Instructions to use quimmedes/Deepwen-3.6 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use quimmedes/Deepwen-3.6 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 quimmedes/Deepwen-3.6:BF16
# Run inference directly in the terminal:
llama cli -hf quimmedes/Deepwen-3.6:BF16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf quimmedes/Deepwen-3.6:BF16
# Run inference directly in the terminal:
llama cli -hf quimmedes/Deepwen-3.6:BF16

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 quimmedes/Deepwen-3.6:BF16
# Run inference directly in the terminal:
./llama-cli -hf quimmedes/Deepwen-3.6:BF16

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 quimmedes/Deepwen-3.6:BF16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf quimmedes/Deepwen-3.6:BF16

Use Docker

docker model run hf.co/quimmedes/Deepwen-3.6:BF16

LM Studio
Jan

vLLM

How to use quimmedes/Deepwen-3.6 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "quimmedes/Deepwen-3.6"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "quimmedes/Deepwen-3.6",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/quimmedes/Deepwen-3.6:BF16

Ollama
How to use quimmedes/Deepwen-3.6 with Ollama:
```
ollama run hf.co/quimmedes/Deepwen-3.6:BF16
```

Unsloth Studio

How to use quimmedes/Deepwen-3.6 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 quimmedes/Deepwen-3.6 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 quimmedes/Deepwen-3.6 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for quimmedes/Deepwen-3.6 to start chatting

How to use quimmedes/Deepwen-3.6 with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf quimmedes/Deepwen-3.6:BF16

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": "quimmedes/Deepwen-3.6:BF16"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use quimmedes/Deepwen-3.6 with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf quimmedes/Deepwen-3.6:BF16

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 quimmedes/Deepwen-3.6:BF16

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use quimmedes/Deepwen-3.6 with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf quimmedes/Deepwen-3.6:BF16

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 "quimmedes/Deepwen-3.6:BF16" \
  --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 quimmedes/Deepwen-3.6 with Docker Model Runner:
```
docker model run hf.co/quimmedes/Deepwen-3.6:BF16
```

Lemonade

How to use quimmedes/Deepwen-3.6 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull quimmedes/Deepwen-3.6:BF16

Run and chat with the model

lemonade run user.Deepwen-3.6-BF16

List all available models

lemonade list

Deepwen 3.6

Deepwen 3.6 is a fine-tuned derivative of Qwen/Qwen3.6-35B-A3B (Mixture-of-Experts, ~35B total / ~3B active), specialized for AAA GameDev 3D production workflows: procedural geometry, hard-surface shape language, and Blender/Unreal asset pipelines.

What the model has

Advanced thinking (DeepSeek style) — the model reasons before it answers. Its thinking comes from two sources:
- Supervised reasoning training: 93.6% of its reasoning-focused training examples (103/110) carry a full reasoning chain as part of the target.
- Reasoning-effort control: a chat template ported from deepseek-ai/DeepSeek-V4-Flash-0731, with three effort levels — low (default), xhigh, and max ("Beyond maximum — exhaustive, relentless... do not stop reasoning until you have independently verified the solution from multiple angles").
Procedural 3D generation — explicit blockout gating before high-poly, conditional lightmap workflows, combinatorial validation, non-destructive pipelines.
Hard-surface shape language — stance/relational design, primary volume architecture, motif propagation, panel breakup.
Multi-skill asset workflows — Blender modifier-driven gear recipes, tooth profile generation, PBR game-prep, layered lighting legibility.

Improvements over the base model

Paired evaluations on held-out tasks (same server, same seeds):

Capability	Improvement
Procedural generation	`blockout_gate`: PARTIAL → PASS; `conditional_lightmap`: FAIL → PASS; 5 units improved vs 2 regressed
Replay safety	base competence suite 6/6 intact (no regressions)
Shape / hard-surface	no catastrophic flips across held-out objects
Blender gear recipe	modifier_workflow, tooth_profile_generation, game_prep_uv_pbr, non_destructive_order
Lighting	layered lighting legibility (bounce and ambient)

Quantizations (MoQ)

All files quantized with the Mixture of Quantizations (MoQ) method proposed by Waleed Ahmad: per-tensor type selection (attention/embeddings at higher precision, MLP/experts at more aggressive types) instead of a single type for every tensor.

File	Approx. size	Notes
`Deepwen-3.6-Q2-MoQ.gguf`	~10 GB	aggressive MoQ mix
`Deepwen-3.6-Q3-MoQ.gguf`	~13 GB	3.0 bpw target
`Deepwen-3.6-Q4.5-MoQ.gguf`	~21 GB	4.5 bpw target, sweet spot for local use
`Deepwen-3.6-Q5-MoQ.gguf`	~22 GB	5.0 bpw target
`Deepwen-3.6-Q6-MoQ.gguf`	~27 GB
`Deepwen-3.6-Q8-MoQ.gguf`	~36 GB	near-lossless
`Deepwen-3.6-BF16.gguf`	~70 GB	original merged weights, bf16

Usage

llama-server -m Deepwen-3.6-Q4.5-MoQ.gguf --host 0.0.0.0 --port 8080
# OpenAI-compatible: /v1/chat/completions

To enable advanced thinking at maximum effort:

{
  "messages": [{"role": "user", "content": "..."}],
  "chat_template_kwargs": {"reasoning_effort": "max"}
}

Works with llama.cpp (b3050+), LM Studio, Ollama, Jan.

Disclosures

The base model is released under the Apache License 2.0; this derivative inherits that license.
Qwen 3.6 is a copyrighted, trademarked model family of Alibaba. "Deepwen 3.6" is an independent fine-tuned derivative and is not affiliated with, endorsed by, or sponsored by Alibaba / Qwen. The "Qwen" name is used solely to identify the base model.
The embedded reasoning-effort prompts are adapted from the chat template of deepseek-ai/DeepSeek-V4-Flash-0731; DeepSeek remains the copyright holder of those prompt texts.
MoQ quantization method: "Mixture of Quantizations" proposed by Waleed Ahmad (https://huggingface.co/w-ahmad).
This model is provided as-is, without warranties of any kind, for research and local experimentation.

Downloads last month: 18

GGUF

Model size

35B params

Architecture

qwen35moe

Hardware compatibility

We're not able to determine the quantization variants.

View all variants

Model tree for quimmedes/Deepwen-3.6

Base model

Qwen/Qwen3.6-35B-A3B

Quantized

(690)

this model