Instructions to use zerodigest/Qwen3.6-27B-YMQ-MTP-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 zerodigest/Qwen3.6-27B-YMQ-MTP-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 zerodigest/Qwen3.6-27B-YMQ-MTP-GGUF
# Run inference directly in the terminal:
llama cli -hf zerodigest/Qwen3.6-27B-YMQ-MTP-GGUF

Install from WinGet (Windows)

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

Use Docker

docker model run hf.co/zerodigest/Qwen3.6-27B-YMQ-MTP-GGUF

LM Studio
Jan

vLLM

How to use zerodigest/Qwen3.6-27B-YMQ-MTP-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "zerodigest/Qwen3.6-27B-YMQ-MTP-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": "zerodigest/Qwen3.6-27B-YMQ-MTP-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/zerodigest/Qwen3.6-27B-YMQ-MTP-GGUF

Ollama
How to use zerodigest/Qwen3.6-27B-YMQ-MTP-GGUF with Ollama:
```
ollama run hf.co/zerodigest/Qwen3.6-27B-YMQ-MTP-GGUF
```

Unsloth Studio

How to use zerodigest/Qwen3.6-27B-YMQ-MTP-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 zerodigest/Qwen3.6-27B-YMQ-MTP-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 zerodigest/Qwen3.6-27B-YMQ-MTP-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

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

How to use zerodigest/Qwen3.6-27B-YMQ-MTP-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf zerodigest/Qwen3.6-27B-YMQ-MTP-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": "zerodigest/Qwen3.6-27B-YMQ-MTP-GGUF"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use zerodigest/Qwen3.6-27B-YMQ-MTP-GGUF with Docker Model Runner:
```
docker model run hf.co/zerodigest/Qwen3.6-27B-YMQ-MTP-GGUF
```

Lemonade

How to use zerodigest/Qwen3.6-27B-YMQ-MTP-GGUF with Lemonade:

Pull the model

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

Run and chat with the model

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

List all available models

lemonade list

Hermes Agent

How to use zerodigest/Qwen3.6-27B-YMQ-MTP-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 zerodigest/Qwen3.6-27B-YMQ-MTP-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 zerodigest/Qwen3.6-27B-YMQ-MTP-GGUF

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use zerodigest/Qwen3.6-27B-YMQ-MTP-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf zerodigest/Qwen3.6-27B-YMQ-MTP-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 "zerodigest/Qwen3.6-27B-YMQ-MTP-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"

Qwen3.6-27B-YMQ-MTP-GGUF

Source Model: Qwen/Qwen3.6-27B

⚖️ An Architecture-Aware, AutoRound-Inspired Mixed Precision Layout

This repository features advanced, custom architecture-aware quantizations of Qwen3.6-27B processed directly from official raw BF16 source files using the custom YMQ-Compiler (v2.0) log-space framework.

These builds natively support parallel multi-token prediction (MTP) speculation engines and utilize high-context optimization parameters tailored for demanding code development API execution environments (such as RooCode/Aider).

📊 Quantization Preset Tier Details

Preset Tier	Total Size	Target Usage / Memory VRAM Profile	Cognitive Real-World Coding Quality
`XXS`	~9.8 GB	Absolute VRAM Squeeze / 12GB Card Lifeline	Massive structural quantization noise. Best restricted to low-context, single-turn instructions. Fits 12GB cards with context cache breathing room.
`XS`	~11.0 GB	Max budget squeeze / For the desperate	High compression noise floor. Works for short scripts, prone to api calling degradation past 50k context size.
`S`	~12.2 GB	Light workspace / Low-VRAM cache headroom	Balanced economy. Great text parsing consistency, minor context layout fatigue on long coding passes.
`M`	~14.0 GB	The Ultimate Coding Sweet Spot (Recommended)	Elite logical stability. Complete logic clarity. It crushes standard industry 4-bit alternatives.
`L`	~17.0 GB	Premium Single-GPU Processing / Heavy workloads	Near-lossless instruction formatting. Pristine multi-turn architecture safety.
`XL`	~19.0 GB	Maximum VRAM Fill / No Compromises	Mathematical saturation ceiling. Full precision logic tracks for massive multi-file codebase operations.

📉 Perplexity Evaluation Metrics (WikiText-2)

The following scores demonstrate the mathematical quality preservation of the YMQ-Compiler log-space cluster analysis compared to standard linear quantization layouts. Tested natively via llama-perplexity at a 4096 context window.

