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

Libraries

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

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="ubergarm/Qwen3.5-122B-A10B-GGUF",
	filename="Qwen3.5-122B-A10B-IQ1_KT.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 ubergarm/Qwen3.5-122B-A10B-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf ubergarm/Qwen3.5-122B-A10B-GGUF:Q2_K
# Run inference directly in the terminal:
llama-cli -hf ubergarm/Qwen3.5-122B-A10B-GGUF:Q2_K

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf ubergarm/Qwen3.5-122B-A10B-GGUF:Q2_K
# Run inference directly in the terminal:
llama-cli -hf ubergarm/Qwen3.5-122B-A10B-GGUF:Q2_K

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 ubergarm/Qwen3.5-122B-A10B-GGUF:Q2_K
# Run inference directly in the terminal:
./llama-cli -hf ubergarm/Qwen3.5-122B-A10B-GGUF:Q2_K

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 ubergarm/Qwen3.5-122B-A10B-GGUF:Q2_K
# Run inference directly in the terminal:
./build/bin/llama-cli -hf ubergarm/Qwen3.5-122B-A10B-GGUF:Q2_K

Use Docker

docker model run hf.co/ubergarm/Qwen3.5-122B-A10B-GGUF:Q2_K

LM Studio
Jan

vLLM

How to use ubergarm/Qwen3.5-122B-A10B-GGUF with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/ubergarm/Qwen3.5-122B-A10B-GGUF:Q2_K

Ollama
How to use ubergarm/Qwen3.5-122B-A10B-GGUF with Ollama:
```
ollama run hf.co/ubergarm/Qwen3.5-122B-A10B-GGUF:Q2_K
```

Unsloth Studio new

How to use ubergarm/Qwen3.5-122B-A10B-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 ubergarm/Qwen3.5-122B-A10B-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 ubergarm/Qwen3.5-122B-A10B-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

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

Pi new

How to use ubergarm/Qwen3.5-122B-A10B-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf ubergarm/Qwen3.5-122B-A10B-GGUF:Q2_K

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": "ubergarm/Qwen3.5-122B-A10B-GGUF:Q2_K"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use ubergarm/Qwen3.5-122B-A10B-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 ubergarm/Qwen3.5-122B-A10B-GGUF:Q2_K

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 ubergarm/Qwen3.5-122B-A10B-GGUF:Q2_K

Run Hermes

hermes

Docker Model Runner
How to use ubergarm/Qwen3.5-122B-A10B-GGUF with Docker Model Runner:
```
docker model run hf.co/ubergarm/Qwen3.5-122B-A10B-GGUF:Q2_K
```

Lemonade

How to use ubergarm/Qwen3.5-122B-A10B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull ubergarm/Qwen3.5-122B-A10B-GGUF:Q2_K

Run and chat with the model

lemonade run user.Qwen3.5-122B-A10B-GGUF-Q2_K

List all available models

lemonade list

Request for q4_0 quant

by TK-13 - opened Feb 27

Discussion

TK-13

Feb 27

Based on your qwen3.5 35B KLD numbers it seems like the q4_0 quant is a great fit for both accuracy and vulkan speed, any intentions to create q4_0 quants for Qwen3.5 122B and 397B?

Thanks for the amazing quants!

ubergarm

Owner Mar 2

@TK-13

Thanks for giving it a go! I decided to do testing on the smaller 35B to see if it would work well and so far so good.

Do you have enough Vulkan VRAM to fit the larger quants? Given they are roughly 5bpw they will be fairly large.

Also I'm catching up from the weekend to understand the update in the unsloth quants, though not sure they have a "vulkan mix" recipe similar to this yet.

TK-13

Mar 2

@TK-13

Thanks for giving it a go! I decided to do testing on the smaller 35B to see if it would work well and so far so good.

Do you have enough Vulkan VRAM to fit the larger quants? Given they are roughly 5bpw they will be fairly large.

Also I'm catching up from the weekend to understand the update in the unsloth quants, though not sure they have a "vulkan mix" recipe similar to this yet.

I've got 240GB of AMD VRAM available, that might be enough 😆

ubergarm

Owner Mar 3

@TK-13

Oh that will run a lot of models 😅

I haven't cooked any "vulkan mix" editions for the bigger models yet, but with that much VRAM you can get a pure Q8_0 which would also be quite fast for PP but will be slower for TG given the usual memory bandwidth bottleneck with larger active parameters.

I still have to do some research on the updated quant landscape to see what unsloth and AesSedai are releasing now as my usual quants are ik_llama.cpp specific, so the "vulkan mixes" are a bit new for me and I'm trying to see how it fits into my quant portfolio haha...

I'm curious what your daily driver is and what kinda client are you using e.g. opencode or mostly silly tavern? haha... also I'm assuming you use mainline llama.cpp and are not compiling ik_llama.cpp?

TK-13

Mar 3

@ubergarm

Thanks!

My use is pretty much exclusively via openwebui as a chatbot, and yes mainline llama.cpp, I'd love to use ik_llama.cpp but lack of rocm/(updated) vulkan support is the limiter 😆

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment