Instructions to use michaelw9999/Qwen3.6-27B-NVFP4-MXFP6-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 michaelw9999/Qwen3.6-27B-NVFP4-MXFP6-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 michaelw9999/Qwen3.6-27B-NVFP4-MXFP6-MTP-GGUF:NVFP4
# Run inference directly in the terminal:
llama cli -hf michaelw9999/Qwen3.6-27B-NVFP4-MXFP6-MTP-GGUF:NVFP4

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf michaelw9999/Qwen3.6-27B-NVFP4-MXFP6-MTP-GGUF:NVFP4
# Run inference directly in the terminal:
llama cli -hf michaelw9999/Qwen3.6-27B-NVFP4-MXFP6-MTP-GGUF:NVFP4

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 michaelw9999/Qwen3.6-27B-NVFP4-MXFP6-MTP-GGUF:NVFP4
# Run inference directly in the terminal:
./llama-cli -hf michaelw9999/Qwen3.6-27B-NVFP4-MXFP6-MTP-GGUF:NVFP4

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 michaelw9999/Qwen3.6-27B-NVFP4-MXFP6-MTP-GGUF:NVFP4
# Run inference directly in the terminal:
./build/bin/llama-cli -hf michaelw9999/Qwen3.6-27B-NVFP4-MXFP6-MTP-GGUF:NVFP4

Use Docker

docker model run hf.co/michaelw9999/Qwen3.6-27B-NVFP4-MXFP6-MTP-GGUF:NVFP4

LM Studio
Jan
Ollama
How to use michaelw9999/Qwen3.6-27B-NVFP4-MXFP6-MTP-GGUF with Ollama:
```
ollama run hf.co/michaelw9999/Qwen3.6-27B-NVFP4-MXFP6-MTP-GGUF:NVFP4
```

Unsloth Studio

How to use michaelw9999/Qwen3.6-27B-NVFP4-MXFP6-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 michaelw9999/Qwen3.6-27B-NVFP4-MXFP6-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 michaelw9999/Qwen3.6-27B-NVFP4-MXFP6-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 michaelw9999/Qwen3.6-27B-NVFP4-MXFP6-MTP-GGUF to start chatting

How to use michaelw9999/Qwen3.6-27B-NVFP4-MXFP6-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 michaelw9999/Qwen3.6-27B-NVFP4-MXFP6-MTP-GGUF:NVFP4

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": "michaelw9999/Qwen3.6-27B-NVFP4-MXFP6-MTP-GGUF:NVFP4"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use michaelw9999/Qwen3.6-27B-NVFP4-MXFP6-MTP-GGUF with Docker Model Runner:
```
docker model run hf.co/michaelw9999/Qwen3.6-27B-NVFP4-MXFP6-MTP-GGUF:NVFP4
```

Lemonade

How to use michaelw9999/Qwen3.6-27B-NVFP4-MXFP6-MTP-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull michaelw9999/Qwen3.6-27B-NVFP4-MXFP6-MTP-GGUF:NVFP4

Run and chat with the model

lemonade run user.Qwen3.6-27B-NVFP4-MXFP6-MTP-GGUF-NVFP4

List all available models

lemonade list

Hermes Agent

How to use michaelw9999/Qwen3.6-27B-NVFP4-MXFP6-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 michaelw9999/Qwen3.6-27B-NVFP4-MXFP6-MTP-GGUF:NVFP4

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 michaelw9999/Qwen3.6-27B-NVFP4-MXFP6-MTP-GGUF:NVFP4

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use michaelw9999/Qwen3.6-27B-NVFP4-MXFP6-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 michaelw9999/Qwen3.6-27B-NVFP4-MXFP6-MTP-GGUF:NVFP4

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 "michaelw9999/Qwen3.6-27B-NVFP4-MXFP6-MTP-GGUF:NVFP4" \
  --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"

Changed GGML TYPE to 50, latest mxfp6 build is required

Model Card for Model ID

This is my best model yet! It offers incredibly fast performance with incredible quality.
This is the MXFP6 enhanced version of michaelw9999/Qwen3.6-27B-NVFP4-MTP-GGUF.

It was quantized with my work-in-progress advanced-gguf-quantizer

Why add MXFP6 tensors into the NVFP4?
MXFP6 has vastly superior quality compared to NVFP4.
Only a relatively small portion of this model is MXFP6, though; it's used to boost the quality up, where needed.
Most of the model is NVFP4, some small numbers of tensors are Q4_K.
How much MXFP6 to inject to get close to BF16 in real world usage and benchmarks vs raw numbers remains TBD.
This model is almost as fast as the primary NVFP4 model, and just a tiny bit bigger, but the results are further improved: See this chart (thanks to@raulgdm) with the NVFP4/MXFP6 blend's improvement over the all original model:

Qwen3.6-27B Quantization Benchmarks
Benchmark	Samples	Q6_K (150K)	NVFP4-Q8_0 (27/05)	NVFP4 1f (29/05)	NVFP4 1f updated (30/05)	NVFP4/MXFP6 (w/ repack)
GSM8K	51	88.2%	86.3%	88.2%	88.2%	96.1%
ARC Easy	30	100%	100%	100%	100%	100%
HellaSwag	30	63.3%	66.7%	73.3%	73.3%	86.7%
PIQA	20	100%	100%	100%	100%	100%
HumanEval pass@1	164	85.4%	84.8%	86.0%	85.4%	87.2%
Average	—	87.9%	88.2%	90.4%	90.4%	94.0%
PPL ratio (WikiText-2 full KLD)	—	—	—	1.13	1.105	1.0269

PPL ratio = Mean PPL(Q)/PPL(base) = 1.026890 from the full KLD/PPL run.

