Instructions to use julianmb/Qwen-3.8-27B-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 julianmb/Qwen-3.8-27B-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 julianmb/Qwen-3.8-27B-ROCmFP4-FAST-GGUF:Q3_K_M
# Run inference directly in the terminal:
llama cli -hf julianmb/Qwen-3.8-27B-ROCmFP4-FAST-GGUF:Q3_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf julianmb/Qwen-3.8-27B-ROCmFP4-FAST-GGUF:Q3_K_M
# Run inference directly in the terminal:
llama cli -hf julianmb/Qwen-3.8-27B-ROCmFP4-FAST-GGUF:Q3_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 julianmb/Qwen-3.8-27B-ROCmFP4-FAST-GGUF:Q3_K_M
# Run inference directly in the terminal:
./llama-cli -hf julianmb/Qwen-3.8-27B-ROCmFP4-FAST-GGUF:Q3_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 julianmb/Qwen-3.8-27B-ROCmFP4-FAST-GGUF:Q3_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf julianmb/Qwen-3.8-27B-ROCmFP4-FAST-GGUF:Q3_K_M

Use Docker

docker model run hf.co/julianmb/Qwen-3.8-27B-ROCmFP4-FAST-GGUF:Q3_K_M

LM Studio
Jan

vLLM

How to use julianmb/Qwen-3.8-27B-ROCmFP4-FAST-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "julianmb/Qwen-3.8-27B-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": "julianmb/Qwen-3.8-27B-ROCmFP4-FAST-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/julianmb/Qwen-3.8-27B-ROCmFP4-FAST-GGUF:Q3_K_M

Ollama
How to use julianmb/Qwen-3.8-27B-ROCmFP4-FAST-GGUF with Ollama:
```
ollama run hf.co/julianmb/Qwen-3.8-27B-ROCmFP4-FAST-GGUF:Q3_K_M
```
Unsloth Desktop

How to use julianmb/Qwen-3.8-27B-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 julianmb/Qwen-3.8-27B-ROCmFP4-FAST-GGUF:Q3_K_M

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": "julianmb/Qwen-3.8-27B-ROCmFP4-FAST-GGUF:Q3_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use julianmb/Qwen-3.8-27B-ROCmFP4-FAST-GGUF with Docker Model Runner:
```
docker model run hf.co/julianmb/Qwen-3.8-27B-ROCmFP4-FAST-GGUF:Q3_K_M
```

Lemonade

How to use julianmb/Qwen-3.8-27B-ROCmFP4-FAST-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull julianmb/Qwen-3.8-27B-ROCmFP4-FAST-GGUF:Q3_K_M

Run and chat with the model

lemonade run user.Qwen-3.8-27B-ROCmFP4-FAST-GGUF-Q3_K_M

List all available models

lemonade list

Hermes Agent

How to use julianmb/Qwen-3.8-27B-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 julianmb/Qwen-3.8-27B-ROCmFP4-FAST-GGUF:Q3_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 julianmb/Qwen-3.8-27B-ROCmFP4-FAST-GGUF:Q3_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use julianmb/Qwen-3.8-27B-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 julianmb/Qwen-3.8-27B-ROCmFP4-FAST-GGUF:Q3_K_M

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 "julianmb/Qwen-3.8-27B-ROCmFP4-FAST-GGUF:Q3_K_M" \
  --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"

780M 890M ?

by bobbytaylor - opened Sep 3

Discussion

bobbytaylor

Sep 3

Will this also work okay on the smaller Radeon unified memory GPUs ?

julianmb

Owner Sep 4

Hugging Face CLI

Hi @bobbytaylor — great question, and short answer: probably yes for the 890M, maybe for the 780M — but you'd be the first to try, so let's find out together.

Why it might just work:

The GGUF itself is architecture-independent; what matters is the engine + ROCm stack.
The 890M (Strix Point, gfx1150) is the close cousin of our validated target (8060S/gfx1151, RDNA 3.5) — same Mesa RADV Vulkan path, same kernel generation.
The 780M depends on which one: a Strix Point 780M (RDNA 3.5) has a shot; an older Hawk Point 780M (RDNA3) is less certain, since the coopmat kernels are tuned for RDNA 3.5.

Memory math (13.55 GiB weights):

32 GB unified: comfortable — 32K context (~16 GiB total), per our memory table.
16 GB unified: tight but plausible — try --profile safe (conservative, no MTP) or --ctx 8192, and max out the UMA frame buffer in BIOS.

Could you try this and report back?

git clone https://github.com/julianmb/q38rocm.git && cd q38rocm
./quickstart.sh

And paste: rocminfo | grep -m1 gfx, total RAM (free -g), OS/distro, plus either the first error you hit or a quick llama-bench line (pp512/tg128). If it runs, we'll add a "Smaller APUs (780M/890M)" compatibility section to the README with your numbers credited.

Which exact machine / how much RAM do you have?

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment