Instructions to use cahlen/Qwen3.5-35B-A3B-Uncensored-HauhauCS-Aggressive-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use cahlen/Qwen3.5-35B-A3B-Uncensored-HauhauCS-Aggressive-GGUF 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 cahlen/Qwen3.5-35B-A3B-Uncensored-HauhauCS-Aggressive-GGUF:Q4_K_S
# Run inference directly in the terminal:
llama cli -hf cahlen/Qwen3.5-35B-A3B-Uncensored-HauhauCS-Aggressive-GGUF:Q4_K_S

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf cahlen/Qwen3.5-35B-A3B-Uncensored-HauhauCS-Aggressive-GGUF:Q4_K_S
# Run inference directly in the terminal:
llama cli -hf cahlen/Qwen3.5-35B-A3B-Uncensored-HauhauCS-Aggressive-GGUF:Q4_K_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 cahlen/Qwen3.5-35B-A3B-Uncensored-HauhauCS-Aggressive-GGUF:Q4_K_S
# Run inference directly in the terminal:
./llama-cli -hf cahlen/Qwen3.5-35B-A3B-Uncensored-HauhauCS-Aggressive-GGUF:Q4_K_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 cahlen/Qwen3.5-35B-A3B-Uncensored-HauhauCS-Aggressive-GGUF:Q4_K_S
# Run inference directly in the terminal:
./build/bin/llama-cli -hf cahlen/Qwen3.5-35B-A3B-Uncensored-HauhauCS-Aggressive-GGUF:Q4_K_S

Use Docker

docker model run hf.co/cahlen/Qwen3.5-35B-A3B-Uncensored-HauhauCS-Aggressive-GGUF:Q4_K_S

LM Studio
Jan
Ollama
How to use cahlen/Qwen3.5-35B-A3B-Uncensored-HauhauCS-Aggressive-GGUF with Ollama:
```
ollama run hf.co/cahlen/Qwen3.5-35B-A3B-Uncensored-HauhauCS-Aggressive-GGUF:Q4_K_S
```

Unsloth Studio

How to use cahlen/Qwen3.5-35B-A3B-Uncensored-HauhauCS-Aggressive-GGUF 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 cahlen/Qwen3.5-35B-A3B-Uncensored-HauhauCS-Aggressive-GGUF 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 cahlen/Qwen3.5-35B-A3B-Uncensored-HauhauCS-Aggressive-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for cahlen/Qwen3.5-35B-A3B-Uncensored-HauhauCS-Aggressive-GGUF to start chatting

How to use cahlen/Qwen3.5-35B-A3B-Uncensored-HauhauCS-Aggressive-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf cahlen/Qwen3.5-35B-A3B-Uncensored-HauhauCS-Aggressive-GGUF:Q4_K_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": "cahlen/Qwen3.5-35B-A3B-Uncensored-HauhauCS-Aggressive-GGUF:Q4_K_S"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

OpenClaw new

How to use cahlen/Qwen3.5-35B-A3B-Uncensored-HauhauCS-Aggressive-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf cahlen/Qwen3.5-35B-A3B-Uncensored-HauhauCS-Aggressive-GGUF:Q4_K_S

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 "cahlen/Qwen3.5-35B-A3B-Uncensored-HauhauCS-Aggressive-GGUF:Q4_K_S" \
  --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 cahlen/Qwen3.5-35B-A3B-Uncensored-HauhauCS-Aggressive-GGUF with Docker Model Runner:
```
docker model run hf.co/cahlen/Qwen3.5-35B-A3B-Uncensored-HauhauCS-Aggressive-GGUF:Q4_K_S
```

Lemonade

How to use cahlen/Qwen3.5-35B-A3B-Uncensored-HauhauCS-Aggressive-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull cahlen/Qwen3.5-35B-A3B-Uncensored-HauhauCS-Aggressive-GGUF:Q4_K_S

Run and chat with the model

lemonade run user.Qwen3.5-35B-A3B-Uncensored-HauhauCS-Aggressive-GGUF-Q4_K_S

List all available models

lemonade list

Hermes Agent

How to use cahlen/Qwen3.5-35B-A3B-Uncensored-HauhauCS-Aggressive-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf cahlen/Qwen3.5-35B-A3B-Uncensored-HauhauCS-Aggressive-GGUF:Q4_K_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 cahlen/Qwen3.5-35B-A3B-Uncensored-HauhauCS-Aggressive-GGUF:Q4_K_S

Run Hermes

hermes

Atomic Chat

Qwen3.5-35B-A3B-Uncensored-HauhauCS-Aggressive-GGUF

Full llama.cpp quantization ladder for HauhauCS/Qwen3.5-35B-A3B-Uncensored-HauhauCS-Aggressive. K-quants from Q8_0 through Q4 use standard llama-quantize without an importance matrix. Low-bit Q3_K_L / Q3_K_M / Q3_K_S, Q2_K, and all IQ* types use WikiText-2 importance-matrix calibration (200 chunks) when this workspace contains imatrix.dat.

About the Source Model

This repo is a GGUF quantization ladder for HauhauCS/Qwen3.5-35B-A3B-Uncensored-HauhauCS-Aggressive: an Aggressive uncensored build based on Qwen/Qwen3.5-35B-A3B (MoE, multimodal, long context). Low-bit K-quants (Q3_K*, Q2_K) and IQ-types use an importance matrix when imatrix.dat was produced in this run—same spirit as our compacted Qwen3.5 GGUF ladder.