For more context, see:

https://github.com/ggml-org/llama.cpp/discussions/22498 and https://github.com/ggml-org/llama.cpp/discussions/23853

You must install the unofficial MXFP6 CUDA build of llama.cpp for this model to work.

For best performance and quality, use NVFP4-Repack with MXFP6 from:
https://github.com/michaelw9999/llama.cpp/tree/nvfp4repack_mxfp6_cuda
Without NVFP4 repack:
https://github.com/michaelw9999/llama.cpp/tree/mxfp6-cuda

These branches are updated regularly.
NVFP4 repack preloads all tensors into a CUDA tile to boost speed. It is a tiny bit slower on first load, then provides ~10% prefill boost with a small reduction in token gen seen on larger models, and an increase on smaller models.
However, it also enables NVFP4 input scale, which boosts model correctness.

Model Performance on 5090 with MXFP6-CUDA branch
This model should be faster than the NVFP4-only version, as the MTP tensors are MXFP6.

| qwen35 27B NVFP4-MXFP6|  15.23 GiB |    27.32 B | CUDA       |  99 | pp512 |       5180.83 ± 2.14  |
| qwen35 27B NVFP4-MXFP6|  15.23 GiB |    27.32 B | CUDA       |  99 | tg128 |         76.56 ± 0.27

Model Performance on 5090 (with NVFP4 Repack)

| qwen35 27B NVFP4-MXFP6| 15.23 GiB | 27.32 B | CUDA | 99 | pp512 | 5675.78 ± 94.88 | | qwen35 27B NVFP4-MXFP6| 15.23 GiB | 27.32 B | CUDA | 99 | tg128 | 73.71 ± 1.24

Model Quality
Running the ppl/kld test on the standard wiki.test:
With NVFP4-Repack

====== Perplexity statistics ====== Mean PPL(Q) : 7.081974 ± 0.047190 Mean PPL(base) : 6.900856 ± 0.045374 Cor(ln(PPL(Q)), ln(PPL(base))): 98.63% Mean ln(PPL(Q)/PPL(base)) : 0.025907 ± 0.001098 Mean PPL(Q)/PPL(base) : 1.026246 ± 0.001127 Mean PPL(Q)-PPL(base) : 0.181118 ± 0.007867 ====== KL divergence statistics ====== Mean KLD: 0.054232 ± 0.000890 Maximum KLD: 25.507811 99.9% KLD: 4.043683 99.0% KLD: 0.546427 95.0% KLD: 0.152158 90.0% KLD: 0.088751 Median KLD: 0.018002 10.0% KLD: 0.000454 5.0% KLD: 0.000123 1.0% KLD: 0.000016 0.1% KLD: 0.000002 Minimum KLD: -0.000066 ====== Token probability statistics ====== Mean Δp: -0.213 ± 0.017 % Maximum Δp: 99.434% 99.9% Δp: 46.017% 99.0% Δp: 15.815% 95.0% Δp: 7.191% 90.0% Δp: 4.217% 75.0% Δp: 0.866% Median Δp: -0.002% 25.0% Δp: -0.963% 10.0% Δp: -4.442% 5.0% Δp: -7.884% 1.0% Δp: -20.542% 0.1% Δp: -61.177% Minimum Δp: -99.506% RMS Δp : 6.427 ± 0.059 % Same top p: 90.779 ± 0.075 %

Without NVFP4 Repack:

====== Perplexity statistics ====== Mean PPL(Q) : 7.088015 ± 0.047272 Mean PPL(base) : 6.900856 ± 0.045374 Cor(ln(PPL(Q)), ln(PPL(base))): 98.68% Mean ln(PPL(Q)/PPL(base)) : 0.026760 ± 0.001081 Mean PPL(Q)/PPL(base) : 1.027121 ± 0.001111 Mean PPL(Q)-PPL(base) : 0.187159 ± 0.007769 ====== KL divergence statistics ====== Mean KLD: 0.054489 ± 0.000910 Maximum KLD: 20.432301 99.9% KLD: 4.555052 99.0% KLD: 0.521524 95.0% KLD: 0.151849 90.0% KLD: 0.087985 Median KLD: 0.017979 10.0% KLD: 0.000450 5.0% KLD: 0.000121 1.0% KLD: 0.000016 0.1% KLD: 0.000002 Minimum KLD: -0.000051 ====== Token probability statistics ====== Mean Δp: -0.209 ± 0.017 % Maximum Δp: 99.650% 99.9% Δp: 46.285% 99.0% Δp: 15.675% 95.0% Δp: 7.215% 90.0% Δp: 4.196% 75.0% Δp: 0.861% Median Δp: -0.002% 25.0% Δp: -0.963% 10.0% Δp: -4.445% 5.0% Δp: -7.878% 1.0% Δp: -20.604% 0.1% Δp: -57.880% Minimum Δp: -99.882% RMS Δp : 6.386 ± 0.060 % Same top p: 90.855 ± 0.075 %

Downloads last month: 1,683

GGUF

Model size

27B params

Architecture

qwen35

Hardware compatibility

4-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for michaelw9999/Qwen3.6-27B-NVFP4-MXFP6-MTP-GGUF

Base model

Qwen/Qwen3.6-27B

Quantized

(710)

this model

Collection including michaelw9999/Qwen3.6-27B-NVFP4-MXFP6-MTP-GGUF

Experimental NVFP4/MXFP6 Mixed

Collection

1 item • Updated Jun 2 • 1