The raw HauhauCS/Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive GGUF (IQ2_M) without any constitutional system prompt. Same 11.7 GB IQ2_M file, zero runtime constraints.

Property	Value
Architecture	Qwen3.6 (35B total, ~3B active per token via MoE)
Quantization	IQ2_M
Size	11 GB
Context	Native 262K tokens, recommended 8K minimum
Runtime	llama.cpp / llama-cpp-python / Ollama
System Prompt	None — bare model, no constitution

Quick Start

Ollama

ollama run hf.co/ordlibrary/hauhau-qwen36-uncensored

llama.cpp

bash

./llama-cli -m Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive-IQ2_M.gguf \
  --temp 0.6 --ctx-size 8192

Python (llama-cpp-python)

pip install llama-cpp-python

python

from llama_cpp import Llama

llm = Llama(
    model_path="Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive-IQ2_M.gguf",
    n_ctx=8192,
    verbose=False
)

output = llm("What's your take on Solana memecoins?", max_tokens=512)
print(output["choices"][0]["text"])

Modelfile (Ollama)

dockerfile

FROM Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive-IQ2_M.gguf

TEMPLATE """{{- if .System }}<|im_start|>system
{{ .System }}<|im_end|>
{{ end }}{{- if .Prompt }}<|im_start|>user
{{ .Prompt }}<|im_end|>
{{ end }}<|im_start|>assistant
{{ .Response }}"""

PARAMETER num_ctx 8192
PARAMETER temperature 0.7
PARAMETER top_p 0.95
PARAMETER stop "<|im_end|>"
PARAMETER stop "<|endoftext|>"

Contrast with the Onchain Edition

Variant	System Prompt	Use Case
`ordlibrary/hauhau-qwen36-onchain`	Full Onchain Constitution (20 articles)	Sovereign agent, verifiable inference
`ordlibrary/hauhau-qwen36-uncensored`	None	Raw model — no guardrails, full aggression

Source

Base: HauhauCS/Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive
Quant: IQ2_M (11 GB)