Instructions to use 2stacks/gemma3-4b-it-comedy-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use 2stacks/gemma3-4b-it-comedy-v2 with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="2stacks/gemma3-4b-it-comedy-v2",
	filename="gemma3-4b-it-comedy-v2-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

llama.cpp

How to use 2stacks/gemma3-4b-it-comedy-v2 with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf 2stacks/gemma3-4b-it-comedy-v2:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf 2stacks/gemma3-4b-it-comedy-v2:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf 2stacks/gemma3-4b-it-comedy-v2:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf 2stacks/gemma3-4b-it-comedy-v2: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 2stacks/gemma3-4b-it-comedy-v2:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf 2stacks/gemma3-4b-it-comedy-v2: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 2stacks/gemma3-4b-it-comedy-v2:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf 2stacks/gemma3-4b-it-comedy-v2:Q4_K_M

Use Docker

docker model run hf.co/2stacks/gemma3-4b-it-comedy-v2:Q4_K_M

LM Studio
Jan
Ollama
How to use 2stacks/gemma3-4b-it-comedy-v2 with Ollama:
```
ollama run hf.co/2stacks/gemma3-4b-it-comedy-v2:Q4_K_M
```

Unsloth Studio new

How to use 2stacks/gemma3-4b-it-comedy-v2 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 2stacks/gemma3-4b-it-comedy-v2 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 2stacks/gemma3-4b-it-comedy-v2 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for 2stacks/gemma3-4b-it-comedy-v2 to start chatting

Docker Model Runner
How to use 2stacks/gemma3-4b-it-comedy-v2 with Docker Model Runner:
```
docker model run hf.co/2stacks/gemma3-4b-it-comedy-v2:Q4_K_M
```

Lemonade

How to use 2stacks/gemma3-4b-it-comedy-v2 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull 2stacks/gemma3-4b-it-comedy-v2:Q4_K_M

Run and chat with the model

lemonade run user.gemma3-4b-it-comedy-v2-Q4_K_M

List all available models

lemonade list

gemma3-4b-it-comedy-v2

QLoRA fine-tune of unsloth/gemma-3-4b-it on 2stacks/comedy-style-instruct (316 examples: 120 verbatim H/A/J + 96 30-comedian variety + 100 in-the-style-of originals).

This model is trained to respond to user prompts with stand-up-style jokes, with a particular emphasis on the voices of Mitch Hedberg, Dave Attell, and Anthony Jeselnik. Style coverage extends to 30 additional comedians via the variety set.

Training


Base	`unsloth/gemma-3-4b-it`
Method	QLoRA r=64, alpha=128, dropout 0
Targets	q,k,v,o,gate,up,down
Schedule	6 epochs, lr 0.0001, cosine, warmup 5
Batch	2×4 effective 8
Seq len	1024
Hardware	1×H100 on Modal
Final loss	3.8498

W&B: gemma3-comedy-qlora / run gemma3-4b-it-r64-a128-6ep-316ex-v2.

Files

LoRA adapter (peft format)
*.safetensors — merged 16-bit
*.Q4_K_M.gguf — llama.cpp / Ollama format

Use

from transformers import AutoModelForCausalLM, AutoTokenizer
m = AutoModelForCausalLM.from_pretrained("2stacks/gemma3-4b-it-comedy-v2")
t = AutoTokenizer.from_pretrained("2stacks/gemma3-4b-it-comedy-v2")

Or in Ollama via the GGUF artifact.

Caveats

Joke-by-default. This model trades general helpfulness for comedic voice. Use it for jokes; use the base model for tasks.
Dark humor over-represented. Jeselnik / Attell / Stanhope material pushes the distribution toward edgier output. Expect the model to take dark turns even on innocent prompts.
Non-commercial license. Per the underlying dataset, this model is CC-BY-NC-4.0 — research, education, and personal use only.

Attribution

The training data is sourced from publicly-available stand-up material released by 33 working comedians. Per-special and per-comedian attribution tables are maintained on the dataset card.

If you enjoy the voices this model imitates, please support those comedians by buying or streaming their specials directly.

Downloads last month: 112

Safetensors

Model size

4B params

Tensor type

BF16

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for 2stacks/gemma3-4b-it-comedy-v2

Base model

google/gemma-3-4b-pt

Finetuned

google/gemma-3-4b-it

Finetuned

unsloth/gemma-3-4b-it

Quantized

(17)

this model

Quantizations

1 model

2stacks
/

gemma3-4b-it-comedy-v2