Qwen β REAP
Collection
REAP-pruned & quantized Qwen3.5 / 3.6 / Coder variants. β’ 15 items β’ Updated
How to use 0xSero/Qwen3.6-28B-GGUF with llama.cpp:
curl -LsSf https://llama.app/install.sh | sh # Start a local OpenAI-compatible server with a web UI: llama serve -hf 0xSero/Qwen3.6-28B-GGUF:Q4_K_M # Run inference directly in the terminal: llama cli -hf 0xSero/Qwen3.6-28B-GGUF:Q4_K_M
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf 0xSero/Qwen3.6-28B-GGUF:Q4_K_M # Run inference directly in the terminal: llama cli -hf 0xSero/Qwen3.6-28B-GGUF:Q4_K_M
git clone https://github.com/ggml-org/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-app # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama serve -hf 0xSero/Qwen3.6-28B-GGUF:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama cli -hf 0xSero/Qwen3.6-28B-GGUF:Q4_K_M
docker model run hf.co/0xSero/Qwen3.6-28B-GGUF:Q4_K_M
How to use 0xSero/Qwen3.6-28B-GGUF with vLLM:
# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "0xSero/Qwen3.6-28B-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": "0xSero/Qwen3.6-28B-GGUF",
"messages": [
{
"role": "user",
"content": "What is the capital of France?"
}
]
}'docker model run hf.co/0xSero/Qwen3.6-28B-GGUF:Q4_K_M
How to use 0xSero/Qwen3.6-28B-GGUF with Ollama:
ollama run hf.co/0xSero/Qwen3.6-28B-GGUF:Q4_K_M
How to use 0xSero/Qwen3.6-28B-GGUF with Pi:
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf 0xSero/Qwen3.6-28B-GGUF:Q4_K_M
# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
"providers": {
"llama-cpp": {
"baseUrl": "http://localhost:9931/v1",
"api": "openai-completions",
"apiKey": "none",
"models": [
{
"id": "0xSero/Qwen3.6-28B-GGUF:Q4_K_M"
}
]
}
}
}# Start Pi in your project directory: pi
How to use 0xSero/Qwen3.6-28B-GGUF with Docker Model Runner:
docker model run hf.co/0xSero/Qwen3.6-28B-GGUF:Q4_K_M
How to use 0xSero/Qwen3.6-28B-GGUF with Lemonade:
# Download Lemonade from https://lemonade-server.ai/ lemonade pull 0xSero/Qwen3.6-28B-GGUF:Q4_K_M
lemonade run user.Qwen3.6-28B-GGUF-Q4_K_M
lemonade list
How to use 0xSero/Qwen3.6-28B-GGUF with Hermes Agent:
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf 0xSero/Qwen3.6-28B-GGUF:Q4_K_M
# 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://127.0.0.1:9931/v1 hermes config set model.default 0xSero/Qwen3.6-28B-GGUF:Q4_K_M
hermes
How to use 0xSero/Qwen3.6-28B-GGUF with OpenClaw:
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf 0xSero/Qwen3.6-28B-GGUF:Q4_K_M
# 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://127.0.0.1:9931/v1 \ --custom-model-id "0xSero/Qwen3.6-28B-GGUF:Q4_K_M" \ --custom-provider-id llama-cpp \ --custom-compatibility openai \ --custom-text-input \ --accept-risk \ --skip-health
openclaw agent --local --agent main --message "Hello from Hugging Face"
Support this work β Β· X Β· GitHub Β· REAP paper Β· Cerebras REAP
GGUF quantization of the base model.
| Base model | β |
| Format | GGUF |
| Total params | 28B |
| Active / token | 3B |
| Experts / layer | β |
| Layers | β |
| Hidden size | β |
| Context | β |
| On-disk size | 147 GB |
| Variant | Format | Link |
|---|---|---|
Qwen3.6-28B |
BF16 | link |
Qwen3.6-28B-GGUF (this) |
GGUF | link |
Qwen3.6-35B-GGUF |
GGUF | link |
License inherited from the base model.
@misc{lasby2025reap,
title = {REAP the Experts: Why Pruning Prevails for One-Shot MoE Compression},
author = {Mike Lasby and Ivan Lazarevich and Nish Sinnadurai and Sean Lie and Yani Ioannou and Vithursan Thangarasa},
year = {2025}, eprint = {2510.13999}, archivePrefix = {arXiv}
}
Made possible by NVIDIA Β· TNG Technology Β· Lambda Β· Prime Intellect Β· Hot Aisle.
4-bit
5-bit
6-bit
8-bit
16-bit