Instructions to use JZC973/Qwen3.6-35B-REAP-MTP-UD-GGUF-Collection with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use JZC973/Qwen3.6-35B-REAP-MTP-UD-GGUF-Collection with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="JZC973/Qwen3.6-35B-REAP-MTP-UD-GGUF-Collection",
	filename="Qwen3.6-35B-A3B-UD-IQ3_S-REAP-RangerX.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 JZC973/Qwen3.6-35B-REAP-MTP-UD-GGUF-Collection with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf JZC973/Qwen3.6-35B-REAP-MTP-UD-GGUF-Collection:UD-IQ3_S
# Run inference directly in the terminal:
llama-cli -hf JZC973/Qwen3.6-35B-REAP-MTP-UD-GGUF-Collection:UD-IQ3_S

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf JZC973/Qwen3.6-35B-REAP-MTP-UD-GGUF-Collection:UD-IQ3_S
# Run inference directly in the terminal:
llama-cli -hf JZC973/Qwen3.6-35B-REAP-MTP-UD-GGUF-Collection:UD-IQ3_S

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 JZC973/Qwen3.6-35B-REAP-MTP-UD-GGUF-Collection:UD-IQ3_S
# Run inference directly in the terminal:
./llama-cli -hf JZC973/Qwen3.6-35B-REAP-MTP-UD-GGUF-Collection:UD-IQ3_S

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 JZC973/Qwen3.6-35B-REAP-MTP-UD-GGUF-Collection:UD-IQ3_S
# Run inference directly in the terminal:
./build/bin/llama-cli -hf JZC973/Qwen3.6-35B-REAP-MTP-UD-GGUF-Collection:UD-IQ3_S

Use Docker

docker model run hf.co/JZC973/Qwen3.6-35B-REAP-MTP-UD-GGUF-Collection:UD-IQ3_S

LM Studio
Jan
Ollama
How to use JZC973/Qwen3.6-35B-REAP-MTP-UD-GGUF-Collection with Ollama:
```
ollama run hf.co/JZC973/Qwen3.6-35B-REAP-MTP-UD-GGUF-Collection:UD-IQ3_S
```

Unsloth Studio

How to use JZC973/Qwen3.6-35B-REAP-MTP-UD-GGUF-Collection 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 JZC973/Qwen3.6-35B-REAP-MTP-UD-GGUF-Collection 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 JZC973/Qwen3.6-35B-REAP-MTP-UD-GGUF-Collection to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for JZC973/Qwen3.6-35B-REAP-MTP-UD-GGUF-Collection to start chatting

How to use JZC973/Qwen3.6-35B-REAP-MTP-UD-GGUF-Collection with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf JZC973/Qwen3.6-35B-REAP-MTP-UD-GGUF-Collection:UD-IQ3_S

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": "JZC973/Qwen3.6-35B-REAP-MTP-UD-GGUF-Collection:UD-IQ3_S"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use JZC973/Qwen3.6-35B-REAP-MTP-UD-GGUF-Collection with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf JZC973/Qwen3.6-35B-REAP-MTP-UD-GGUF-Collection:UD-IQ3_S

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 JZC973/Qwen3.6-35B-REAP-MTP-UD-GGUF-Collection:UD-IQ3_S

Run Hermes

hermes

Atomic Chat new
Docker Model Runner
How to use JZC973/Qwen3.6-35B-REAP-MTP-UD-GGUF-Collection with Docker Model Runner:
```
docker model run hf.co/JZC973/Qwen3.6-35B-REAP-MTP-UD-GGUF-Collection:UD-IQ3_S
```

Lemonade

How to use JZC973/Qwen3.6-35B-REAP-MTP-UD-GGUF-Collection with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull JZC973/Qwen3.6-35B-REAP-MTP-UD-GGUF-Collection:UD-IQ3_S

Run and chat with the model

lemonade run user.Qwen3.6-35B-REAP-MTP-UD-GGUF-Collection-UD-IQ3_S

List all available models

lemonade list

YAML Metadata Warning:empty or missing yaml metadata in repo card

Check out the documentation for more information.

Qwen 3.6 REAP-Pruned MTP GGUF Collection

This archive contains a collection of pruned models derived from Unsloth's Qwen 3.6 35B MTP GGUF. These models have been pruned using the REAP (Routed-Expert Pruning) strategy while carefully maintaining the Multi-Token Prediction (MTP) layer (Layer 40) functionality.

Models Included

1. ATBender Configuration (192 Experts)

Pruned based on the atbender/Qwen3.6-VL-REAP-26B-A3B strategy.

Qwen3.6-35B-A3B-UD-IQ3_S-REAP.gguf
Qwen3.6-35B-A3B-UD-IQ3_XXS-REAP.gguf
Qwen3.6-35B-A3B-UD-Q3_K_M-REAP.gguf
Qwen3.6-35B-A3B-UD-Q3_K_XL-REAP.gguf

2. RangerX Configuration (180 Experts, Ratio 0.3)

Pruned based on the RangerX/Qwen3.6-35B-REAP-Pruned-ratio-0.3 strategy (reverse-engineered from router weights).

Qwen3.6-35B-A3B-UD-IQ3_S-REAP-RangerX.gguf
Qwen3.6-35B-A3B-UD-IQ3_XXS-REAP-RangerX.gguf
Qwen3.6-35B-A3B-UD-Q3_K_M-REAP-RangerX.gguf
Qwen3.6-35B-A3B-UD-Q3_K_XL-REAP-RangerX.gguf

Creation Process

These models were created using a custom Python script that:

Identified Kept Experts: For the ATBender set, indices were pulled from reap_metadata.json. For the RangerX set, indices were reverse-engineered by comparing the pruned router gate weights against the original unpruned gates via cosine similarity.
Surgical Slicing: The script directly sliced the GGUF tensors along the expert dimension (dim0 in the raw memory layout) without dequantizing the individual blocks.
MTP Preservation: All MTP-specific tensors (Layer 40) were handled correctly. For tensors with expert dimensions in Layer 40, the Layer 39 pruning strategy was applied to maintain architectural consistency.
Metadata Updates: The qwen35moe.expert_count was updated in the GGUF headers to ensure compatibility with llama.cpp.

Usage

To run with MTP support, use a recent build of llama.cpp (May 2026 or later) with the following flag: --spec-type draft-mtp --spec-draft-n-max 3

Created by Gemini CLI on May 21, 2026.

Downloads last month: 2,508

GGUF

Model size

26B params

Architecture

qwen35moe

Hardware compatibility

3-bit

Inference Providers NEW

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