Instructions to use mradermacher/Qwen3.5-397B-A17B-i1-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mradermacher/Qwen3.5-397B-A17B-i1-GGUF with Transformers:

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("mradermacher/Qwen3.5-397B-A17B-i1-GGUF", dtype="auto")

llama-cpp-python

How to use mradermacher/Qwen3.5-397B-A17B-i1-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="mradermacher/Qwen3.5-397B-A17B-i1-GGUF",
	filename="Qwen3.5-397B-A17B.i1-IQ1_M.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use mradermacher/Qwen3.5-397B-A17B-i1-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf mradermacher/Qwen3.5-397B-A17B-i1-GGUF:IQ1_M
# Run inference directly in the terminal:
llama-cli -hf mradermacher/Qwen3.5-397B-A17B-i1-GGUF:IQ1_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf mradermacher/Qwen3.5-397B-A17B-i1-GGUF:IQ1_M
# Run inference directly in the terminal:
llama-cli -hf mradermacher/Qwen3.5-397B-A17B-i1-GGUF:IQ1_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 mradermacher/Qwen3.5-397B-A17B-i1-GGUF:IQ1_M
# Run inference directly in the terminal:
./llama-cli -hf mradermacher/Qwen3.5-397B-A17B-i1-GGUF:IQ1_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 mradermacher/Qwen3.5-397B-A17B-i1-GGUF:IQ1_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf mradermacher/Qwen3.5-397B-A17B-i1-GGUF:IQ1_M

Use Docker

docker model run hf.co/mradermacher/Qwen3.5-397B-A17B-i1-GGUF:IQ1_M

LM Studio
Jan
Ollama
How to use mradermacher/Qwen3.5-397B-A17B-i1-GGUF with Ollama:
```
ollama run hf.co/mradermacher/Qwen3.5-397B-A17B-i1-GGUF:IQ1_M
```

Unsloth Studio new

How to use mradermacher/Qwen3.5-397B-A17B-i1-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 mradermacher/Qwen3.5-397B-A17B-i1-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 mradermacher/Qwen3.5-397B-A17B-i1-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for mradermacher/Qwen3.5-397B-A17B-i1-GGUF to start chatting

Pi new

How to use mradermacher/Qwen3.5-397B-A17B-i1-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf mradermacher/Qwen3.5-397B-A17B-i1-GGUF:IQ1_M

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": "mradermacher/Qwen3.5-397B-A17B-i1-GGUF:IQ1_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use mradermacher/Qwen3.5-397B-A17B-i1-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 mradermacher/Qwen3.5-397B-A17B-i1-GGUF:IQ1_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 mradermacher/Qwen3.5-397B-A17B-i1-GGUF:IQ1_M

Run Hermes

hermes

Docker Model Runner
How to use mradermacher/Qwen3.5-397B-A17B-i1-GGUF with Docker Model Runner:
```
docker model run hf.co/mradermacher/Qwen3.5-397B-A17B-i1-GGUF:IQ1_M
```

Lemonade

How to use mradermacher/Qwen3.5-397B-A17B-i1-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull mradermacher/Qwen3.5-397B-A17B-i1-GGUF:IQ1_M

Run and chat with the model

lemonade run user.Qwen3.5-397B-A17B-i1-GGUF-IQ1_M

List all available models

lemonade list

About

weighted/imatrix quants of https://huggingface.co/Qwen/Qwen3.5-397B-A17B

For a convenient overview and download list, visit our model page for this model.

static quants are available at https://huggingface.co/mradermacher/Qwen3.5-397B-A17B-GGUF

This is a vision model - mmproj files (if any) will be in the static repository.

Usage

If you are unsure how to use GGUF files, refer to one of TheBloke's READMEs for more details, including on how to concatenate multi-part files.

Provided Quants

(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)

Link	Type	Size/GB	Notes
GGUF	imatrix	1.2	imatrix file (for creating your own quants)
GGUF	i1-IQ1_S	80.7	for the desperate
GGUF	i1-IQ1_M	89.6	mostly desperate
PART 1 PART 2 PART 3	i1-IQ2_XXS	104.6
PART 1 PART 2 PART 3	i1-IQ2_XS	116.6
PART 1 PART 2 PART 3	i1-IQ2_S	117.6
PART 1 PART 2 PART 3	i1-IQ2_M	129.6
PART 1 PART 2 PART 3	i1-Q2_K_S	135.2	very low quality
PART 1 PART 2 PART 3	i1-Q2_K	144.8	IQ3_XXS probably better
PART 1 PART 2 PART 3 PART 4	i1-IQ3_XXS	153.0	lower quality
PART 1 PART 2 PART 3 PART 4	i1-IQ3_XS	162.5
PART 1 PART 2 PART 3 PART 4	i1-Q3_K_S	171.3	IQ3_XS probably better
PART 1 PART 2 PART 3 PART 4	i1-IQ3_S	171.6	beats Q3_K*
PART 1 PART 2 PART 3 PART 4	i1-IQ3_M	173.6
PART 1 PART 2 PART 3 PART 4	i1-Q3_K_M	189.6	IQ3_S probably better
P1 P2 P3 P4 P5	i1-Q3_K_L	205.3	IQ3_M probably better
P1 P2 P3 P4 P5	i1-IQ4_XS	211.8
P1 P2 P3 P4 P5	i1-Q4_0	224.7	fast, low quality
P1 P2 P3 P4 P5	i1-Q4_K_S	225.7	optimal size/speed/quality
P1 P2 P3 P4 P5	i1-Q4_K_M	240.7	fast, recommended
P1 P2 P3 P4 P5 P6	i1-Q4_1	248.5
P1 P2 P3 P4 P5 P6	i1-Q5_K_S	273.2
P1 P2 P3 P4 P5 P6	i1-Q5_K_M	281.9
P1 P2 P3 P4 P5 P6 P7	i1-Q6_K	325.6	practically like static Q6_K

Here is a handy graph by ikawrakow comparing some lower-quality quant types (lower is better):

And here are Artefact2's thoughts on the matter: https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9

FAQ / Model Request

See https://huggingface.co/mradermacher/model_requests for some answers to questions you might have and/or if you want some other model quantized.

Thanks

I thank my company, nethype GmbH, for letting me use its servers and providing upgrades to my workstation to enable this work in my free time. Additional thanks to @nicoboss for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to.

Downloads last month: 5,529

GGUF

Model size

396B params

Architecture

qwen35moe

Hardware compatibility

1-bit

View +1 variant

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for mradermacher/Qwen3.5-397B-A17B-i1-GGUF

Base model

Qwen/Qwen3.5-397B-A17B

Quantized

(71)

this model