Instructions to use Gorilla4X/Quacken-27B-NVFP4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Gorilla4X/Quacken-27B-NVFP4 with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Gorilla4X/Quacken-27B-NVFP4",
	filename="Qwen3.6-27B-NVFP4-FP8.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 Gorilla4X/Quacken-27B-NVFP4 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 Gorilla4X/Quacken-27B-NVFP4:NVFP4
# Run inference directly in the terminal:
llama cli -hf Gorilla4X/Quacken-27B-NVFP4:NVFP4

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Gorilla4X/Quacken-27B-NVFP4:NVFP4
# Run inference directly in the terminal:
llama cli -hf Gorilla4X/Quacken-27B-NVFP4: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 Gorilla4X/Quacken-27B-NVFP4:NVFP4
# Run inference directly in the terminal:
./llama-cli -hf Gorilla4X/Quacken-27B-NVFP4: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 Gorilla4X/Quacken-27B-NVFP4:NVFP4
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Gorilla4X/Quacken-27B-NVFP4:NVFP4

Use Docker

docker model run hf.co/Gorilla4X/Quacken-27B-NVFP4:NVFP4

LM Studio
Jan

vLLM

How to use Gorilla4X/Quacken-27B-NVFP4 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Gorilla4X/Quacken-27B-NVFP4"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Gorilla4X/Quacken-27B-NVFP4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Gorilla4X/Quacken-27B-NVFP4:NVFP4

Ollama
How to use Gorilla4X/Quacken-27B-NVFP4 with Ollama:
```
ollama run hf.co/Gorilla4X/Quacken-27B-NVFP4:NVFP4
```

Unsloth Studio

How to use Gorilla4X/Quacken-27B-NVFP4 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 Gorilla4X/Quacken-27B-NVFP4 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 Gorilla4X/Quacken-27B-NVFP4 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Gorilla4X/Quacken-27B-NVFP4 to start chatting

How to use Gorilla4X/Quacken-27B-NVFP4 with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Gorilla4X/Quacken-27B-NVFP4: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": "Gorilla4X/Quacken-27B-NVFP4:NVFP4"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use Gorilla4X/Quacken-27B-NVFP4 with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Gorilla4X/Quacken-27B-NVFP4: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 Gorilla4X/Quacken-27B-NVFP4:NVFP4

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use Gorilla4X/Quacken-27B-NVFP4 with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Gorilla4X/Quacken-27B-NVFP4: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 "Gorilla4X/Quacken-27B-NVFP4: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"

Docker Model Runner
How to use Gorilla4X/Quacken-27B-NVFP4 with Docker Model Runner:
```
docker model run hf.co/Gorilla4X/Quacken-27B-NVFP4:NVFP4
```

Lemonade

How to use Gorilla4X/Quacken-27B-NVFP4 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Gorilla4X/Quacken-27B-NVFP4:NVFP4

Run and chat with the model

lemonade run user.Quacken-27B-NVFP4-NVFP4

List all available models

lemonade list

Quacken-27B-NVFP4 (mixed FP4 + FP8) 🦆

The Rock8 — Got any weights? 💪

A mixed-precision GGUF of Qwen3.6-27B for AMD RDNA4 (gfx1201 — Radeon AI PRO R9700 / RX 9070 / 9070 XT / W-series): NVFP4 (4-bit) MLPs + native FP8 (E4M3) attention/lm_head. Ingested from unsloth/Qwen3.6-27B-NVFP4 with The Rock8's mixed-precision compressed-tensors converter, then run on RDNA4 via native fp8 WMMA + the NVFP4 int8/dp4a path.

Why it's interesting — smaller, more accurate, faster decode than fp8

Benched on one R9700 (gfx1201), vs our own native-fp8 build of the same base:

Metric	This (NVFP4 + FP8)	Quacken-27B FP8
Size	23.2 GB → fits one 32 GB card	~29 GB (needs 2 GPUs)
Perplexity (wikitext, 20×512)	6.88	7.14
Decode `tg128`	24.0 t/s (+30%)	18.5 t/s
Prefill `pp512`	1069 t/s	1251 t/s
Coherence ("dried grape" → raisin)	✅	✅

Single-card — the FP4 MLPs shrink it to 23 GB, so it runs on one R9700 (the fp8 build needs two).
Better accuracy — PPL 6.88 beats the fp8 build's 7.14.
+30% decode — FP4 MLPs move far less data in the memory-bound decode phase.
Honest tradeoff: prefill ~15% slower than pure fp8. RDNA4 has no native FP4 matmul (that's CDNA4/MI350), so the NVFP4 tensors run the int8/dp4a fallback — the win here is memory & decode bandwidth, not FP4 tensor-core acceleration. Best for interactive / decode-heavy use.

What's inside (verified tensor histogram)

168 NVFP4 tensors (8.4 GB) — mlp.{gate,up,down}_proj, layers 0–55 (E2M1, group-16, E4M3 scale)
233 F8E4M3 tensors (11.3 GB) — attention q/k/v/o, linear-attn proj, lm_head, layers 56–63 MLP
F16 remainder (3.4 GB) — SSM/conv1d/norms + vision encoder + MTP head (intentionally unquantized)

This is the faithful mixed quant — the FP8 group is preserved as native F8E4M3, not dequantized to BF16.

Run it (The Rock8 fork, single GPU)

llama-cli   -m Qwen3.6-27B-NVFP4-FP8.gguf -ngl 999 -p "What do you call a dried grape? Answer in one word."
llama-bench -m Qwen3.6-27B-NVFP4-FP8.gguf -ngl 999 -p 512 -n 128

Source & license

Base model Qwen/Qwen3.6-27B (Apache-2.0). NVFP4 quantization by Unsloth; this repo re-packages that checkpoint as a faithful mixed FP4/FP8 GGUF for RDNA4. Apache-2.0.