Model Preset Variant	File Size	Perplexity Score	Cognitive Calibration Verdict
`XXS`	9.8G	8.2515	Extreme VRAM economy boundary cliff.
`XS`	11G	7.6273	Isolated task profile fallback
`S`	12G	8.4656	Maximum budget compression cliff
`M` (Recommended)	14G	7.5295	🎯 The Ultimate Golden Target Balance
`L`	17G	8.0920	Mild network accumulation noise
`XL`	19G	7.9757	Diminishing returns / Structural bloat

💡 The Performance Breakthrough Explained

Notice how the M preset achieves a significantly lower perplexity score (lower is better) than the heavier L and XL files while being up to 5 Gigabytes smaller. This occurs because the YMQ-Compiler surgically protects the high-leverage 71k imatrix cognitive reasoning spikes with Q5_K and Q6_K shields, while aggressively compressing idle fact-storage tensors.

⚖️ YMQ vs. Uniform Quantization (The AutoRound Philosophy)

Standard quantization pipelines apply a blunt, uniform bit-depth across every single layer in a model. This wastes valuable VRAM on silent background layers while starving critical logic anchors of necessary precision.

The YMQ-Compiler implements a philosophy similar to advanced weight-tuning frameworks like Intel's AutoRound:

Targeted Bit Allocation: It strips bits away from low-leverage background tensors and automatically re-allocates that saved VRAM budget straight into full high-fidelity shields for the model's highest cognitive spikes and boundary pathways.
Instant Optimization: Instead of running heavy, days-long optimization training loops, YMQ achieves a highly accurate mixed-precision layout instantly by analyzing layer importance metrics in log-space.

The result is a custom mixed-precision portfolio that matches the low perplexity and high context stability of premium optimized quants (like AutoRound), while maintaining an ultra-lightweight, high-speed single-GPU cache footprint.

🛠️ The YMQ Compilation Architecture

Standard quantization pipelines treat network tensors like a flat dataset, applying destructive blanket low-bit compression to delicate tracking networks. The YMQ-Compiler solves high-context logic decay by parsing model files dynamically via an automated, multi-tiered protection matrix:

Log-Space Gap Detection Clustering: Instead of flat percentage thresholds, the engine computes statistical cluster variances in log-space, successfully isolating intermediate logical reasoning spikes and elevating them to stable non-linear 4-bit (IQ4_XS) formats, while compressing idle fact-storage layers to aggressive 2-bit baselines.
Fading Boundary Tapering: Recognizes the extreme fragility of initial token entry data vectors, forcing an input wave cushion (L00=IQ4_NL → L01=IQ4_XS → L02=IQ3_XXS) that gradually stabilizes parameters before hitting the fallback pools.
Dedicated Gate Insulation: Hard-shields volatile parallel Transformer Multi-Head Attention and Mamba Linear State Space Model (SSM) routing paths, keeping context tracking perfectly noise-free.
Asymmetric Vocabulary Shielding: Fixes tied-weight boundary errors by mapping the final logit classification exit heads to robust configurations to completely eliminate formatting loops and API tag leakage under deep contexts.
Native Next-N Speculative Stripping: Processed with advanced pre-tokenizer stripping to ensure zero index offset drift or layer-shifting risks across hybrid configurations.

🚀 Recommended Runtime Parameters (llama.cpp / llama-server)

$./llama-server -m models/Qwen3.6-27B-YMQ-M-MTP.gguf -ctk q8_0 -ctv q4_0 --ctx-size 245760 --mmproj proj/Qwen3.6-27B-Q8.mmproj \
  --spec-type draft-mtp --spec-draft-n-max 2 --timeout 36000 --checkpoint-min-step 2048 --ctx-checkpoints 4 \
  --n-predict -1 --temp 0.6 --top-p 0.95 --top-k 20 --repeat-penalty 1.05 --jinja -fa

☕ Support & Future R&D

If the YMQ-Compiler builds saved your context window from collapsing or optimized your active development cycle speeds, consider buying a coffee to fund further low-level optimization research. Your support keeps the server nodes baking future model scales!

👉 Support ZeroDigest Research on ko-fi

📦 Source Framework & Automation Code

The compiler pipeline automation engine, setup thresholds, and structural mapping rules are open-source. To view the implementation details or compile your own custom models natively using this profile layout, visit the official development hub:

👉 GitHub: ZeroDigest / YMQ-Compiler

Downloads last month: 4,964

GGUF

Model size

27B params

Architecture

qwen35

Hardware compatibility

We're not able to determine the quantization variants.

View all variants

Model tree for zerodigest/Qwen3.6-27B-YMQ-MTP-GGUF

Base model

Qwen/Qwen3.6-27B

Quantized

(708)

this model