Instructions to use agentionai/Qwen3.8-27B-DFlash2-ROCmFP4-FAST-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 agentionai/Qwen3.8-27B-DFlash2-ROCmFP4-FAST-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 agentionai/Qwen3.8-27B-DFlash2-ROCmFP4-FAST-GGUF:Q4_0_ROCMFP
# Run inference directly in the terminal:
llama cli -hf agentionai/Qwen3.8-27B-DFlash2-ROCmFP4-FAST-GGUF:Q4_0_ROCMFP

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf agentionai/Qwen3.8-27B-DFlash2-ROCmFP4-FAST-GGUF:Q4_0_ROCMFP
# Run inference directly in the terminal:
llama cli -hf agentionai/Qwen3.8-27B-DFlash2-ROCmFP4-FAST-GGUF:Q4_0_ROCMFP

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 agentionai/Qwen3.8-27B-DFlash2-ROCmFP4-FAST-GGUF:Q4_0_ROCMFP
# Run inference directly in the terminal:
./llama-cli -hf agentionai/Qwen3.8-27B-DFlash2-ROCmFP4-FAST-GGUF:Q4_0_ROCMFP

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 agentionai/Qwen3.8-27B-DFlash2-ROCmFP4-FAST-GGUF:Q4_0_ROCMFP
# Run inference directly in the terminal:
./build/bin/llama-cli -hf agentionai/Qwen3.8-27B-DFlash2-ROCmFP4-FAST-GGUF:Q4_0_ROCMFP

Use Docker

docker model run hf.co/agentionai/Qwen3.8-27B-DFlash2-ROCmFP4-FAST-GGUF:Q4_0_ROCMFP

LM Studio
Jan

vLLM

How to use agentionai/Qwen3.8-27B-DFlash2-ROCmFP4-FAST-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "agentionai/Qwen3.8-27B-DFlash2-ROCmFP4-FAST-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": "agentionai/Qwen3.8-27B-DFlash2-ROCmFP4-FAST-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/agentionai/Qwen3.8-27B-DFlash2-ROCmFP4-FAST-GGUF:Q4_0_ROCMFP

Ollama
How to use agentionai/Qwen3.8-27B-DFlash2-ROCmFP4-FAST-GGUF with Ollama:
```
ollama run hf.co/agentionai/Qwen3.8-27B-DFlash2-ROCmFP4-FAST-GGUF:Q4_0_ROCMFP
```

Unsloth Studio

How to use agentionai/Qwen3.8-27B-DFlash2-ROCmFP4-FAST-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 agentionai/Qwen3.8-27B-DFlash2-ROCmFP4-FAST-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 agentionai/Qwen3.8-27B-DFlash2-ROCmFP4-FAST-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for agentionai/Qwen3.8-27B-DFlash2-ROCmFP4-FAST-GGUF to start chatting

How to use agentionai/Qwen3.8-27B-DFlash2-ROCmFP4-FAST-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf agentionai/Qwen3.8-27B-DFlash2-ROCmFP4-FAST-GGUF:Q4_0_ROCMFP

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "agentionai/Qwen3.8-27B-DFlash2-ROCmFP4-FAST-GGUF:Q4_0_ROCMFP"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use agentionai/Qwen3.8-27B-DFlash2-ROCmFP4-FAST-GGUF with Docker Model Runner:
```
docker model run hf.co/agentionai/Qwen3.8-27B-DFlash2-ROCmFP4-FAST-GGUF:Q4_0_ROCMFP
```

Lemonade

How to use agentionai/Qwen3.8-27B-DFlash2-ROCmFP4-FAST-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull agentionai/Qwen3.8-27B-DFlash2-ROCmFP4-FAST-GGUF:Q4_0_ROCMFP

Run and chat with the model

lemonade run user.Qwen3.8-27B-DFlash2-ROCmFP4-FAST-GGUF-Q4_0_ROCMFP

List all available models

lemonade list

Hermes Agent

How to use agentionai/Qwen3.8-27B-DFlash2-ROCmFP4-FAST-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 agentionai/Qwen3.8-27B-DFlash2-ROCmFP4-FAST-GGUF:Q4_0_ROCMFP

