Instructions to use HauhauCS/Qwen3.5-35B-Optimized-HauhauCS-40 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use HauhauCS/Qwen3.5-35B-Optimized-HauhauCS-40 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 HauhauCS/Qwen3.5-35B-Optimized-HauhauCS-40:F16
# Run inference directly in the terminal:
llama cli -hf HauhauCS/Qwen3.5-35B-Optimized-HauhauCS-40:F16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf HauhauCS/Qwen3.5-35B-Optimized-HauhauCS-40:F16
# Run inference directly in the terminal:
llama cli -hf HauhauCS/Qwen3.5-35B-Optimized-HauhauCS-40:F16

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 HauhauCS/Qwen3.5-35B-Optimized-HauhauCS-40:F16
# Run inference directly in the terminal:
./llama-cli -hf HauhauCS/Qwen3.5-35B-Optimized-HauhauCS-40:F16

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 HauhauCS/Qwen3.5-35B-Optimized-HauhauCS-40:F16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf HauhauCS/Qwen3.5-35B-Optimized-HauhauCS-40:F16

Use Docker

docker model run hf.co/HauhauCS/Qwen3.5-35B-Optimized-HauhauCS-40:F16

LM Studio
Jan
Ollama
How to use HauhauCS/Qwen3.5-35B-Optimized-HauhauCS-40 with Ollama:
```
ollama run hf.co/HauhauCS/Qwen3.5-35B-Optimized-HauhauCS-40:F16
```

Unsloth Studio

How to use HauhauCS/Qwen3.5-35B-Optimized-HauhauCS-40 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 HauhauCS/Qwen3.5-35B-Optimized-HauhauCS-40 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 HauhauCS/Qwen3.5-35B-Optimized-HauhauCS-40 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for HauhauCS/Qwen3.5-35B-Optimized-HauhauCS-40 to start chatting

How to use HauhauCS/Qwen3.5-35B-Optimized-HauhauCS-40 with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf HauhauCS/Qwen3.5-35B-Optimized-HauhauCS-40:F16

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": "HauhauCS/Qwen3.5-35B-Optimized-HauhauCS-40:F16"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use HauhauCS/Qwen3.5-35B-Optimized-HauhauCS-40 with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf HauhauCS/Qwen3.5-35B-Optimized-HauhauCS-40:F16

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 HauhauCS/Qwen3.5-35B-Optimized-HauhauCS-40:F16

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use HauhauCS/Qwen3.5-35B-Optimized-HauhauCS-40 with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf HauhauCS/Qwen3.5-35B-Optimized-HauhauCS-40:F16

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 "HauhauCS/Qwen3.5-35B-Optimized-HauhauCS-40:F16" \
  --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 HauhauCS/Qwen3.5-35B-Optimized-HauhauCS-40 with Docker Model Runner:
```
docker model run hf.co/HauhauCS/Qwen3.5-35B-Optimized-HauhauCS-40:F16
```

Lemonade

How to use HauhauCS/Qwen3.5-35B-Optimized-HauhauCS-40 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull HauhauCS/Qwen3.5-35B-Optimized-HauhauCS-40:F16

Run and chat with the model

lemonade run user.Qwen3.5-35B-Optimized-HauhauCS-40-F16

List all available models

lemonade list

You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

Qwen3.5-35B-Optimized-HauhauCS

Join the Discord for updates, roadmaps, projects, or just to chat.

Optimized Qwen3.5-35B-A3B by HauhauCS.

Access

This is currently a Closed Beta release designed to lower (V)RAM requirements by up to 50% without sacrificing real world capabilities.

Downloads

File	Type	Size
Qwen3.5-35B-Optimized-HauhauCS-40-Q8_K_P.gguf	Q8_K_P	25 GB
Qwen3.5-35B-Optimized-HauhauCS-40-Q4_K_P.gguf	Q4_K_P	14 GB
mmproj-Qwen3.5-35B-Optimized-HauhauCS-40-f16.gguf	mmproj (F16)	858 MB

What are K_P quants?

K_P quants use model-specific importance analysis to selectively preserve quality where it matters most. Fully compatible with llama.cpp, LM Studio, and any GGUF runtime.

Specs

35B-A3B MoE (35B total, ~3B active per forward pass)
262K context
Multimodal (vision support via mmproj)
Based on Qwen3.5-35B-A3B

Usage

Works with llama.cpp, LM Studio, Jan, koboldcpp, etc.

llama-cli -m Qwen3.5-35B-Optimized-HauhauCS-40-Q8_K_P.gguf --mmproj mmproj-Qwen3.5-35B-Optimized-HauhauCS-40-f16.gguf -ngl 99

Note: K_P quants may show as "?" in LM Studio's quant column — display issue only, loads and runs fine.

Downloads last month: -

GGUF

Model size

22B params

Architecture

qwen35moe

Hardware compatibility

We're not able to determine the quantization variants.

View +1 variant

Inference Providers NEW

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