Instructions to use williamliao/Qwen3.8-27B-NVFP4-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 williamliao/Qwen3.8-27B-NVFP4-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 williamliao/Qwen3.8-27B-NVFP4-GGUF:NVFP4
# Run inference directly in the terminal:
llama cli -hf williamliao/Qwen3.8-27B-NVFP4-GGUF:NVFP4

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf williamliao/Qwen3.8-27B-NVFP4-GGUF:NVFP4
# Run inference directly in the terminal:
llama cli -hf williamliao/Qwen3.8-27B-NVFP4-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 williamliao/Qwen3.8-27B-NVFP4-GGUF:NVFP4
# Run inference directly in the terminal:
./llama-cli -hf williamliao/Qwen3.8-27B-NVFP4-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 williamliao/Qwen3.8-27B-NVFP4-GGUF:NVFP4
# Run inference directly in the terminal:
./build/bin/llama-cli -hf williamliao/Qwen3.8-27B-NVFP4-GGUF:NVFP4

Use Docker

docker model run hf.co/williamliao/Qwen3.8-27B-NVFP4-GGUF:NVFP4

LM Studio
Jan

vLLM

How to use williamliao/Qwen3.8-27B-NVFP4-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "williamliao/Qwen3.8-27B-NVFP4-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": "williamliao/Qwen3.8-27B-NVFP4-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/williamliao/Qwen3.8-27B-NVFP4-GGUF:NVFP4

Ollama
How to use williamliao/Qwen3.8-27B-NVFP4-GGUF with Ollama:
```
ollama run hf.co/williamliao/Qwen3.8-27B-NVFP4-GGUF:NVFP4
```
Unsloth Desktop

How to use williamliao/Qwen3.8-27B-NVFP4-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf williamliao/Qwen3.8-27B-NVFP4-GGUF:NVFP4

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": "williamliao/Qwen3.8-27B-NVFP4-GGUF:NVFP4"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use williamliao/Qwen3.8-27B-NVFP4-GGUF with Docker Model Runner:
```
docker model run hf.co/williamliao/Qwen3.8-27B-NVFP4-GGUF:NVFP4
```

Lemonade

How to use williamliao/Qwen3.8-27B-NVFP4-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull williamliao/Qwen3.8-27B-NVFP4-GGUF:NVFP4

Run and chat with the model

lemonade run user.Qwen3.8-27B-NVFP4-GGUF-NVFP4

List all available models

lemonade list

Hermes Agent

How to use williamliao/Qwen3.8-27B-NVFP4-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 williamliao/Qwen3.8-27B-NVFP4-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 williamliao/Qwen3.8-27B-NVFP4-GGUF:NVFP4

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use williamliao/Qwen3.8-27B-NVFP4-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf williamliao/Qwen3.8-27B-NVFP4-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 "williamliao/Qwen3.8-27B-NVFP4-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"

williamliao commited on 28 days ago

Commit

b590952

verified ·

1 Parent(s): bc57a64

Update README.md

Browse files

Files changed (1) hide show

README.md +10 -2

README.md CHANGED Viewed

@@ -98,9 +98,9 @@ unsloth/Qwen3.8-27B-NVFP4
 using a modified `convert_hf_to_gguf.py` with support for Qwen3.8 compressed-tensors mixed NVFP4 / FP8 layouts.
-### Important: this is NOT a 100% faithful restoration of the Unsloth checkpoint
-The Unsloth source checkpoint uses **mixed-precision compressed-tensors** with multiple quantization groups.
 During conversion:
@@ -109,6 +109,14 @@ During conversion:
 - FP8 tensors are dequantized by the converter.
 - With `--fp8-as-q8`, those FP8 tensors are then written as **Q8_0** instead of preserving their original FP8 storage format.
 Therefore:
 > **Qwen3.8-27B-Unsloth-NVFP4-Q8 is not a bit-identical, numerically identical, or 100% format-faithful copy of `unsloth/Qwen3.8-27B-NVFP4`.**

 using a modified `convert_hf_to_gguf.py` with support for Qwen3.8 compressed-tensors mixed NVFP4 / FP8 layouts.
+### Important: not a 1:1 reproduction of the Unsloth checkpoint
+This GGUF is derived from `unsloth/Qwen3.8-27B-NVFP4`, but it is not a bit-identical or format-identical reproduction of the original compressed-tensors checkpoint.
 During conversion:
 - FP8 tensors are dequantized by the converter.
 - With `--fp8-as-q8`, those FP8 tensors are then written as **Q8_0** instead of preserving their original FP8 storage format.
+As a result, the original Unsloth mixed-precision layout is not preserved exactly.
+Qwen3.8-27B-Unsloth-NVFP4-Q8 should therefore be considered an Unsloth-derived NVFP4/Q8 GGUF conversion for llama.cpp, not a 100% faithful reproduction of unsloth/Qwen3.8-27B-NVFP4.
+The NVFP4 portions are preserved through repacking where applicable, but the checkpoint's complete original mixed-precision representation is not reproduced exactly.
+It should also not be assumed to behave identically to the original Unsloth checkpoint under Transformers, compressed-tensors, vLLM, or another reference runtime.
 Therefore:
 > **Qwen3.8-27B-Unsloth-NVFP4-Q8 is not a bit-identical, numerically identical, or 100% format-faithful copy of `unsloth/Qwen3.8-27B-NVFP4`.**