Instructions to use Brian6145/Qwen3.6-27B-Claude-Opus-Sonnet-DistilledV2-MTP-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Brian6145/Qwen3.6-27B-Claude-Opus-Sonnet-DistilledV2-MTP-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Brian6145/Qwen3.6-27B-Claude-Opus-Sonnet-DistilledV2-MTP-GGUF",
	filename="Qwen3.6-27B-Claude-Opus-Sonnet-DistilledV2-MTP-Q2_K.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use Brian6145/Qwen3.6-27B-Claude-Opus-Sonnet-DistilledV2-MTP-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Brian6145/Qwen3.6-27B-Claude-Opus-Sonnet-DistilledV2-MTP-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf Brian6145/Qwen3.6-27B-Claude-Opus-Sonnet-DistilledV2-MTP-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Brian6145/Qwen3.6-27B-Claude-Opus-Sonnet-DistilledV2-MTP-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf Brian6145/Qwen3.6-27B-Claude-Opus-Sonnet-DistilledV2-MTP-GGUF:Q4_K_M

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 Brian6145/Qwen3.6-27B-Claude-Opus-Sonnet-DistilledV2-MTP-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf Brian6145/Qwen3.6-27B-Claude-Opus-Sonnet-DistilledV2-MTP-GGUF:Q4_K_M

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 Brian6145/Qwen3.6-27B-Claude-Opus-Sonnet-DistilledV2-MTP-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Brian6145/Qwen3.6-27B-Claude-Opus-Sonnet-DistilledV2-MTP-GGUF:Q4_K_M

Use Docker

docker model run hf.co/Brian6145/Qwen3.6-27B-Claude-Opus-Sonnet-DistilledV2-MTP-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use Brian6145/Qwen3.6-27B-Claude-Opus-Sonnet-DistilledV2-MTP-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Brian6145/Qwen3.6-27B-Claude-Opus-Sonnet-DistilledV2-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": "Brian6145/Qwen3.6-27B-Claude-Opus-Sonnet-DistilledV2-MTP-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Brian6145/Qwen3.6-27B-Claude-Opus-Sonnet-DistilledV2-MTP-GGUF:Q4_K_M

Ollama
How to use Brian6145/Qwen3.6-27B-Claude-Opus-Sonnet-DistilledV2-MTP-GGUF with Ollama:
```
ollama run hf.co/Brian6145/Qwen3.6-27B-Claude-Opus-Sonnet-DistilledV2-MTP-GGUF:Q4_K_M
```

Unsloth Studio

How to use Brian6145/Qwen3.6-27B-Claude-Opus-Sonnet-DistilledV2-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 Brian6145/Qwen3.6-27B-Claude-Opus-Sonnet-DistilledV2-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 Brian6145/Qwen3.6-27B-Claude-Opus-Sonnet-DistilledV2-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 Brian6145/Qwen3.6-27B-Claude-Opus-Sonnet-DistilledV2-MTP-GGUF to start chatting

How to use Brian6145/Qwen3.6-27B-Claude-Opus-Sonnet-DistilledV2-MTP-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf Brian6145/Qwen3.6-27B-Claude-Opus-Sonnet-DistilledV2-MTP-GGUF:Q4_K_M

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": "Brian6145/Qwen3.6-27B-Claude-Opus-Sonnet-DistilledV2-MTP-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use Brian6145/Qwen3.6-27B-Claude-Opus-Sonnet-DistilledV2-MTP-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf Brian6145/Qwen3.6-27B-Claude-Opus-Sonnet-DistilledV2-MTP-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 Brian6145/Qwen3.6-27B-Claude-Opus-Sonnet-DistilledV2-MTP-GGUF:Q4_K_M

Run Hermes

hermes

Docker Model Runner
How to use Brian6145/Qwen3.6-27B-Claude-Opus-Sonnet-DistilledV2-MTP-GGUF with Docker Model Runner:
```
docker model run hf.co/Brian6145/Qwen3.6-27B-Claude-Opus-Sonnet-DistilledV2-MTP-GGUF:Q4_K_M
```

Lemonade

How to use Brian6145/Qwen3.6-27B-Claude-Opus-Sonnet-DistilledV2-MTP-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Brian6145/Qwen3.6-27B-Claude-Opus-Sonnet-DistilledV2-MTP-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Qwen3.6-27B-Claude-Opus-Sonnet-DistilledV2-MTP-GGUF-Q4_K_M

List all available models

lemonade list

Qwen3.6-27B-Claude-Opus-Sonnet-DistilledV2-MTP-GGUF

GGUF quantized release of the Claude Opus / Sonnet reasoning distillation on Qwen3.6-27B, with native MTP speculative decoding support in llama.cpp.

Key numbers: Q4_K_M + MTP2 → 114.78 tok/s generation, 80.33% draft acceptance, 64% faster than non-MTP baseline. On the same machine, this release delivers 2x the visible answer content vs the original qwen3.6-27b while maintaining 4/4 correctness.

Quick Download

File	Size	Best for
Q4_K_M (recommended)	15.66 GB	Best overall balance
Q6_K	20.89 GB	Quality-first
Q2_K	10.12 GB	Extreme compression
Q8_0	27.05 GB	High-fidelity experiments

Compared to Original qwen3.6-27b

Same-machine benchmark against the original (non-quantized) qwen3.6-27b:

GGUF side includes llama-cli cold start — this is a conservative estimate.

