Instructions to use maczzinatui/Qwen3.6-27B-MTP-TQ3_4S-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use maczzinatui/Qwen3.6-27B-MTP-TQ3_4S-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="maczzinatui/Qwen3.6-27B-MTP-TQ3_4S-GGUF",
	filename="Qwen3.6-27B-MTP-TQ3_4S.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use maczzinatui/Qwen3.6-27B-MTP-TQ3_4S-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 maczzinatui/Qwen3.6-27B-MTP-TQ3_4S-GGUF
# Run inference directly in the terminal:
llama cli -hf maczzinatui/Qwen3.6-27B-MTP-TQ3_4S-GGUF

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf maczzinatui/Qwen3.6-27B-MTP-TQ3_4S-GGUF
# Run inference directly in the terminal:
llama cli -hf maczzinatui/Qwen3.6-27B-MTP-TQ3_4S-GGUF

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 maczzinatui/Qwen3.6-27B-MTP-TQ3_4S-GGUF
# Run inference directly in the terminal:
./llama-cli -hf maczzinatui/Qwen3.6-27B-MTP-TQ3_4S-GGUF

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 maczzinatui/Qwen3.6-27B-MTP-TQ3_4S-GGUF
# Run inference directly in the terminal:
./build/bin/llama-cli -hf maczzinatui/Qwen3.6-27B-MTP-TQ3_4S-GGUF

Use Docker

docker model run hf.co/maczzinatui/Qwen3.6-27B-MTP-TQ3_4S-GGUF

LM Studio
Jan
Ollama
How to use maczzinatui/Qwen3.6-27B-MTP-TQ3_4S-GGUF with Ollama:
```
ollama run hf.co/maczzinatui/Qwen3.6-27B-MTP-TQ3_4S-GGUF
```

Unsloth Studio

How to use maczzinatui/Qwen3.6-27B-MTP-TQ3_4S-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 maczzinatui/Qwen3.6-27B-MTP-TQ3_4S-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 maczzinatui/Qwen3.6-27B-MTP-TQ3_4S-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for maczzinatui/Qwen3.6-27B-MTP-TQ3_4S-GGUF to start chatting

How to use maczzinatui/Qwen3.6-27B-MTP-TQ3_4S-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf maczzinatui/Qwen3.6-27B-MTP-TQ3_4S-GGUF

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": "maczzinatui/Qwen3.6-27B-MTP-TQ3_4S-GGUF"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use maczzinatui/Qwen3.6-27B-MTP-TQ3_4S-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 maczzinatui/Qwen3.6-27B-MTP-TQ3_4S-GGUF

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 maczzinatui/Qwen3.6-27B-MTP-TQ3_4S-GGUF

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use maczzinatui/Qwen3.6-27B-MTP-TQ3_4S-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf maczzinatui/Qwen3.6-27B-MTP-TQ3_4S-GGUF

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 "maczzinatui/Qwen3.6-27B-MTP-TQ3_4S-GGUF" \
  --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 maczzinatui/Qwen3.6-27B-MTP-TQ3_4S-GGUF with Docker Model Runner:
```
docker model run hf.co/maczzinatui/Qwen3.6-27B-MTP-TQ3_4S-GGUF
```

Lemonade

How to use maczzinatui/Qwen3.6-27B-MTP-TQ3_4S-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull maczzinatui/Qwen3.6-27B-MTP-TQ3_4S-GGUF

Run and chat with the model

lemonade run user.Qwen3.6-27B-MTP-TQ3_4S-GGUF-{{QUANT_TAG}}

List all available models

lemonade list

Qwen3.6-27B-MTP TQ3_4S — GGUF

TQ3_4S quant of Qwen/Qwen3.6-27B (Apache 2.0), produced via turbo-tan's llama.cpp-tq3 CUDA fork. Benchmarked on a Blackwell RTX 5060 Ti (16 GB). Mean AEON score: 0.525 (120 scored / 150 cases, 2048 budget).

File

File	Size	Quant	BPW
`Qwen3.6-27B-MTP-TQ3_4S.gguf`	14.2 GB	TQ3_4S (turbo-tan)	~3.8 bpw

NOT a stock llama.cpp quant

TQ3_4S (TurboQuant 3-bit 4-state) is a custom weight format unique to turbo-tan/llama.cpp-tq3. Stock llama.cpp and nixpkgs llama-cpp will exit with unknown quantization at load time. Use the llama-server/llama-cli from the tq3 fork.

