Instructions to use barozp/Qwen-3.5-28B-A3B-REAP-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use barozp/Qwen-3.5-28B-A3B-REAP-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="barozp/Qwen-3.5-28B-A3B-REAP-GGUF",
	filename="Qwen-3.5-28B-A3B-REAP-BF16.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use barozp/Qwen-3.5-28B-A3B-REAP-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/Qwen-3.5-28B-A3B-REAP-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf barozp/Qwen-3.5-28B-A3B-REAP-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/Qwen-3.5-28B-A3B-REAP-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf barozp/Qwen-3.5-28B-A3B-REAP-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/Qwen-3.5-28B-A3B-REAP-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf barozp/Qwen-3.5-28B-A3B-REAP-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/Qwen-3.5-28B-A3B-REAP-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf barozp/Qwen-3.5-28B-A3B-REAP-GGUF:Q4_K_M

Use Docker

docker model run hf.co/barozp/Qwen-3.5-28B-A3B-REAP-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use barozp/Qwen-3.5-28B-A3B-REAP-GGUF with Ollama:
```
ollama run hf.co/barozp/Qwen-3.5-28B-A3B-REAP-GGUF:Q4_K_M
```

Unsloth Studio

How to use barozp/Qwen-3.5-28B-A3B-REAP-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/Qwen-3.5-28B-A3B-REAP-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/Qwen-3.5-28B-A3B-REAP-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/Qwen-3.5-28B-A3B-REAP-GGUF to start chatting

How to use barozp/Qwen-3.5-28B-A3B-REAP-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/Qwen-3.5-28B-A3B-REAP-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/Qwen-3.5-28B-A3B-REAP-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use barozp/Qwen-3.5-28B-A3B-REAP-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/Qwen-3.5-28B-A3B-REAP-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/Qwen-3.5-28B-A3B-REAP-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat new
Docker Model Runner
How to use barozp/Qwen-3.5-28B-A3B-REAP-GGUF with Docker Model Runner:
```
docker model run hf.co/barozp/Qwen-3.5-28B-A3B-REAP-GGUF:Q4_K_M
```

Lemonade

How to use barozp/Qwen-3.5-28B-A3B-REAP-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull barozp/Qwen-3.5-28B-A3B-REAP-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Qwen-3.5-28B-A3B-REAP-GGUF-Q4_K_M

List all available models

lemonade list

Qwen-3.5-28B-A3B-REAP — GGUF Q4_K_M

GGUF quantization of 0xSero/Qwen-3.5-28B-A3B-REAP, a pruned variant of Qwen/Qwen3.5-35B-A3B using the REAP (Refined Expert Activation Pruning) method.

Available Files

File	Quant	Size	BPW	Description
`Qwen-3.5-28B-A3B-REAP-BF16.gguf`	BF16	53 GB	16.01	Full precision, for re-quantization
`Qwen-3.5-28B-A3B-REAP-Q4_K_M.gguf`	Q4_K_M	17 GB	4.89	4-bit medium, recommended for most users
`Qwen3.5-28B-A3B-REAP-IQ3_XXS.gguf`	IQ3_XXS	11 GB	3.16	3-bit imatrix, smallest size with good quality

RAM / VRAM Estimation

Each quantization requires roughly model file size + 1.5–2 GB overhead for KV cache and runtime buffers (at default 4K context). Larger contexts will increase memory usage.

File	Quant	File Size	Est. RAM Usage
`Qwen-3.5-28B-A3B-REAP-BF16.gguf`	BF16	53 GB	~55 GB
`Qwen-3.5-28B-A3B-REAP-Q4_K_M.gguf`	Q4_K_M	17 GB	~19 GB
`Qwen3.5-28B-A3B-REAP-IQ3_XXS.gguf`	IQ3_XXS	11 GB	~13 GB

Which Quant Fits Your RAM?

System RAM	IQ3_XXS (~13 GB)	Q4_K_M (~19 GB)	BF16 (~55 GB)
8 GB	❌	❌	❌
16 GB	✅	❌	❌
32 GB	✅	✅	❌
64 GB	✅	✅	✅

Tip: If running on GPU, the same estimates apply to VRAM. With -ngl 99 (full GPU offload), you need the above amounts in VRAM. Partial offload splits the load between VRAM and system RAM.

Model Details

Property	Value
Architecture	Qwen3.5 MoE (linear + full attention hybrid)
Parameters	28.24B total / 3B active
Experts	205 total / 8 active per token
Context Length	262,144 tokens
Original dtype	BF16
Quantization	Q4_K_M (4.89 BPW)
Quantization tool	llama.cpp b8565
License	Apache 2.0

Quantization Process

# 1. Convert BF16 SafeTensors → GGUF
python convert_hf_to_gguf.py 0xSero/Qwen-3.5-28B-A3B-REAP \
  --outfile Qwen-3.5-28B-A3B-REAP-BF16.gguf \
  --outtype bf16

# 2a. Quantize to Q4_K_M
llama-quantize Qwen-3.5-28B-A3B-REAP-BF16.gguf \
  Qwen-3.5-28B-A3B-REAP-Q4_K_M.gguf Q4_K_M

# 2b. Generate imatrix (wikitext-2, 128 chunks)
llama-imatrix -m Qwen-3.5-28B-A3B-REAP-BF16.gguf \
  -f wiki.test.raw -o imatrix.dat --chunks 128

# 2c. Quantize to IQ3_XXS with imatrix
llama-quantize --imatrix imatrix.dat \
  Qwen-3.5-28B-A3B-REAP-BF16.gguf \
  Qwen3.5-28B-A3B-REAP-IQ3_XXS.gguf IQ3_XXS

Usage

llama.cpp

llama-cli \
  -m Qwen-3.5-28B-A3B-REAP-Q4_K_M.gguf \
  -ngl 99 \
  -c 4096 \
  -p "Your prompt here"

llama-server (OpenAI-compatible API)

llama-server \
  -m Qwen-3.5-28B-A3B-REAP-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 (recommended)	20+ GB VRAM
Hybrid CPU+GPU	12 GB VRAM + 16 GB RAM
CPU only	24+ GB RAM

About the Original Model

0xSero/Qwen-3.5-28B-A3B-REAP applies REAP expert pruning (arXiv:2510.13999) to reduce Qwen3.5-35B-A3B from 128 to fewer experts while preserving performance. The result is a 28B-parameter model with only 3B active parameters per forward pass.

License

Apache 2.0 — inherited from the original model.

Downloads last month: 68

GGUF

Model size

28B params

Architecture

qwen35moe

Hardware compatibility

3-bit

4-bit

16-bit

Inference Providers NEW

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

Model tree for barozp/Qwen-3.5-28B-A3B-REAP-GGUF

Base model

Qwen/Qwen3.5-35B-A3B-Base

Finetuned

Qwen/Qwen3.5-35B-A3B

Finetuned

0xSero/Qwen3.5-28B

Quantized

(3)

this model

Paper for barozp/Qwen-3.5-28B-A3B-REAP-GGUF

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

Paper • 2510.13999 • Published Oct 15, 2025 • 20