Instructions to use barozp/Qwen3.6-28B-REAP20-A3B-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use barozp/Qwen3.6-28B-REAP20-A3B-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="barozp/Qwen3.6-28B-REAP20-A3B-GGUF",
	filename="Qwen3.6-28B-REAP20-A3B-BF16.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 barozp/Qwen3.6-28B-REAP20-A3B-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf barozp/Qwen3.6-28B-REAP20-A3B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf barozp/Qwen3.6-28B-REAP20-A3B-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf barozp/Qwen3.6-28B-REAP20-A3B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf barozp/Qwen3.6-28B-REAP20-A3B-GGUF:Q4_K_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 barozp/Qwen3.6-28B-REAP20-A3B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf barozp/Qwen3.6-28B-REAP20-A3B-GGUF:Q4_K_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 barozp/Qwen3.6-28B-REAP20-A3B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf barozp/Qwen3.6-28B-REAP20-A3B-GGUF:Q4_K_M

Use Docker

docker model run hf.co/barozp/Qwen3.6-28B-REAP20-A3B-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use barozp/Qwen3.6-28B-REAP20-A3B-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "barozp/Qwen3.6-28B-REAP20-A3B-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": "barozp/Qwen3.6-28B-REAP20-A3B-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/barozp/Qwen3.6-28B-REAP20-A3B-GGUF:Q4_K_M

Ollama
How to use barozp/Qwen3.6-28B-REAP20-A3B-GGUF with Ollama:
```
ollama run hf.co/barozp/Qwen3.6-28B-REAP20-A3B-GGUF:Q4_K_M
```

Unsloth Studio new

How to use barozp/Qwen3.6-28B-REAP20-A3B-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 barozp/Qwen3.6-28B-REAP20-A3B-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 barozp/Qwen3.6-28B-REAP20-A3B-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for barozp/Qwen3.6-28B-REAP20-A3B-GGUF to start chatting

Pi new

How to use barozp/Qwen3.6-28B-REAP20-A3B-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf barozp/Qwen3.6-28B-REAP20-A3B-GGUF:Q4_K_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": "barozp/Qwen3.6-28B-REAP20-A3B-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use barozp/Qwen3.6-28B-REAP20-A3B-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 barozp/Qwen3.6-28B-REAP20-A3B-GGUF:Q4_K_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 barozp/Qwen3.6-28B-REAP20-A3B-GGUF:Q4_K_M

Run Hermes

hermes

Docker Model Runner
How to use barozp/Qwen3.6-28B-REAP20-A3B-GGUF with Docker Model Runner:
```
docker model run hf.co/barozp/Qwen3.6-28B-REAP20-A3B-GGUF:Q4_K_M
```

Lemonade

How to use barozp/Qwen3.6-28B-REAP20-A3B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull barozp/Qwen3.6-28B-REAP20-A3B-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Qwen3.6-28B-REAP20-A3B-GGUF-Q4_K_M

List all available models

lemonade list

Qwen3.6-28B-REAP20-A3B — GGUF Quantizations

GGUF quantizations of 0xSero/Qwen3.6-28B-REAP20-A3B, a 20% expert-pruned variant of Qwen/Qwen3.6-35B-A3B using the REAP (Router-weighted Expert Activation Pruning) method.

