Instructions to use bombdefuser-124/Qwen3.6-35BA3B-MTP-Q4_0-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use bombdefuser-124/Qwen3.6-35BA3B-MTP-Q4_0-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="bombdefuser-124/Qwen3.6-35BA3B-MTP-Q4_0-GGUF",
	filename="Qwen3.6-35BA3B-MTP-Q4_0.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 bombdefuser-124/Qwen3.6-35BA3B-MTP-Q4_0-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf bombdefuser-124/Qwen3.6-35BA3B-MTP-Q4_0-GGUF:Q4_0
# Run inference directly in the terminal:
llama-cli -hf bombdefuser-124/Qwen3.6-35BA3B-MTP-Q4_0-GGUF:Q4_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf bombdefuser-124/Qwen3.6-35BA3B-MTP-Q4_0-GGUF:Q4_0
# Run inference directly in the terminal:
llama-cli -hf bombdefuser-124/Qwen3.6-35BA3B-MTP-Q4_0-GGUF:Q4_0

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 bombdefuser-124/Qwen3.6-35BA3B-MTP-Q4_0-GGUF:Q4_0
# Run inference directly in the terminal:
./llama-cli -hf bombdefuser-124/Qwen3.6-35BA3B-MTP-Q4_0-GGUF:Q4_0

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 bombdefuser-124/Qwen3.6-35BA3B-MTP-Q4_0-GGUF:Q4_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf bombdefuser-124/Qwen3.6-35BA3B-MTP-Q4_0-GGUF:Q4_0

Use Docker

docker model run hf.co/bombdefuser-124/Qwen3.6-35BA3B-MTP-Q4_0-GGUF:Q4_0

LM Studio
Jan
Ollama
How to use bombdefuser-124/Qwen3.6-35BA3B-MTP-Q4_0-GGUF with Ollama:
```
ollama run hf.co/bombdefuser-124/Qwen3.6-35BA3B-MTP-Q4_0-GGUF:Q4_0
```

Unsloth Studio new

How to use bombdefuser-124/Qwen3.6-35BA3B-MTP-Q4_0-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 bombdefuser-124/Qwen3.6-35BA3B-MTP-Q4_0-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 bombdefuser-124/Qwen3.6-35BA3B-MTP-Q4_0-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for bombdefuser-124/Qwen3.6-35BA3B-MTP-Q4_0-GGUF to start chatting

Pi new

How to use bombdefuser-124/Qwen3.6-35BA3B-MTP-Q4_0-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf bombdefuser-124/Qwen3.6-35BA3B-MTP-Q4_0-GGUF:Q4_0

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": "Qwen3.6-35BA3B-MTP-Q4_0-GGUF"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use bombdefuser-124/Qwen3.6-35BA3B-MTP-Q4_0-GGUF with Docker Model Runner:
```
docker model run hf.co/bombdefuser-124/Qwen3.6-35BA3B-MTP-Q4_0-GGUF:Q4_0
```

Lemonade

How to use bombdefuser-124/Qwen3.6-35BA3B-MTP-Q4_0-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull bombdefuser-124/Qwen3.6-35BA3B-MTP-Q4_0-GGUF:Q4_0

Run and chat with the model

lemonade run user.Qwen3.6-35BA3B-MTP-Q4_0-GGUF-Q4_0

List all available models

lemonade list

Not even close to an ideal quantization. I just requantized am17an/Qwen3.6-35BA3B-MTP-GGUF (which is Q8_0) to Q4_0.

Made using this llama.cpp PR

Flags I use for inference (25tk/s to 37tk/s | 1,5x~ speedup):

./llama.cpp/build/bin/llama-server --host 0.0.0.0 --port 5000 \
                  -m ./Models/Qwen3.6-35BA3B-MTP-Q4_0.gguf --fit on \
                  -a "Qwen3.6-35B-A3B" -c 200000 \
                  --top-k 20 --top-p 0.95 --min-p 0 --repeat-penalty 1.0 --presence-penalty 0.0 \
                  -fa on --temp 0.6 -ctk q8_0 -ctv q8_0 --batch-size 4096 \
                  --reasoning off --no-mmap --jinja -t 6 --checkpoint-every-n-tokens 4096 --ctx-checkpoints 64 -fitt 512 \
                  --spec-draft-n-max 2

Downloads last month: 974

GGUF

Model size

36B params

Architecture

qwen35moe

Hardware compatibility

4-bit

Inference Providers NEW

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

Model tree for bombdefuser-124/Qwen3.6-35BA3B-MTP-Q4_0-GGUF

Base model

am17an/Qwen3.6-35BA3B-MTP-GGUF

Quantized

(2)

this model