Instructions to use amd/Qwen3.6-35B-A3B-EXTENSOR with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use amd/Qwen3.6-35B-A3B-EXTENSOR 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 amd/Qwen3.6-35B-A3B-EXTENSOR
# Run inference directly in the terminal:
llama cli -hf amd/Qwen3.6-35B-A3B-EXTENSOR

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf amd/Qwen3.6-35B-A3B-EXTENSOR
# Run inference directly in the terminal:
llama cli -hf amd/Qwen3.6-35B-A3B-EXTENSOR

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 amd/Qwen3.6-35B-A3B-EXTENSOR
# Run inference directly in the terminal:
./llama-cli -hf amd/Qwen3.6-35B-A3B-EXTENSOR

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 amd/Qwen3.6-35B-A3B-EXTENSOR
# Run inference directly in the terminal:
./build/bin/llama-cli -hf amd/Qwen3.6-35B-A3B-EXTENSOR

Use Docker

docker model run hf.co/amd/Qwen3.6-35B-A3B-EXTENSOR

LM Studio
Jan

vLLM

How to use amd/Qwen3.6-35B-A3B-EXTENSOR with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "amd/Qwen3.6-35B-A3B-EXTENSOR"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "amd/Qwen3.6-35B-A3B-EXTENSOR",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/amd/Qwen3.6-35B-A3B-EXTENSOR

Ollama
How to use amd/Qwen3.6-35B-A3B-EXTENSOR with Ollama:
```
ollama run hf.co/amd/Qwen3.6-35B-A3B-EXTENSOR
```
Unsloth Desktop

How to use amd/Qwen3.6-35B-A3B-EXTENSOR with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf amd/Qwen3.6-35B-A3B-EXTENSOR

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "amd/Qwen3.6-35B-A3B-EXTENSOR"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use amd/Qwen3.6-35B-A3B-EXTENSOR with Docker Model Runner:
```
docker model run hf.co/amd/Qwen3.6-35B-A3B-EXTENSOR
```

Lemonade

How to use amd/Qwen3.6-35B-A3B-EXTENSOR with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull amd/Qwen3.6-35B-A3B-EXTENSOR

Run and chat with the model

lemonade run user.Qwen3.6-35B-A3B-EXTENSOR-{{QUANT_TAG}}

List all available models

lemonade list

Hermes Agent

How to use amd/Qwen3.6-35B-A3B-EXTENSOR with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf amd/Qwen3.6-35B-A3B-EXTENSOR

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 amd/Qwen3.6-35B-A3B-EXTENSOR

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use amd/Qwen3.6-35B-A3B-EXTENSOR with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf amd/Qwen3.6-35B-A3B-EXTENSOR

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 "amd/Qwen3.6-35B-A3B-EXTENSOR" \
  --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"

Qwen3.6-35B-A3B-EXTENSOR

An EXTENSOR runtime image derived from Qwen/Qwen3.6-35B-A3B. It contains the text target and its MTP draft module; the vision tower is not included. EXTENSOR uses MTP for lossless greedy speculative decoding while the target remains the authority for every emitted token.

Artifact

File: Qwen3.6-35B-A3B-EXTENSOR-ROCmFP4-MTP-v2.extensor.gguf
Size: 19,659,370,496 bytes
SHA-256: 4844f6145ece96b433b494cf87fd2da700b87333508edccbb78cfba53f953de1
Quantization: ROCmFP4/ROCmFP4_FAST target and MTP, Q8_0 MTP fusion, F16 controls
Format: GGUF v3, EXTENSOR pack v2, qmoe-v4 target slab, resident MTP expert bank

Requires EXTENSOR 2.4.0 or a newer build with backend API 4. Exact MTP verification requires the complete target expert slab resident. This file is not compatible with llama.cpp.

The target-only v1 artifact remains supported by the separate qwen35moe-rocmfp4-runtime-v1 backend profile:

File: Qwen3.6-35B-A3B-EXTENSOR-ROCmFP4-v1.extensor.gguf
Size: 19,205,345,280 bytes
SHA-256: 66260013d3ec7b880b9d148fc688a2b17f7dafcdadcdc3599738db7302edf896

Source

Qwen/Qwen3.6-35B-A3B at revision 995ad96eacd98c81ed38be0c5b274b04031597b0.

License

Apache License 2.0. See the upstream repository for usage and citation details.

Downloads last month: 200

GGUF

Model size

35B params

Architecture

qwen35moe

Hardware compatibility

We're not able to determine the quantization variants.

View all variants

Model tree for amd/Qwen3.6-35B-A3B-EXTENSOR

Base model

Qwen/Qwen3.6-35B-A3B

Quantized

(918)

this model