Available Files

File	Quant	Size	BPW	Description
`Qwen3.6-28B-REAP20-A3B-BF16.gguf`	BF16	~56.5 GB	16.0	Full precision, for re-quantization
`Qwen3.6-28B-REAP20-A3B-Q8_0.gguf`	Q8_0	~30 GB	8.0	Near-lossless, large file
`Qwen3.6-28B-REAP20-A3B-Q6_K.gguf`	Q6_K	~23 GB	6.56	Near-lossless, recommended for high quality
`Qwen3.6-28B-REAP20-A3B-Q5_K_M.gguf`	Q5_K_M	~20 GB	5.68	High quality, larger size
`Qwen3.6-28B-REAP20-A3B-Q5_K_S.gguf`	Q5_K_S	~19 GB	5.52	High quality, slightly smaller
`Qwen3.6-28B-REAP20-A3B-Q4_K_M.gguf`	Q4_K_M	~17 GB	4.89	Recommended — best quality/size balance
`Qwen3.6-28B-REAP20-A3B-Q4_K_S.gguf`	Q4_K_S	~16 GB	4.63	4-bit small
`Qwen3.6-28B-REAP20-A3B-Q3_K_L.gguf`	Q3_K_L	~15 GB	4.27	3-bit large
`Qwen3.6-28B-REAP20-A3B-Q3_K_M.gguf`	Q3_K_M	~14 GB	3.91	3-bit medium
`Qwen3.6-28B-REAP20-A3B-Q3_K_S.gguf`	Q3_K_S	~13 GB	3.66	3-bit small
`Qwen3.6-28B-REAP20-A3B-IQ3_XXS.gguf`	IQ3_XXS	~12 GB	3.06	Ultra-small, imatrix-based
`Qwen3.6-28B-REAP20-A3B-Q2_K.gguf`	Q2_K	~11 GB	2.96	Smallest size, lowest quality

Model Details

Property	Value
Architecture	Qwen3.6 MoE (hybrid Gated DeltaNet + MoE)
Parameters	~28B total / ~3B active per token
Experts	205 total / 8 active per token (pruned from 256)
Context Length	262,144 tokens
Original dtype	BF16
Quantization source	BF16 GGUF from 0xSero/Qwen3.6-28B-REAP20-A3B-GGUF
Quantization tool	llama.cpp
imatrix	Used for IQ3_XXS (from source repo)
License	Apache 2.0

Quantization Process

# 1. Download BF16 GGUF from source
huggingface-cli download 0xSero/Qwen3.6-28B-REAP20-A3B-GGUF \
  --include "model.bf16.gguf" --local-dir ./

# 2. Download imatrix (for IQ quants)
huggingface-cli download 0xSero/Qwen3.6-28B-REAP20-A3B-GGUF \
  --include "imatrix.dat" --local-dir ./

# 3. Quantize (example: Q4_K_M)
llama-quantize model.bf16.gguf Qwen3.6-28B-REAP20-A3B-Q4_K_M.gguf Q4_K_M

# 4. Quantize with imatrix (example: IQ3_XXS)
llama-quantize --imatrix imatrix.dat model.bf16.gguf \
  Qwen3.6-28B-REAP20-A3B-IQ3_XXS.gguf IQ3_XXS

Usage

llama.cpp

llama-cli \
  -m Qwen3.6-28B-REAP20-A3B-Q4_K_M.gguf \
  -ngl 99 -c 4096 \
  -p "Your prompt here"

llama-server (OpenAI-compatible API)

llama-server \
  -m Qwen3.6-28B-REAP20-A3B-Q4_K_M.gguf \
  -ngl 99 -c 4096 \
  --port 8080

LM Studio / Jan / Ollama

Download the .gguf file and load it directly in your preferred local inference UI.

Hardware Requirements

Config	VRAM / RAM
Full GPU (Q4_K_M, recommended)	20+ GB VRAM
Hybrid CPU+GPU (Q4_K_M)	10 GB VRAM + 10 GB RAM
CPU only (Q4_K_M)	24+ GB RAM

About the Original Model

0xSero/Qwen3.6-28B-REAP20-A3B applies REAP expert pruning (arXiv:2510.13999) to remove 20% of MoE experts (51 of 256 per layer) from Qwen3.6-35B-A3B, while preserving routing behavior via router weight renormalization. Active parameters per token remain unchanged at ~3B. The result is a ~25% smaller model with competitive generation quality across coding, reasoning, and knowledge benchmarks.

License

Apache 2.0 — see Qwen License.

Downloads last month: 1,998

GGUF

Model size

28B params

Architecture

qwen35moe

Hardware compatibility

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

16-bit

Model tree for barozp/Qwen3.6-28B-REAP20-A3B-GGUF

Base model

Qwen/Qwen3.6-35B-A3B

Finetuned

0xSero/Qwen3.6-28B-REAP

Quantized

(4)

this model

Paper for barozp/Qwen3.6-28B-REAP20-A3B-GGUF

REAP the Experts: Why Pruning Prevails for One-Shot MoE compression

Paper • 2510.13999 • Published Oct 15, 2025 • 19