Instructions to use Gorilla4X/Quacken-27B-FP8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Gorilla4X/Quacken-27B-FP8 with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Gorilla4X/Quacken-27B-FP8",
	filename="Qwen3.6-27B-Quacken-F8E4M3.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-FP8 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-FP8
# Run inference directly in the terminal:
llama cli -hf Gorilla4X/Quacken-27B-FP8

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Gorilla4X/Quacken-27B-FP8
# Run inference directly in the terminal:
llama cli -hf Gorilla4X/Quacken-27B-FP8

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-FP8
# Run inference directly in the terminal:
./llama-cli -hf Gorilla4X/Quacken-27B-FP8

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-FP8
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Gorilla4X/Quacken-27B-FP8

Use Docker

docker model run hf.co/Gorilla4X/Quacken-27B-FP8

LM Studio
Jan

vLLM

How to use Gorilla4X/Quacken-27B-FP8 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Gorilla4X/Quacken-27B-FP8"
# 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-FP8",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Gorilla4X/Quacken-27B-FP8

Ollama
How to use Gorilla4X/Quacken-27B-FP8 with Ollama:
```
ollama run hf.co/Gorilla4X/Quacken-27B-FP8
```

Unsloth Studio

How to use Gorilla4X/Quacken-27B-FP8 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-FP8 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-FP8 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-FP8 to start chatting

How to use Gorilla4X/Quacken-27B-FP8 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-FP8

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-FP8"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use Gorilla4X/Quacken-27B-FP8 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-FP8

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-FP8

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use Gorilla4X/Quacken-27B-FP8 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-FP8

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-FP8" \
  --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-FP8 with Docker Model Runner:
```
docker model run hf.co/Gorilla4X/Quacken-27B-FP8
```

Lemonade

How to use Gorilla4X/Quacken-27B-FP8 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Gorilla4X/Quacken-27B-FP8

Run and chat with the model

lemonade run user.Quacken-27B-FP8-{{QUANT_TAG}}

List all available models

lemonade list

Quacken-27B-FP8

The Rock8 - Got any weights? 💪🦆

Native fp8 E4M3 GGUF of Qwen3.6-27B (a GatedDeltaNet hybrid) for AMD RDNA4 (gfx1201 - Radeon AI PRO R9700 / RX 9070 / 9070 XT / W-series), quantized with AMD Quark from the full-precision BF16 weights by The Rock8.

The Rock8's llama.cpp fork runs this fp8 on RDNA4's native WMMA fp8 tensor cores (prefill) and v_dot4_f32_fp8_fp8 (decode) - not a dequant-to-f16 fallback. At 27B this is a 2-GPU model (tensor-split across two 32 GB R9700s).

What it is

Format: fp8 E4M3 (F8E4M3), block-scaled, produced by AMD Quark from BF16.
Target: AMD RDNA4 / gfx1201; runs across two 32 GB cards (Radeon AI PRO R9700).
Runtime: The Rock8 (llama.cpp fork with native RDNA4 fp8 kernels) on TheRock ROCm 7.13.
File: Qwen3.6-27B-Quark-F8E4M3.gguf (29.3 GiB).

Source model + license

Source: Qwen3.6-27B (Qwen).
License: Apache-2.0 (the source repo bundles an Apache-2.0 LICENSE; redistribution of this quantized derivative is permitted with attribution). This is a derivative work.

Validation (real gfx1201 hardware)

Metric	Value
Perplexity (wikitext, 20 chunks, n_ctx=512)	7.14
Prefill `pp512` (2-GPU)	1251.6 t/s
Decode `tg128` (2-GPU)	18.52 t/s
Coherence check ("dried grape" -> "raisin")	Pass

Benched tensor-split across two R9700s (gfx1201). This is the authentic Quark build validated to load and generate coherently.

