Instructions to use radm/prophet-qwen3-4b-sft-Q4_K_M-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use radm/prophet-qwen3-4b-sft-Q4_K_M-GGUF with Transformers:

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("radm/prophet-qwen3-4b-sft-Q4_K_M-GGUF", dtype="auto")

llama-cpp-python

How to use radm/prophet-qwen3-4b-sft-Q4_K_M-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="radm/prophet-qwen3-4b-sft-Q4_K_M-GGUF",
	filename="prophet-qwen3-4b-sft-q4_k_m.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use radm/prophet-qwen3-4b-sft-Q4_K_M-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf radm/prophet-qwen3-4b-sft-Q4_K_M-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf radm/prophet-qwen3-4b-sft-Q4_K_M-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf radm/prophet-qwen3-4b-sft-Q4_K_M-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf radm/prophet-qwen3-4b-sft-Q4_K_M-GGUF:Q4_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 radm/prophet-qwen3-4b-sft-Q4_K_M-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf radm/prophet-qwen3-4b-sft-Q4_K_M-GGUF:Q4_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 radm/prophet-qwen3-4b-sft-Q4_K_M-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf radm/prophet-qwen3-4b-sft-Q4_K_M-GGUF:Q4_K_M

Use Docker

docker model run hf.co/radm/prophet-qwen3-4b-sft-Q4_K_M-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use radm/prophet-qwen3-4b-sft-Q4_K_M-GGUF with Ollama:
```
ollama run hf.co/radm/prophet-qwen3-4b-sft-Q4_K_M-GGUF:Q4_K_M
```

Unsloth Studio

How to use radm/prophet-qwen3-4b-sft-Q4_K_M-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 radm/prophet-qwen3-4b-sft-Q4_K_M-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 radm/prophet-qwen3-4b-sft-Q4_K_M-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for radm/prophet-qwen3-4b-sft-Q4_K_M-GGUF to start chatting

How to use radm/prophet-qwen3-4b-sft-Q4_K_M-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf radm/prophet-qwen3-4b-sft-Q4_K_M-GGUF:Q4_K_M

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": "radm/prophet-qwen3-4b-sft-Q4_K_M-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use radm/prophet-qwen3-4b-sft-Q4_K_M-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf radm/prophet-qwen3-4b-sft-Q4_K_M-GGUF:Q4_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 radm/prophet-qwen3-4b-sft-Q4_K_M-GGUF:Q4_K_M

Run Hermes

hermes

Docker Model Runner
How to use radm/prophet-qwen3-4b-sft-Q4_K_M-GGUF with Docker Model Runner:
```
docker model run hf.co/radm/prophet-qwen3-4b-sft-Q4_K_M-GGUF:Q4_K_M
```

Lemonade

How to use radm/prophet-qwen3-4b-sft-Q4_K_M-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull radm/prophet-qwen3-4b-sft-Q4_K_M-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.prophet-qwen3-4b-sft-Q4_K_M-GGUF-Q4_K_M

List all available models

lemonade list

prophet-qwen3-4b-sft-Q4_K_M-GGUF / README.md

radm

Update README.md

c656465 verified about 1 year ago

preview code

raw

history blame

2.19 kB

	---
	base_model: radm/prophet-qwen3-4b-sft
	language:
	- zho
	- eng
	- fra
	- spa
	- por
	- deu
	- ita
	- rus
	- jpn
	- kor
	- vie
	- tha
	- ara
	library_name: transformers
	tags:
	- qwen3
	- sft
	- unsloth
	- philosophical
	- esoteric
	- llama-cpp
	- gguf-my-repo
	---

	# radm/prophet-qwen3-4b-sft-Q4_K_M-GGUF

	<img src="https://huggingface.co/radm/prophet-qwen3-4b-sft/resolve/main/model-image.png" alt="Model Image" width="100%">

	This model was converted to GGUF format from [`radm/prophet-qwen3-4b-sft`](https://huggingface.co/radm/prophet-qwen3-4b-sft) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
	Refer to the [original model card](https://huggingface.co/radm/prophet-qwen3-4b-sft) for more details on the model.

	## Usage

	For chat templapte errors (eg lmstudio) use [this issue](https://github.com/lmstudio-ai/lmstudio-bug-tracker/issues/479#issuecomment-2701947624).

	## Use with llama.cpp
	Install llama.cpp through brew (works on Mac and Linux)

	```bash
	brew install llama.cpp

	```
	Invoke the llama.cpp server or the CLI.

	### CLI:
	```bash
	llama-cli --hf-repo radm/prophet-qwen3-4b-sft-Q4_K_M-GGUF --hf-file prophet-qwen3-4b-sft-q4_k_m.gguf -p "The meaning to life and the universe is"
	```

	### Server:
	```bash
	llama-server --hf-repo radm/prophet-qwen3-4b-sft-Q4_K_M-GGUF --hf-file prophet-qwen3-4b-sft-q4_k_m.gguf -c 2048
	```

	Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well.

	Step 1: Clone llama.cpp from GitHub.
	```
	git clone https://github.com/ggerganov/llama.cpp
	```

	Step 2: Move into the llama.cpp folder and build it with `LLAMA_CURL=1` flag along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux).
	```
	cd llama.cpp && LLAMA_CURL=1 make
	```

	Step 3: Run inference through the main binary.
	```
	./llama-cli --hf-repo radm/prophet-qwen3-4b-sft-Q4_K_M-GGUF --hf-file prophet-qwen3-4b-sft-q4_k_m.gguf -p "The meaning to life and the universe is"
	```
	or
	```
	./llama-server --hf-repo radm/prophet-qwen3-4b-sft-Q4_K_M-GGUF --hf-file prophet-qwen3-4b-sft-q4_k_m.gguf -c 2048
	```