Instructions to use zTrojan/Qwen3.5-122B-A10B-REAP20-APEX-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use zTrojan/Qwen3.5-122B-A10B-REAP20-APEX-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="zTrojan/Qwen3.5-122B-A10B-REAP20-APEX-GGUF",
	filename="Qwen3.5-122B-A10B-REAP20-APEX-I-Compact.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 zTrojan/Qwen3.5-122B-A10B-REAP20-APEX-GGUF with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf zTrojan/Qwen3.5-122B-A10B-REAP20-APEX-GGUF
# Run inference directly in the terminal:
llama cli -hf zTrojan/Qwen3.5-122B-A10B-REAP20-APEX-GGUF

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf zTrojan/Qwen3.5-122B-A10B-REAP20-APEX-GGUF
# Run inference directly in the terminal:
llama cli -hf zTrojan/Qwen3.5-122B-A10B-REAP20-APEX-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 zTrojan/Qwen3.5-122B-A10B-REAP20-APEX-GGUF
# Run inference directly in the terminal:
./llama-cli -hf zTrojan/Qwen3.5-122B-A10B-REAP20-APEX-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 zTrojan/Qwen3.5-122B-A10B-REAP20-APEX-GGUF
# Run inference directly in the terminal:
./build/bin/llama-cli -hf zTrojan/Qwen3.5-122B-A10B-REAP20-APEX-GGUF

Use Docker

docker model run hf.co/zTrojan/Qwen3.5-122B-A10B-REAP20-APEX-GGUF

LM Studio
Jan

vLLM

How to use zTrojan/Qwen3.5-122B-A10B-REAP20-APEX-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "zTrojan/Qwen3.5-122B-A10B-REAP20-APEX-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": "zTrojan/Qwen3.5-122B-A10B-REAP20-APEX-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/zTrojan/Qwen3.5-122B-A10B-REAP20-APEX-GGUF

Ollama
How to use zTrojan/Qwen3.5-122B-A10B-REAP20-APEX-GGUF with Ollama:
```
ollama run hf.co/zTrojan/Qwen3.5-122B-A10B-REAP20-APEX-GGUF
```

Unsloth Studio

How to use zTrojan/Qwen3.5-122B-A10B-REAP20-APEX-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 zTrojan/Qwen3.5-122B-A10B-REAP20-APEX-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 zTrojan/Qwen3.5-122B-A10B-REAP20-APEX-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for zTrojan/Qwen3.5-122B-A10B-REAP20-APEX-GGUF to start chatting

How to use zTrojan/Qwen3.5-122B-A10B-REAP20-APEX-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf zTrojan/Qwen3.5-122B-A10B-REAP20-APEX-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": "zTrojan/Qwen3.5-122B-A10B-REAP20-APEX-GGUF"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use zTrojan/Qwen3.5-122B-A10B-REAP20-APEX-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf zTrojan/Qwen3.5-122B-A10B-REAP20-APEX-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 zTrojan/Qwen3.5-122B-A10B-REAP20-APEX-GGUF

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use zTrojan/Qwen3.5-122B-A10B-REAP20-APEX-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf zTrojan/Qwen3.5-122B-A10B-REAP20-APEX-GGUF

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "zTrojan/Qwen3.5-122B-A10B-REAP20-APEX-GGUF" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

Docker Model Runner
How to use zTrojan/Qwen3.5-122B-A10B-REAP20-APEX-GGUF with Docker Model Runner:
```
docker model run hf.co/zTrojan/Qwen3.5-122B-A10B-REAP20-APEX-GGUF
```

Lemonade

How to use zTrojan/Qwen3.5-122B-A10B-REAP20-APEX-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull zTrojan/Qwen3.5-122B-A10B-REAP20-APEX-GGUF

Run and chat with the model

lemonade run user.Qwen3.5-122B-A10B-REAP20-APEX-GGUF-{{QUANT_TAG}}

List all available models

lemonade list

Qwen3.5-122B-A10B REAP20 APEX GGUF

Physical REAP20-pruned APEX GGUF builds of Qwen/Qwen3.5-122B-A10B.

This repository is focused on APEX quantizations of a physically expert-pruned REAP20 version of Qwen3.5-122B-A10B.

Available quants

File	Description
`Qwen3.5-122B-A10B-REAP20-APEX-Mini.gguf`	Production APEX Mini quant with imatrix

Source model

Base model:

Qwen/Qwen3.5-122B-A10B
REAP pruning
Method: physical REAP expert pruning
Compression ratio: 20%
Original experts per MoE layer: 256
Retained experts per MoE layer: 205
Layers: 48
Experts per token: 8
Observation: 32 batches
Distance: cosine
Seed: 42
Calibration source: custom calibration-v2
APEX Mini quantization

APEX Mini was generated with llama.cpp llama-quantize using a tensor-type map and imatrix.

Tensor config: configs/qwen35_122b_mini.txt
Base fallback type: Q3_K_M
Imatrix: production REAP20 imatrix
Imatrix context: -c 4096
Imatrix chunks: --chunks 128
Imatrix calibration: 64MB shuffled calibration-v2
Imatrix model source: REAP20 BF16 GGUF

The Mini profile uses Q3_K edge experts and IQ2_S middle routed experts, so imatrix is required.

Example: llama.cpp
llama-cli \
  -m Qwen3.5-122B-A10B-REAP20-APEX-Mini.gguf \
  -p "<|im_start|>user
Привіт. Напиши один короткий параграф українською. /no_think
<|im_end|>
<|im_start|>assistant
" \
  -n 128 \
  -c 4096 \
  -ngl 40 \
  --temp 0.6 \
  --top-p 0.95
Notes

This is an experimental physical expert-pruned build. It is intended for testing, iteration, and comparison with other REAP/APEX variants.

Future files may include:

APEX I-Compact
APEX I-Balanced
APEX I-Quality
other GGUF quantizations

Downloads last month: 282

GGUF

Model size

99B params

Architecture

qwen35moe

Hardware compatibility

We're not able to determine the quantization variants.

View all variants

Model tree for zTrojan/Qwen3.5-122B-A10B-REAP20-APEX-GGUF

Base model

Qwen/Qwen3.5-122B-A10B

Quantized

(127)

this model