Instructions to use dxx117/Qwen3.6-35B-REAP-IQ1M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use dxx117/Qwen3.6-35B-REAP-IQ1M with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="dxx117/Qwen3.6-35B-REAP-IQ1M",
	filename="qwen3.6-35b-reap25_iq1m.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 dxx117/Qwen3.6-35B-REAP-IQ1M 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 dxx117/Qwen3.6-35B-REAP-IQ1M
# Run inference directly in the terminal:
llama cli -hf dxx117/Qwen3.6-35B-REAP-IQ1M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf dxx117/Qwen3.6-35B-REAP-IQ1M
# Run inference directly in the terminal:
llama cli -hf dxx117/Qwen3.6-35B-REAP-IQ1M

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 dxx117/Qwen3.6-35B-REAP-IQ1M
# Run inference directly in the terminal:
./llama-cli -hf dxx117/Qwen3.6-35B-REAP-IQ1M

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 dxx117/Qwen3.6-35B-REAP-IQ1M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf dxx117/Qwen3.6-35B-REAP-IQ1M

Use Docker

docker model run hf.co/dxx117/Qwen3.6-35B-REAP-IQ1M

LM Studio
Jan

vLLM

How to use dxx117/Qwen3.6-35B-REAP-IQ1M with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "dxx117/Qwen3.6-35B-REAP-IQ1M"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "dxx117/Qwen3.6-35B-REAP-IQ1M",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/dxx117/Qwen3.6-35B-REAP-IQ1M

Ollama
How to use dxx117/Qwen3.6-35B-REAP-IQ1M with Ollama:
```
ollama run hf.co/dxx117/Qwen3.6-35B-REAP-IQ1M
```

Unsloth Studio

How to use dxx117/Qwen3.6-35B-REAP-IQ1M 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 dxx117/Qwen3.6-35B-REAP-IQ1M 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 dxx117/Qwen3.6-35B-REAP-IQ1M to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for dxx117/Qwen3.6-35B-REAP-IQ1M to start chatting

How to use dxx117/Qwen3.6-35B-REAP-IQ1M with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf dxx117/Qwen3.6-35B-REAP-IQ1M

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": "dxx117/Qwen3.6-35B-REAP-IQ1M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use dxx117/Qwen3.6-35B-REAP-IQ1M with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf dxx117/Qwen3.6-35B-REAP-IQ1M

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 dxx117/Qwen3.6-35B-REAP-IQ1M

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use dxx117/Qwen3.6-35B-REAP-IQ1M with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf dxx117/Qwen3.6-35B-REAP-IQ1M

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 "dxx117/Qwen3.6-35B-REAP-IQ1M" \
  --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 dxx117/Qwen3.6-35B-REAP-IQ1M with Docker Model Runner:
```
docker model run hf.co/dxx117/Qwen3.6-35B-REAP-IQ1M
```

Lemonade

How to use dxx117/Qwen3.6-35B-REAP-IQ1M with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull dxx117/Qwen3.6-35B-REAP-IQ1M

Run and chat with the model

lemonade run user.Qwen3.6-35B-REAP-IQ1M-{{QUANT_TAG}}

List all available models

lemonade list

Qwen 3.6 35B A3B REAP IQ1_M GGUFs

This repo contains three experimental IQ1_M GGUF quants derived from REAP-pruned Qwen 3.6 35B A3B checkpoints. I just wanted to get a local LLM that could answer the car wash test correctly on my iPad Pro with 8GB RAM as all the other smaller LLMs it could run just couldn't, and also faster than 3tk/s for the full 35B IQ1M model due to partial offload to swap.

These are not plain base-model quants. They come from REAP-pruned MoE checkpoints, then were converted to trunk-only GGUF and quantized with a Bartowski-style Qwen 3.6 IQ1_M tensor policy.

What These Are

Starting point:

Qwen/Qwen3.6-35B-A3B

Pruning method:

REAP expert pruning on the HF BF16 model

Quantization method:

GGUF export
trunk-only / no-mtp conversion path
fresh per-model imatrix
Bartowski-style Qwen 3.6 IQ1_M tensor map

Recommended Variant

Use qwen3.6-35b-reap25_iq1m.gguf if you want the strongest general-purpose REAP variant.
Use qwen3.6-35b-reap40_iq1m.gguf if you care more about instruction-following and strict prompt obedience.
Use qwen3.6-35b-reap50_iq1m.gguf only if size is the main priority.

Benchmarks

35B Model	Size	HellaSwag	ARC-C	IFEval Prompt Strict	IFEval Inst Strict	Car wash test	iPad Pro M1 CPU TG
`reap25_iq1m`	7.93 GB	77.5642	50.5017	0.3641	0.4868	Yes	7.18
`reap40_iq1m`	6.68 GB	71.2209	49.4983	0.4067	0.5432	Sometimes	8.06
`reap50_iq1m`	5.82 GB	64.2004	50.1672	0.4011	0.5360	No	7.91
`bartowski_iq1m`	10.04 GB	80.1733	50.1672	0.4584	0.5707	Yes	3-4
`unsloth_q4_k_xl`	20.82 GB	82.4935	53.1773	0.3272	0.4616	Yes	N/A

Interpretation

reap25 is the strongest broad-quality REAP quant.
reap40 is the most interesting instruction-following variant. It gives up a lot on HellaSwag, but beats reap25 and reap50 on both strict IFEval metrics.
reap50 is the most compressed and the most uneven. It keeps ARC surprisingly well, but broad completion quality drops much harder.

One likely explanation is that heavier REAP pruning narrows the model more than it destroys literal instruction compliance. That can hurt broad reasoning / continuation tasks while still preserving, or sometimes slightly improving, rigid format-following behavior.

Downloads last month: 266

GGUF

Model size

27B params

Architecture

qwen35moe

Hardware compatibility

We're not able to determine the quantization variants.

View all variants

Model tree for dxx117/Qwen3.6-35B-REAP-IQ1M

Base model

Qwen/Qwen3.6-35B-A3B

Quantized

(658)

this model