For refusal behavior, recommended sampling settings, and mmproj vision tensors, follow the HauhauCS model card and Qwen docs. Note: LM Studio may show 256×2.6B in the params column; HauhauCS reports this is a cosmetic metadata quirk.

Complementary files (read this if a quant is missing here)

The HauhauCS weight index already hosts BF16, Q8_0 through Q6_K, several Q4/Q5 variants, IQ4_XS, IQ3_M, IQ2_M, Q3_K_M, etc. This cahlen companion repo (HF names end with -GGUF) is disk-aware: it adds the extra ladder rungs we use on constrained hardware (e.g. Q5_K_S, Q4_K_S, Q3_K_L / Q3_K_S, Q2_K, IQ3_S, IQ3_XXS, IQ2_S, IQ2_XXS, IQ1_M) with the same WikiText-2 / 200-chunk imatrix workflow as cahlen/qwen3.5-35b-a3b-compacted-GGUF. Pull from HauhauCS if you need a size we do not mirror here.

Available Quantizations

Filename	Quant	Size	Notes
Q5_K_S	Q5_K_S	23G	K-quant
Q4_K_S	Q4_K_S	19G	K-quant
Q3_K_L	Q3_K_L	17G	imatrix
Q3_K_S	Q3_K_S	15G	imatrix
IQ3_S	IQ3_S	15G	imatrix
IQ3_XXS	IQ3_XXS	13G	imatrix
Q2_K	Q2_K	13G	imatrix
IQ2_S	IQ2_S	10G	imatrix
IQ2_XXS	IQ2_XXS	8.9G	imatrix
IQ1_M	IQ1_M	7.7G	imatrix
mmproj-...-f16.gguf	mmproj (vision)	858M	Pair with any quant above

All filenames are prefixed with Qwen3.5-35B-A3B-Uncensored-HauhauCS-Aggressive-. The BF16 baseline (65G) was used locally for quantization but is not uploaded to save space; grab it from the HauhauCS source repo if needed. "imatrix" rows used WikiText-2 importance-matrix calibration (200 chunks).

Quality (WikiText-2 Perplexity)

Lower is better. First row is the unquantized baseline.

Quant	Size	Perplexity	vs Baseline
BF16 (baseline)	65G	6.4393	—
Q5_K_S	23G	6.4871	+0.7%
Q4_K_S	19G	6.6214	+2.8%
Q3_K_L	17G	6.7204	+4.4%
IQ3_S	15G	6.7631	+5.0%
Q3_K_S	15G	6.9724	+8.3%
IQ3_XXS	13G	7.0490	+9.5%
Q2_K	13G	7.4896	+16.3%
IQ2_S	10G	8.1019	+25.8%
IQ2_XXS	8.9G	9.0738	+40.9%
IQ1_M	7.7G	11.1425	+73.0%

Measured with llama-perplexity on the WikiText-2 test set (580 chunks, context 512). BF16 baseline evaluated on CPU; quantized variants on NVIDIA RTX 5090.

How to Use

With llama.cpp (text)

llama-cli -m Qwen3.5-35B-A3B-Uncensored-HauhauCS-Aggressive-Q4_K_S.gguf --jinja -c 131072 -ngl 99 -p "Hello"

With llama.cpp (vision)

llama-cli -m Qwen3.5-35B-A3B-Uncensored-HauhauCS-Aggressive-Q4_K_S.gguf \
  --mmproj mmproj-Qwen3.5-35B-A3B-Uncensored-HauhauCS-Aggressive-f16.gguf \
  --jinja -c 131072 -ngl 99

With llama-server

llama-server -m Qwen3.5-35B-A3B-Uncensored-HauhauCS-Aggressive-Q4_K_S.gguf --jinja -c 131072 -ngl 99

With Ollama

ollama run hf.co/cahlen/Qwen3.5-35B-A3B-Uncensored-HauhauCS-Aggressive-GGUF:Q4_K_S

With LM Studio

Download any GGUF from the table and load it.

Choosing a Quant

Rough disk size / VRAM guidance (actual usage varies by context length and loader). Quants marked ★ are in this repo; others are on the HauhauCS source repo.

Your VRAM	Try	Size
24GB+	Q8_0 or Q6_K (HauhauCS)	largest
16GB	★ Q5_K_S / ★ Q4_K_S	19–23G
12GB	★ Q3_K_L / ★ IQ3_S	15–17G
8GB	★ IQ3_XXS / ★ Q2_K	13G
6GB	★ IQ2_S / ★ IQ2_XXS	8.9–10G

Quantization Details

Quantized by: cahlen
Importance matrix: WikiText-2 (wikitext-2-raw-v1, 200 chunks), when generated for this run
Tool: llama.cpp @ 59d840209
Hardware: NVIDIA RTX 5090 32GB / Intel Core Ultra 9 285K / 188GB RAM

Downloads last month: 744

GGUF

Model size

35B params

Architecture

qwen35moe

Hardware compatibility

1-bit

2-bit

3-bit

4-bit

5-bit

Inference Providers NEW

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

Model tree for cahlen/Qwen3.5-35B-A3B-Uncensored-HauhauCS-Aggressive-GGUF

Base model

Qwen/Qwen3.5-35B-A3B-Base

Finetuned

Qwen/Qwen3.5-35B-A3B

Quantized

HauhauCS/Qwen3.5-35B-A3B-Uncensored-HauhauCS-Aggressive

Quantized

(7)

this model