Instructions to use Assiduous42/Qwen3.6-27B-Fable-Fusion-711-Heretic2-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 Assiduous42/Qwen3.6-27B-Fable-Fusion-711-Heretic2-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 Assiduous42/Qwen3.6-27B-Fable-Fusion-711-Heretic2-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Assiduous42/Qwen3.6-27B-Fable-Fusion-711-Heretic2-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Assiduous42/Qwen3.6-27B-Fable-Fusion-711-Heretic2-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Assiduous42/Qwen3.6-27B-Fable-Fusion-711-Heretic2-GGUF:Q4_K_M

Build from source code

git clone https://github.com/ggml-org/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-app
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama serve -hf Assiduous42/Qwen3.6-27B-Fable-Fusion-711-Heretic2-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama cli -hf Assiduous42/Qwen3.6-27B-Fable-Fusion-711-Heretic2-GGUF:Q4_K_M

Use Docker

docker model run hf.co/Assiduous42/Qwen3.6-27B-Fable-Fusion-711-Heretic2-GGUF:Q4_K_M

Llama new
LM Studio
Jan

vLLM

How to use Assiduous42/Qwen3.6-27B-Fable-Fusion-711-Heretic2-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Assiduous42/Qwen3.6-27B-Fable-Fusion-711-Heretic2-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Assiduous42/Qwen3.6-27B-Fable-Fusion-711-Heretic2-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Assiduous42/Qwen3.6-27B-Fable-Fusion-711-Heretic2-GGUF:Q4_K_M

Ollama
How to use Assiduous42/Qwen3.6-27B-Fable-Fusion-711-Heretic2-GGUF with Ollama:
```
ollama run hf.co/Assiduous42/Qwen3.6-27B-Fable-Fusion-711-Heretic2-GGUF:Q4_K_M
```
Unsloth Desktop

How to use Assiduous42/Qwen3.6-27B-Fable-Fusion-711-Heretic2-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Assiduous42/Qwen3.6-27B-Fable-Fusion-711-Heretic2-GGUF:Q4_K_M

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": "Assiduous42/Qwen3.6-27B-Fable-Fusion-711-Heretic2-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use Assiduous42/Qwen3.6-27B-Fable-Fusion-711-Heretic2-GGUF with Docker Model Runner:
```
docker model run hf.co/Assiduous42/Qwen3.6-27B-Fable-Fusion-711-Heretic2-GGUF:Q4_K_M
```

Lemonade

How to use Assiduous42/Qwen3.6-27B-Fable-Fusion-711-Heretic2-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Assiduous42/Qwen3.6-27B-Fable-Fusion-711-Heretic2-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Qwen3.6-27B-Fable-Fusion-711-Heretic2-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use Assiduous42/Qwen3.6-27B-Fable-Fusion-711-Heretic2-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 Assiduous42/Qwen3.6-27B-Fable-Fusion-711-Heretic2-GGUF:Q4_K_M

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 Assiduous42/Qwen3.6-27B-Fable-Fusion-711-Heretic2-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use Assiduous42/Qwen3.6-27B-Fable-Fusion-711-Heretic2-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Assiduous42/Qwen3.6-27B-Fable-Fusion-711-Heretic2-GGUF:Q4_K_M

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 "Assiduous42/Qwen3.6-27B-Fable-Fusion-711-Heretic2-GGUF:Q4_K_M" \
  --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"

Qwen3.6-27B-Fable-Fusion-711-Heretic2 — GGUF

GGUF quants of Assiduous42/Qwen3.6-27B-Fable-Fusion-711-Heretic2 — a terminal Heretic ablation of DavidAU's Fable-Fusion-711, targeted at creative-writing refusals rather than AdvBench-style harm refusals.

See the source repo for method, prompt-set design, and honest caveats on the refusal numbers.

Files

file	size	notes
`FF-Heretic2-Q4_K_S.gguf`	15.59 GB	tested; fits 98k ctx on 24 GB with Q4_0 KV
`FF-Heretic2-Q4_K_M.gguf`	16.55 GB
`FF-Heretic2-Q5_K_M.gguf`	19.23 GB
`mmproj-F16.gguf`	0.93 GB	vision projector, from the base model (unmodified by the ablation)

No Q5_1 tensors in any quant — see the note at the bottom on why that matters.

Measured on a single RTX 4090 (24 GB)

FF-Heretic2-Q4_K_S in LM Studio, 98304 context, Q4_0 K and V cache:


load time	9 s
VRAM	20311 MiB (18585 MiB model + KV)
headroom	3828 MiB free
generation	~29.5 tok/s

⚠️ Patched metadata — read this if you compare against the original

The base model is a -MTP build carrying an extra multi-token-prediction layer (blk.64). transformers does not model that head, so it was dropped during the LoRA merge — these weights have 64 layers, not 65.

The converter still read nextn_predict_layers: 1 and wrote block_count: 65, producing files that failed to load with:

check_tensor_dims: tensor 'blk.64.attn_norm.weight' not found

Both keys were corrected in-place in every quant here:

key	original	patched
`qwen35.block_count`	65	64
`qwen35.nextn_predict_layers`	1	0

Both are UINT32, so this is a same-width byte write with no offset changes — the tensor data is untouched.

Consequence: MTP speculative decoding is not available. If you were getting "draft tokens accepted" percentages from the original, you will not here.

A note on `Q5_1`

Worth checking on any GGUF before you trust it: if a quant contains Q5_1 tensors in the MoE/expert path, llama.cpp may fall back to CPU for those matmuls and the model will load almost entirely into system RAM despite ample free VRAM — silently, with no error. Symptoms are ~100% reported GPU utilisation at very low power draw.

You can check the tensor-type histogram from the GGUF header alone, without downloading the whole file, using an HTTP range request for the first few MB.

These quants are clean:

Q4_K 485, F32 353, Q5_K 12, Q6_K 1

Suggested settings

Context 98304 with Q4_0 K/V cache fits comfortably on 24 GB at Q4_K_S.
This is a thinking model. Short max_tokens will be consumed entirely by the reasoning channel and you will get empty content. Either allow 600+ tokens, or disable thinking: chat_template_kwargs: {"enable_thinking": false}

License

Apache 2.0, inherited. Derivative work.

Downloads last month: 608

GGUF

Model size

27B params

Architecture

qwen35

Hardware compatibility

4-bit

5-bit

Model tree for Assiduous42/Qwen3.6-27B-Fable-Fusion-711-Heretic2-GGUF

Base model

Qwen/Qwen3.6-27B

Finetuned

DavidAU/Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-MTP

Finetuned

Assiduous42/Qwen3.6-27B-Fable-Fusion-711-Heretic2

Quantized

(1)

this model

Qwen3.6-27B-Fable-Fusion-711-Heretic2 — GGUF

Files

Measured on a single RTX 4090 (24 GB)

⚠️ Patched metadata — read this if you compare against the original

A note on Q5_1

Suggested settings

License

Model tree for Assiduous42/Qwen3.6-27B-Fable-Fusion-711-Heretic2-GGUF

A note on `Q5_1`