Scope of these benchmarks — read this first

These numbers are a light baseline, not a thorough TQ3 evaluation. The mesh's bench framework is built for production agent workload regression-detection on the local stack, not for the kind of multi-axis sweep that upstream quant maintainers typically publish. Specifically:

Harness scope is bounded. The numbers below come from the mesh's Aeon-Bench-Pod (self-reported mode, 150-case full suite, text-only, no agentic harness). That's a regression suite, not a quality benchmark.
Sample sizes are small. 150 cases on a single GPU, single rep. None are powered for statistical significance.
No perplexity / wikitext / MMLU / GSM8K. The mesh's stack isn't a quality benchmark — those are upstream's territory.
Single GPU class (Blackwell 16 GB). All measurements are on an NVIDIA RTX 5060 Ti 16 GB (CUDA 13.2, turbo-tan/llama.cpp-tq3). No RDNA4, no multi-GPU, no Vulkan. Cross-hardware generalization is NOT implied.
No human eval. "0.525 mean on the AEON suite" is not a quality verdict on this specific quant.
30 prose cases unscored — no frontier judge endpoint configured, so the prose category (30/150 cases) is excluded from the mean.

What this IS good for: a quick signal that the quant (a) loads, (b) runs at sane throughput, (c) produces coherent output across math, instruction, reasoning, and coding. What this is NOT good for: claiming "this is the best quant of this model," reproducing academic benchmark results, or substituting for upstream's validation work.

For a rigorous view, see Qwen/Qwen3.6-27B (parent model) and turbo-tan/llama.cpp-tq3 (quantizer). Raw bench reports are attached as BENCH-*.md files in this repo.

What we measured

AEON v3 — 150 cases (120 scored)

Benchmarked on Blackwell RTX 5060 Ti 16 GB, full suite.

Category	Mean	N
Overall	0.525	120
coding	0.933	30
math	0.467	30
reasoning	0.367	30
instruction	0.333	30

Difficulty	Mean	N
easy	1.000	8
medium	0.833	12
hard	0.700	20
expert	0.500	32
frontier	0.312	48

Profile: Strong on coding (0.933), weak on instruction-following (0.333) and reasoning (0.367). Typical Qwen3.6-TQ3 profile — excels at structured code tasks, struggles on instruction-heavy and frontier-difficulty cases.

Companion: ROCmFP4_FAST (RDNA4)

The companion ROCmFP4_FAST quant for AMD RDNA4 scores 0.558 on the same suite. Cross-format parity is within ~3pp on most categories; the AMD arm benefits from a higher coding score but the overall profile is similar.

Quick start

# Build turbo-tan's tq3 fork
git clone https://github.com/turbo-tan/llama.cpp-tq3
cd llama.cpp-tq3
mkdir build && cd build
cmake .. -DGGML_CUDA=ON -DCUDA_DOCKER_ARCH=sm_120
make -j$(nproc)

# Serve with production-equivalent flags
llama-server \
  -m Qwen3.6-27B-MTP-TQ3_4S.gguf \
  --host 0.0.0.0 --port 8081 \
  -ngl 99 -c 131072 -t 12 \
  -ctk q4_0 -ctv q4_0 \
  -np 1 --batch-size 512 --ubatch-size 128 \
  --jinja --metrics -rea off

Reproduce the quant

# Requires the tq3 fork and the BF16 source GGUF
llama-quantize --allow-requantize Qwen3.6-27B-BF16.gguf \
  Qwen3.6-27B-MTP-TQ3_4S.gguf TQ3_4S

Files in this repo

File	Description
`Qwen3.6-27B-MTP-TQ3_4S.gguf`	The quantized model (LFS-tracked)
`README.md`	This model card
`BENCH-aeon-full-suite.md`	AEON bench results (150 cases, 120 scored)

What's NOT in this repo (caveats)

Stock llama.cpp will not load this file. TQ3_4S is a custom weight format unique to turbo-tan/llama.cpp-tq3.
No AMD GPU bench. All measurements are RTX 5060 Ti (CUDA). The companion ROCmFP4_FAST quant for RDNA4 is in a separate repo.
No quality benchmark (perplexity, MMLU, GSM8K). The custom 3-bit quant works on the mesh's regression tests; whether it's "the best TQ3 quant" needs upstream validation.
No MTP / speculative-decode bench. MTP heads are present in the source model but were not benched on this quant.

Provenance

Source model: Qwen/Qwen3.6-27B — Apache 2.0
Quantizer: turbo-tan/llama.cpp-tq3
Quantizer license: MIT
Build hardware: NVIDIA RTX 5060 Ti 16 GB (Blackwell), CUDA 13.2, NixOS 25.11
Bench harness: Aeon-Bench-Pod v1 (self-reported mode)

License

Qwen/Qwen3.6-27B is Apache 2.0.
turbo-tan/llama.cpp-tq3 is MIT.
The GGUF in this repo is a derivative of the Apache 2.0-licensed parent, produced with the MIT-licensed quantizer. The Apache 2.0 license is preserved.