Instructions to use KeinNiemand/Qwen3.5-122B-A10B-IK_GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use KeinNiemand/Qwen3.5-122B-A10B-IK_GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="KeinNiemand/Qwen3.5-122B-A10B-IK_GGUF",
	filename="Qwen3.5-122B-A10B-IQ4_K.gguf",
)

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

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use KeinNiemand/Qwen3.5-122B-A10B-IK_GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf KeinNiemand/Qwen3.5-122B-A10B-IK_GGUF
# Run inference directly in the terminal:
llama-cli -hf KeinNiemand/Qwen3.5-122B-A10B-IK_GGUF

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf KeinNiemand/Qwen3.5-122B-A10B-IK_GGUF
# Run inference directly in the terminal:
llama-cli -hf KeinNiemand/Qwen3.5-122B-A10B-IK_GGUF

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 KeinNiemand/Qwen3.5-122B-A10B-IK_GGUF
# Run inference directly in the terminal:
./llama-cli -hf KeinNiemand/Qwen3.5-122B-A10B-IK_GGUF

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 KeinNiemand/Qwen3.5-122B-A10B-IK_GGUF
# Run inference directly in the terminal:
./build/bin/llama-cli -hf KeinNiemand/Qwen3.5-122B-A10B-IK_GGUF

Use Docker

docker model run hf.co/KeinNiemand/Qwen3.5-122B-A10B-IK_GGUF

LM Studio
Jan

vLLM

How to use KeinNiemand/Qwen3.5-122B-A10B-IK_GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "KeinNiemand/Qwen3.5-122B-A10B-IK_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": "KeinNiemand/Qwen3.5-122B-A10B-IK_GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/KeinNiemand/Qwen3.5-122B-A10B-IK_GGUF

Ollama
How to use KeinNiemand/Qwen3.5-122B-A10B-IK_GGUF with Ollama:
```
ollama run hf.co/KeinNiemand/Qwen3.5-122B-A10B-IK_GGUF
```

Unsloth Studio

How to use KeinNiemand/Qwen3.5-122B-A10B-IK_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 KeinNiemand/Qwen3.5-122B-A10B-IK_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 KeinNiemand/Qwen3.5-122B-A10B-IK_GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for KeinNiemand/Qwen3.5-122B-A10B-IK_GGUF to start chatting

How to use KeinNiemand/Qwen3.5-122B-A10B-IK_GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf KeinNiemand/Qwen3.5-122B-A10B-IK_GGUF

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": "KeinNiemand/Qwen3.5-122B-A10B-IK_GGUF"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use KeinNiemand/Qwen3.5-122B-A10B-IK_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 KeinNiemand/Qwen3.5-122B-A10B-IK_GGUF

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 KeinNiemand/Qwen3.5-122B-A10B-IK_GGUF

Run Hermes

hermes

Atomic Chat new
Docker Model Runner
How to use KeinNiemand/Qwen3.5-122B-A10B-IK_GGUF with Docker Model Runner:
```
docker model run hf.co/KeinNiemand/Qwen3.5-122B-A10B-IK_GGUF
```

Lemonade

How to use KeinNiemand/Qwen3.5-122B-A10B-IK_GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull KeinNiemand/Qwen3.5-122B-A10B-IK_GGUF

Run and chat with the model

lemonade run user.Qwen3.5-122B-A10B-IK_GGUF-{{QUANT_TAG}}

List all available models

lemonade list

Qwen3.5 122B A10B - Custom GGUF Quantizations

🚨 CRITICAL COMPATIBILITY WARNING 🚨 These are iqk format quantizations and are EXCLUSIVE to the ik_llama.cpp fork. They will NOT work on mainline llama.cpp, standard LM Studio, standard Text Generation WebUI, or KoboldCPP. You must compile and run this using ikawrakow's llama.cpp fork (or a UI where you have manually swapped the backend to an ik_llama build).

This repository contains custom, mixed-precision ik_llama.cpp GGUF quantizations for Qwen/Qwen3.5-122B-A10B.

These quants were specifically designed to push the routed expert layers to slightly higher precision (IQ4_KS and IQ4_K) while maintaining strict precision on the attention and embedding layers.

⚠️ Disclaimer: The "Vibes Test"

These quantizations have NOT been formally tested for perplexity. They were compiled blindly as an experiment to see how the model handles shifting bottlenecks. There is no guarantee that they are mathematically optimal or perform flawlessly. They are provided entirely as-is. If they pass the vibes test for you, enjoy!

🙏 Credits & Acknowledgments

Massive credit goes to ubergarm/Qwen3.5-122B-A10B-GGUF. The imatrix.dat used to calculate these custom quants was pulled directly from their phenomenal enterprise-hardware run, and the custom layer-mapping recipes used here are heavily based on their original blending logic.

🛠️ Quantization Recipes

1. The IQ4_KS Mix

This mix balances an upgraded routed-expert layer with highly compressed (but imatrix-optimized) embeddings to save VRAM.

Token Embeddings & Output: IQ6_K
Attention / Delta Net / Shared Experts: Q8_0
Routed Experts: IQ4_KS

2. The IQ4_K Mix

This mix opts to spend a tiny bit more VRAM to give the model absolute Q8_0 precision on its vocabulary, alongside slightly heavier experts.

Token Embeddings & Output: Q8_0
Attention / Delta Net / Shared Experts: Q8_0
Routed Experts: IQ4_K

💻 How to Run

Clone and build the ik_llama.cpp fork from ikawrakow/ik_llama.cpp.
Use the compiled llama-server or llama-cli from that specific build.

Example llama-server launch command:

./llama-server -m Qwen3.5-122B-A10B-IQ4_KS.gguf -c 8192 -ngl 99 -fa

Downloads last month: 15

GGUF

Model size

122B params

Architecture

qwen35moe

Hardware compatibility

Model tree for KeinNiemand/Qwen3.5-122B-A10B-IK_GGUF

Base model

Qwen/Qwen3.5-122B-A10B

Quantized

(120)

this model