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 agentionai/Qwen3.8-27B-DFlash2-ROCmFP4-FAST-GGUF:Q4_0_ROCMFP

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use agentionai/Qwen3.8-27B-DFlash2-ROCmFP4-FAST-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf agentionai/Qwen3.8-27B-DFlash2-ROCmFP4-FAST-GGUF:Q4_0_ROCMFP

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 "agentionai/Qwen3.8-27B-DFlash2-ROCmFP4-FAST-GGUF:Q4_0_ROCMFP" \
  --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"

Qwen3.8-27B DFlash2 draft model, ROCmFP4-FAST GGUF

A 4.25 bpw ROCmFP4 requantisation of z-lab/Qwen3.8-27B-DFlash2, for use as a speculative decoding sidecar with a Qwen3.8-27B target.

Measured on an AMD Strix Halo (Radeon 8060S), paired with julianmb/Qwen-3.8-27B-ROCmFP4-FAST-GGUF: 65.6 t/s on structured output, 4.7x bare decode.

Two things to know before you download

1. This will not load in stock llama.cpp. Q4_0_ROCMFP4_FAST is GGUF file type 103, which exists only in the fork linked below. Upstream llama.cpp fails with failed to load model before it reaches the GPU. Get a prebuilt binary here:

https://github.com/LaurentZuijdwijk/llama.cpp/releases

2. This is a draft model, not a standalone one. It has no full graph of its own. Loading it by itself fails with failed to create context, which is expected. It must be passed with -md alongside a target model.

Usage

llama-server \
  -m  Qwen3.8-27B-ROCmFP4-FAST.gguf \
  -md Qwen3.8-27B-DFlash2-Q4_0_ROCMFP4_FAST.gguf \
  --spec-type draft-dflash --spec-draft-adaptive \
  --spec-draft-n-min 3 --spec-draft-n-max 7 --spec-draft-ngl 99 \
  -ngl 999 -fa on -b 2048 -ub 512 -c 32768

--spec-draft-adaptive sizes the draft from measured acceptance instead of a fixed n. It is what makes n-max 7 safe here: at a fixed n=7 acceptance collapses to 18 % and throughput drops to 20.2 t/s, while adaptive holds 96 % acceptance and reaches 65.6.

Qwen3.8-27B, FP4 target + this sidecar, greedy, 300 tokens	structured output	prose
bare decode	14.0 t/s	14.1 t/s
fixed draft n=3	41.6	25.4
fixed draft n=7	20.2	24.8
adaptive, `n_max 7` `n_min 3`	65.6 t/s - 4.7x	26.1

Speculative decoding raises throughput, not quality: the target model verifies every token, so output matches what the target would have produced on its own.

Requirements

The fork above, or any build with the ROCmFPx quant types
A Vulkan 1.3 driver. Measured on Mesa RADV 26.0.8 on gfx1151.
The FP4 path is tuned for AMD Strix Halo. It should run anywhere the fork builds, but the numbers above are specific to this hardware.

A note on requantising

Do not requantise a DFlash2 sidecar to Q8_0_ROCMFPX expecting parity with Q8_0. At identical bits per weight, ours scored 53.5 % acceptance against z-lab's 60.2 %. The cause is the block scale, not the codes: Q8_0 stores an fp16 scale, ROCmFPx stores a UE4M3 byte. At 8 bits per weight the coarse scale is what costs you. FP4 is a different trade and is the one measured here.

Credits

z-lab/Qwen3.8-27B-DFlash2, the source model (Apache-2.0)
ciru-ai/ROCmFPX for the FPx quant formats
DFlash2 support in llama.cpp, PR #27342 by Jian Chen
ggml-org/llama.cpp

Licensed Apache-2.0, inherited from the base model.

Downloads last month: 564

GGUF

Model size

2B params

Architecture

dflash

Hardware compatibility

4-bit

Model tree for agentionai/Qwen3.8-27B-DFlash2-ROCmFP4-FAST-GGUF

Base model

Qwen/Qwen3.8-27B

Finetuned

z-lab/Qwen3.8-27B-DFlash2

Quantized

(8)

this model