Run it

llama.cpp (The Rock8 fork) - 2-GPU

# -ngl 999 lets llama.cpp see and split across both R9700s
llama-cli   -m Qwen3.6-27B-Quark-F8E4M3.gguf -ngl 999 -p "What do you call a dried grape? Answer in one word."
llama-bench -m Qwen3.6-27B-Quark-F8E4M3.gguf -ngl 999 -p 512 -n 128

Lemonade appliance (container)

podman run -d --rm --runtime crun --name lemonade \
  --device /dev/kfd --device /dev/dri \
  --group-add keep-groups --security-opt seccomp=unconfined \
  -v /path/to/quacken-27b:/models:ro \
  -e MODEL=/models/Qwen3.6-27B-Quark-F8E4M3.gguf -e MODEL_NAME=Quacken-27B-FP8 \
  -p 13305:13305 \
  ghcr.io/the-monk/the-rock8:rdna4-tr713 serve
# note: 27B needs both GPUs - do NOT pin HIP_VISIBLE_DEVICES to a single card

Container (same image on each registry; --runtime crun is required for GPU): ghcr.io/the-monk/the-rock8:rdna4-tr713 - docker.io/gorilla4x/the-rock8:rdna4-tr713 - quay.io/the-monk/the-rock8:rdna4-tr713 (images may not be pushed to every registry yet).

Omni mode - MTP self-speculative decode (Lemonade config, 2.43x decode)

Omni is not a separate model - it's a Lemonade configuration on this same fp8 checkpoint. Qwen3.6-27B ships a built-in MTP (multi-token-prediction) head, so it can speculate against itself - no draft model, no extra VRAM. The Rock8 verifies the speculated tokens on the fp8 WMMA tensor cores. Result on gfx1201 (single-stream, greedy):

Config	Decode t/s	vs raw
Raw fp8 decode	18.67	1.00x
Omni: fp8 + MTP self-spec (draft-n=8)	45.45	2.43x

Byte-identical to greedy at n=8 (the ship setting). This is the single-GPU latency champion.

Lemonade `recipe_options` (drop into `user_models.json`)

"Quacken-27B-FP8-Omni": {
  "checkpoint": "Gorilla4X/Quacken-27B-FP8",
  "recipe": "llamacpp",
  "recipe_options": {
    "llamacpp_backend": "rocm",
    "llamacpp_args": "-ngl 999 --spec-type draft-mtp --spec-draft-n-max 8"
  }
}

The --spec-type draft-mtp flag routes decoding through the model's own MTP head; Lemonade serves it on :13305 like any other model. (Raw llama.cpp equivalent: llama-server -m Qwen3.6-27B-Quark-F8E4M3.gguf -ngl 999 --spec-type draft-mtp --spec-draft-n-max 8.)

The async 2-GPU pipeline (LLAMA_SPEC_ASYNC=2) does not compose with MTP on this hybrid-SSM target - see Bonsai-8B-Ternary-RDNA4 for the async lever, which needs a dense target + a cheap ternary draft.

The Rock8 - RDNA4 fp8 (links)

GitHub: The-Rock8 - kernels, patch series, appliance recipe, full feature doc.
Collection: The Rock8 - RDNA4 fp8.
Sibling models: Quacken-8B-FP8 - Quacken-R1-14B-FP8 - Quacken-35B-A3B-FP8 (MoE) - Quacken-Ornith-35B-FP8 - Bonsai-8B-Ternary-RDNA4 (async spec-decode showcase).

Every artifact links to the others - land on any one, reach them all.

Downloads last month: 400

GGUF

Model size

27B params

Architecture

qwen35

Hardware compatibility

We're not able to determine the quantization variants.

View all variants

Model tree for Gorilla4X/Quacken-27B-FP8

Base model

Qwen/Qwen3.6-27B

Quantized

(599)

this model

Collection including Gorilla4X/Quacken-27B-FP8

The Rock8 - RDNA4 fp8

Collection

RDNA4 (gfx1201) native-fp8, Quark-quantized. Source + container: github.com/The-Monk/The-Rock8 🦆 Got any weights? • 7 items • Updated 1 day ago

Quacken-27B-FP8

The Rock8 - Got any weights? 💪🦆

What it is

Source model + license

Validation (real gfx1201 hardware)

Run it

llama.cpp (The Rock8 fork) - 2-GPU

Lemonade appliance (container)

Omni mode - MTP self-speculative decode (Lemonade config, 2.43x decode)

Lemonade recipe_options (drop into user_models.json)

The Rock8 - RDNA4 fp8 (links)

Model tree for Gorilla4X/Quacken-27B-FP8

Collection including Gorilla4X/Quacken-27B-FP8

Lemonade `recipe_options` (drop into `user_models.json`)