Instructions to use duyntnet/Impish_LLAMA_4B-imatrix-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use duyntnet/Impish_LLAMA_4B-imatrix-GGUF with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="duyntnet/Impish_LLAMA_4B-imatrix-GGUF")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("duyntnet/Impish_LLAMA_4B-imatrix-GGUF", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use duyntnet/Impish_LLAMA_4B-imatrix-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 duyntnet/Impish_LLAMA_4B-imatrix-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf duyntnet/Impish_LLAMA_4B-imatrix-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf duyntnet/Impish_LLAMA_4B-imatrix-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf duyntnet/Impish_LLAMA_4B-imatrix-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 duyntnet/Impish_LLAMA_4B-imatrix-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf duyntnet/Impish_LLAMA_4B-imatrix-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 duyntnet/Impish_LLAMA_4B-imatrix-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf duyntnet/Impish_LLAMA_4B-imatrix-GGUF:Q4_K_M

Use Docker

docker model run hf.co/duyntnet/Impish_LLAMA_4B-imatrix-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use duyntnet/Impish_LLAMA_4B-imatrix-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "duyntnet/Impish_LLAMA_4B-imatrix-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "duyntnet/Impish_LLAMA_4B-imatrix-GGUF",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/duyntnet/Impish_LLAMA_4B-imatrix-GGUF:Q4_K_M

SGLang

How to use duyntnet/Impish_LLAMA_4B-imatrix-GGUF with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "duyntnet/Impish_LLAMA_4B-imatrix-GGUF" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "duyntnet/Impish_LLAMA_4B-imatrix-GGUF",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "duyntnet/Impish_LLAMA_4B-imatrix-GGUF" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "duyntnet/Impish_LLAMA_4B-imatrix-GGUF",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Ollama
How to use duyntnet/Impish_LLAMA_4B-imatrix-GGUF with Ollama:
```
ollama run hf.co/duyntnet/Impish_LLAMA_4B-imatrix-GGUF:Q4_K_M
```

Unsloth Studio

How to use duyntnet/Impish_LLAMA_4B-imatrix-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 duyntnet/Impish_LLAMA_4B-imatrix-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 duyntnet/Impish_LLAMA_4B-imatrix-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for duyntnet/Impish_LLAMA_4B-imatrix-GGUF to start chatting

Docker Model Runner
How to use duyntnet/Impish_LLAMA_4B-imatrix-GGUF with Docker Model Runner:
```
docker model run hf.co/duyntnet/Impish_LLAMA_4B-imatrix-GGUF:Q4_K_M
```

Lemonade

How to use duyntnet/Impish_LLAMA_4B-imatrix-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull duyntnet/Impish_LLAMA_4B-imatrix-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Impish_LLAMA_4B-imatrix-GGUF-Q4_K_M

List all available models

lemonade list

Atomic Chat

Quantizations of https://huggingface.co/SicariusSicariiStuff/Impish_LLAMA_4B

Open source inference clients/UIs

Closed source inference clients/UIs

LM Studio
More will be added...

From original readme

Impish_LLAMA_4B

5th of May, 2025, Impish_LLAMA_4B.

Almost a year ago, I created Impish_LLAMA_3B, the first fully coherent 3B roleplay model at the time. It was quickly adopted by some platforms, as well as one of the go-to models for mobile. After some time, I made Fiendish_LLAMA_3B and insisted it was not an upgrade, but a different flavor (which was indeed the case, as a different dataset was used to tune it).

Impish_LLAMA_4B, however, is an upgrade, a big one. I've had over a dozen 4B candidates, but none of them were 'worthy' of the Impish badge. This model has superior responsiveness and context awareness, and is able to pull off very coherent adventures. It even comes with some additional assistant capabilities too. Of course, while it is exceptionally competent for its size, it is still 4B. Manage expectations and all that. I, however, am very much pleased with it. It took several tries to pull off just right. Total tokens trained: about 400m (due to being a generalist model, lots of tokens went there, despite the emphasis on roleplay & adventure).

This took more effort than I thought it would. Because of course it would. This is mainly due to me refusing to release a model only 'slightly better' than my two 3B models mentioned above. Because "what would be the point" in that? The reason I included so many tokens for this tune is that small models are especially sensitive to many factors, including the percentage of moisture in the air and how many times I ran nvidia-smi since the system last started.

It's no secret that roleplay/creative writing models can reduce a model's general intelligence (any tune and RL risk this, but roleplay models are especially 'fragile'). Therefore, additional tokens of general assistant data were needed in my opinion, and indeed seemed to help a lot with retaining intelligence.

This model is also 'built a bit different', literally, as it is based on nVidia's prune; it does not 'behave' like a typical 8B, from my own subjective impression. This helped a lot with keeping it smart at such size.

To be honest, my 'job' here in open source is 'done' at this point. I've achieved everything I wanted to do here, and then some.

Downloads last month: 117

GGUF

Model size

5B params

Architecture

llama

Hardware compatibility

1-bit

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit