Instructions to use tarruda/Qwen3.5-397B-A17B-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use tarruda/Qwen3.5-397B-A17B-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="tarruda/Qwen3.5-397B-A17B-GGUF",
	filename="IQ3_XXS/Qwen3.5-397B-A17B-IQ3_XXS-00001-of-00004.gguf",
)

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

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use tarruda/Qwen3.5-397B-A17B-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf tarruda/Qwen3.5-397B-A17B-GGUF:IQ3_XXS
# Run inference directly in the terminal:
llama-cli -hf tarruda/Qwen3.5-397B-A17B-GGUF:IQ3_XXS

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf tarruda/Qwen3.5-397B-A17B-GGUF:IQ3_XXS
# Run inference directly in the terminal:
llama-cli -hf tarruda/Qwen3.5-397B-A17B-GGUF:IQ3_XXS

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 tarruda/Qwen3.5-397B-A17B-GGUF:IQ3_XXS
# Run inference directly in the terminal:
./llama-cli -hf tarruda/Qwen3.5-397B-A17B-GGUF:IQ3_XXS

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 tarruda/Qwen3.5-397B-A17B-GGUF:IQ3_XXS
# Run inference directly in the terminal:
./build/bin/llama-cli -hf tarruda/Qwen3.5-397B-A17B-GGUF:IQ3_XXS

Use Docker

docker model run hf.co/tarruda/Qwen3.5-397B-A17B-GGUF:IQ3_XXS

LM Studio
Jan

vLLM

How to use tarruda/Qwen3.5-397B-A17B-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "tarruda/Qwen3.5-397B-A17B-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": "tarruda/Qwen3.5-397B-A17B-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/tarruda/Qwen3.5-397B-A17B-GGUF:IQ3_XXS

Ollama
How to use tarruda/Qwen3.5-397B-A17B-GGUF with Ollama:
```
ollama run hf.co/tarruda/Qwen3.5-397B-A17B-GGUF:IQ3_XXS
```

Unsloth Studio new

How to use tarruda/Qwen3.5-397B-A17B-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 tarruda/Qwen3.5-397B-A17B-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 tarruda/Qwen3.5-397B-A17B-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for tarruda/Qwen3.5-397B-A17B-GGUF to start chatting

Pi new

How to use tarruda/Qwen3.5-397B-A17B-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf tarruda/Qwen3.5-397B-A17B-GGUF:IQ3_XXS

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": "tarruda/Qwen3.5-397B-A17B-GGUF:IQ3_XXS"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use tarruda/Qwen3.5-397B-A17B-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 tarruda/Qwen3.5-397B-A17B-GGUF:IQ3_XXS

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 tarruda/Qwen3.5-397B-A17B-GGUF:IQ3_XXS

Run Hermes

hermes

Docker Model Runner
How to use tarruda/Qwen3.5-397B-A17B-GGUF with Docker Model Runner:
```
docker model run hf.co/tarruda/Qwen3.5-397B-A17B-GGUF:IQ3_XXS
```

Lemonade

How to use tarruda/Qwen3.5-397B-A17B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull tarruda/Qwen3.5-397B-A17B-GGUF:IQ3_XXS

Run and chat with the model

lemonade run user.Qwen3.5-397B-A17B-GGUF-IQ3_XXS

List all available models

lemonade list

Intro

This is a 2.54 BPW Qwen 3.5 397B quantization using a recipe inspired by @AesSedai and @ubergarm.

My goal was to maximize BPW for my hardware (128G M1 ultra) while allowing up for 128K context.

The recipe is:

TYPE_FFN_GATE_UP_EXPS=IQ2_XXS
TYPE_FFN_DOWN_EXPS=IQ3_XXS
TYPE_TOKEN_EMBEDDING=Q4_K
TYPE_OUTPUT=Q6_K
TYPE_DEFAULT=Q8_0

Running

This is the command I use to run it locally:

llama-server --no-mmap --no-warmup -fa on --model IQ3_XXS/Qwen3.5-397B-A17B-IQ3_XXS-00001-of-00004.gguf --mmproj mmproj-F16.gguf --ctx-size 131072 --jinja --temp 0.6 --top-p 0.95 --top-k 20 --min-p 0.00 -cram 0

I use -cram 0 because the model + context will take 100% of my available RAM.

Quantizing

Assuming the original model is located at ../../Qwen/Qwen3.5-397B-A17B and llama.cpp (with built binaries) is located at ~/llama.cpp, the full quantization is done with:

./scripts/convert-to-gguf.sh ~/llama.cpp ../../Qwen/Qwen3.5-397B-A17B
./scripts/quantize.sh ~/code/llama.cpp IQ3_XXS

The quantization depends on imatrix.gguf, which was copied from @ubergarm's 397B repo.

Downloads last month: 74

GGUF

Model size

396B params

Architecture

qwen35moe

Hardware compatibility

3-bit

View +1 variant

Model tree for tarruda/Qwen3.5-397B-A17B-GGUF

Base model

Qwen/Qwen3.5-397B-A17B

Quantized

(72)

this model