited.

	## Benchmarks

	<!-- BENCH-START -->

	\| Machine \| Quant \| Cold start \| Prompt eval \| Token gen \| Tested \|
	\|---------\|-------\|------------\|-------------\|-----------\|--------\|
	\| Mac mini M4 16GB \| Q4_K_M \| —s \| — t/s \| — t/s \| 2026-05-01 \|
	\| Mac mini M4 16GB \| Q6_K \| —s \| — t/s \| — t/s \| 2026-05-01 \|
	\| MacBook Pro M4 Max 128GB \| Q4_K_M \| 2.274s \| 272.23 t/s \| 46.08 t/s \| 2026-05-03 \|
	\| MacBook Pro M4 Max 128GB \| Q6_K \| 2.552s \| 304.85 t/s \| 38.54 t/s \| 2026-05-03 \|

	<!-- BENCH-END -->