	Original	This release
Average response time	10.93s	10.09s
Correctness (4 prompts)	3/4	4/4
Visible answer chars	1336	2845
Hidden reasoning overhead	9002 chars	minimal

The original spends a large fraction of its token budget on hidden reasoning chains. This release converts that budget into visible answers, making it better suited for interactive local use.

Compatibility

Requires a recent llama.cpp build with Qwen3.5/3.6 MTP support. Older conversion pipelines may miss the required metadata and fail with failed to create MTP context.

Verified stack:

Windows CUDA build of llama.cpp
GPU: NVIDIA RTX PRO 6000 Blackwell 96 GB
-ngl 999 --spec-type draft-mtp --spec-draft-n-max 2 --spec-draft-ngl 999
LM Studio 0.4.14+ opens MTP by default, zero configuration

Benchmarks

Quantization Comparison (short context)

Test: three-person logic puzzle, n=160, GPU + MTP2.

Variant	Prompt tok/s	Generation tok/s	Draft acceptance
Q2_K + MTP2	439.73	118.01	68.66%
Q4_K_M + MTP2	240.55	114.78	80.33%
Q6_K + MTP2	503.87	99.85	78.86%
Q8_0 + MTP2	421.04	78.86	69.17%

MTP vs non-MTP baseline (Q4_K_M):

Variant	Prompt tok/s	Generation tok/s
Non-MTP	796.22	69.98
MTP2	240.55	114.78
MTP3	390.77	117.16

MTP2 offers the best acceptance/throughput tradeoff. MTP3 acceptance drops to 69.48%.

Long Context

Prompt lengths ~6.6K (ctx8k) and ~26.7K (ctx32k). Generation is intentionally short (17-23 tokens) to isolate prompt processing.

Context	Variant	Prompt tok/s	Generation tok/s	Draft acceptance
ctx8k	Q2_K	1304.11	104.41	83.33%
ctx8k	Q4_K_M	2798.63	31.73	60.00%
ctx8k	Q6_K	2415.74	69.48	60.00%
ctx8k	Q8_0	2143.06	63.78	60.00%
ctx32k	Q2_K	2450.46	71.41	78.57%
ctx32k	Q4_K_M	2846.65	87.42	83.33%
ctx32k	Q6_K	2620.59	81.02	71.43%
ctx32k	Q8_0	3120.27	71.19	71.43%

Q4_K_M is the most balanced variant across both short and long contexts. Q6_K is a solid quality-first choice.

Note: BF16 + MTP2 (historical reference) yielded 20.49 tok/s prompt / 0.85 tok/s generation on this GPU — quantization is required for practical throughput on this hardware.

Usage

LM Studio (zero config)

Upgrade to LM Studio 0.4.14 or later. Load the GGUF file and MTP speculative decoding is enabled automatically — no settings, no flags, no configuration needed.

llama-cli

# Regular inference
./llama-cli -m Qwen3.6-27B-Claude-Opus-Sonnet-DistilledV2-MTP-Q4_K_M.gguf -ngl 999 -c 8192 -p "Your prompt here"

# With MTP enabled
./llama-cli -m Qwen3.6-27B-Claude-Opus-Sonnet-DistilledV2-MTP-Q4_K_M.gguf -ngl 999 -c 8192 \
  --spec-type draft-mtp --spec-draft-n-max 2 --spec-draft-ngl 999 -p "Your prompt here"

Recommended args:

Short replies: -c 4096 --temp 0 --top-k 1 --spec-draft-n-max 2
Long reasoning: -c 8192 --temp 0 --top-k 1 --spec-draft-n-max 2

Quality Validation

All four quantized variants passed:

GGUF header integrity check
GPU draft-mtp loadability
Same-prompt logic consistency (all converge to the same answer: A=lying, B=truth, C=lying)

Variant	Quality verdict	Recommendation
Q2_K	Usable, most aggressive compression	Extreme compression only
Q4_K_M	Best balance	Default
Q6_K	More stable quality	Quality-first choice
Q8_0	Fine, but not always faster than Q6_K	High-fidelity experiments

Note: Windows PowerShell CLI may corrupt Chinese prompt arguments. Use UTF-8 prompt files, API calls, or your own inference service for Chinese workloads.

Known Limitations

Requires a recent llama.cpp build (older exports may miss Qwen3.5/3.6 MTP metadata)
Q8_0 is not guaranteed to be faster than Q6_K on bandwidth-limited GPUs
Chinese prompts may need extra encoding care in Windows CLI environments

V1 → V2

V2 optimizes distillation targets, reasoning chain compression, and MTP deployment compatibility. Coding accuracy, tool calling stability, and debugging efficiency are all meaningfully improved.

Downloads last month: 8,952

GGUF

Model size

27B params

Architecture

qwen35

Hardware compatibility

2-bit

4-bit

6-bit

8-bit

Model tree for Brian6145/Qwen3.6-27B-Claude-Opus-Sonnet-DistilledV2-MTP-GGUF

Base model

Qwen/Qwen3.6-27B

Quantized

(436)

this model