Instructions to use artokun/gemma4-comfyui-mcp with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use artokun/gemma4-comfyui-mcp with Transformers:

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

pipe = pipeline("text-generation", model="artokun/gemma4-comfyui-mcp")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("artokun/gemma4-comfyui-mcp", dtype="auto")

llama-cpp-python

How to use artokun/gemma4-comfyui-mcp with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="artokun/gemma4-comfyui-mcp",
	filename="12b/model-q4_k_m.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use artokun/gemma4-comfyui-mcp 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 artokun/gemma4-comfyui-mcp:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf artokun/gemma4-comfyui-mcp:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf artokun/gemma4-comfyui-mcp:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf artokun/gemma4-comfyui-mcp: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 artokun/gemma4-comfyui-mcp:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf artokun/gemma4-comfyui-mcp: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 artokun/gemma4-comfyui-mcp:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf artokun/gemma4-comfyui-mcp:Q4_K_M

Use Docker

docker model run hf.co/artokun/gemma4-comfyui-mcp:Q4_K_M

LM Studio
Jan

vLLM

How to use artokun/gemma4-comfyui-mcp with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "artokun/gemma4-comfyui-mcp"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "artokun/gemma4-comfyui-mcp",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/artokun/gemma4-comfyui-mcp:Q4_K_M

SGLang

How to use artokun/gemma4-comfyui-mcp 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 "artokun/gemma4-comfyui-mcp" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "artokun/gemma4-comfyui-mcp",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "artokun/gemma4-comfyui-mcp" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "artokun/gemma4-comfyui-mcp",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use artokun/gemma4-comfyui-mcp with Ollama:
```
ollama run hf.co/artokun/gemma4-comfyui-mcp:Q4_K_M
```

Unsloth Studio

How to use artokun/gemma4-comfyui-mcp 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 artokun/gemma4-comfyui-mcp 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 artokun/gemma4-comfyui-mcp to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for artokun/gemma4-comfyui-mcp to start chatting

How to use artokun/gemma4-comfyui-mcp with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf artokun/gemma4-comfyui-mcp: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": "artokun/gemma4-comfyui-mcp:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use artokun/gemma4-comfyui-mcp with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf artokun/gemma4-comfyui-mcp: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 artokun/gemma4-comfyui-mcp:Q4_K_M

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use artokun/gemma4-comfyui-mcp with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf artokun/gemma4-comfyui-mcp:Q4_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 "artokun/gemma4-comfyui-mcp:Q4_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"

Docker Model Runner
How to use artokun/gemma4-comfyui-mcp with Docker Model Runner:
```
docker model run hf.co/artokun/gemma4-comfyui-mcp:Q4_K_M
```

Lemonade

How to use artokun/gemma4-comfyui-mcp with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull artokun/gemma4-comfyui-mcp:Q4_K_M

Run and chat with the model

lemonade run user.gemma4-comfyui-mcp-Q4_K_M

List all available models

lemonade list

gemma4-comfyui-mcp

Local, offline LLMs fine-tuned to be ComfyUI experts that drive the full comfyui-mcp tool surface — 178 tools (113 MCP server tools + 65 live-canvas panel_* tools) — in Gemma 4's native tool-call format. These are the free, no-API-key backends for the comfyui-mcp Agent Panel: pick Ollama (local) in the panel and the agent edits your live graph, generates images/video/audio, manages models and custom nodes, and runs your workflows — entirely on your GPU.

Quickstart (Ollama, recommended):

ollama pull artokun/gemma4-comfyui-mcp:e4b   # default — ~3.5 GB VRAM at q4
# also:  :e2b (~2 GB VRAM)   :12b (~8 GB VRAM)

Size ladder

Pick by VRAM budget. Every rung is the same data, same recipe — only the base size changes.

Tag	Rung	Folder	Download (q4)	VRAM (q4)	Status
`:e2b`	Gemma 4 E2B (Heretic-ara)	`e2b/`	3.4 GB	~2 GB	✅ available
`:e4b`	Gemma 4 E4B (Heretic)	`e4b/`	5.3 GB	~3.5 GB	✅ available — the default
`:12b`	Gemma 4 12B (Heretic)	`12b/`	7.4 GB	~8 GB	✅ available
`:26b-a4b`	Gemma 4 26B-A4B, NVFP4 (nvidia)	—	—	—	⏸ parked (QLoRA+MoE routing interact poorly)

Each folder ships the GGUF quant(s), the LoRA adapter (r=32 — apply to the base or re-export any quant yourself), the trained chat template, and tokenizer/trainer configs.

What makes these different

A stock model meets comfyui-mcp's ~200-schema catalog cold and burns its context (and your patience) learning it. These models were trained on the tool suite itself:

Data: 1,055 server-verified tool-use trajectories (e4b/e2b; the earlier 12b rung trained on the initial 772) — synthesized TOUCAN-style against a live ComfyUI + comfyui-mcp server: task synthesis → real trajectory generation → server-verified filtering (every outcome checked against the actual server state, never the model's claims). Grounded in real pack workflows (krea2 / ideogram / qwen-edit / wan / ltxv) and skills. Fully open: artokun/comfyui-mcp-trajectories.
Trimmed-context tool-menu training: each example is rendered with the tools it actually calls plus random distractors (≤24 of the 178), in random order — the model learns to navigate a menu, not memorize positions, and generalizes to the full surface at inference (the xLAM/Toucan/Hermes recipe).
Teachers: open-weight only. No Anthropic/OpenAI/Google outputs anywhere in the training data (ToS), enforced by a blocklist in the dataset assembly.
Bases: the Heretic-abliterated Gemma 4 family (Optuna-optimized directional ablation — cleanest abliteration lineage), chosen by a server-verified bake-off over other abliterated variants.
Recipe: QLoRA r=32 / α=32 on q/k/v/o + MLP projections, 2 epochs, cosine LR 2e-4, seq len 12–16K, loss masked to assistant turns.

Validation

Every rung is validated in llama-server --jinja before release: native tool-call emission (finish_reason=tool_calls), correct tool selection, well-formed JSON arguments, and dimension/parameter extraction from natural-language requests. Final train loss: 0.022 (e4b), 0.021 (e2b); the 12b rung additionally passed live end-to-end panel runs.

Known behavior: :e2b reasons verbosely before calling — give it max_tokens ≥ 512 or the call gets truncated mid-thought. The current :e2b tag is the v2 retrain (see Arena results below).

Usage

ComfyUI Agent Panel (the intended home): install comfyui-mcp, pull a tag, pick Ollama (local) in the panel's backend picker. :e4b is the built-in default — zero further config.

Plain Ollama / any OpenAI-compatible client:

ollama pull artokun/gemma4-comfyui-mcp:e4b
# tags ship num_ctx 65536 + temperature 0 + the ComfyUI agent system prompt

llama.cpp:

llama-server -m e4b/model-q4_k_m.gguf --jinja -c 16384

From the adapter (transformers + PEFT): load the base (AutoModelForImageTextToText — Gemma 4 is the unified multimodal arch), attach <size>/adapter_model.safetensors, merge_and_unload(). A clean re-export path (sharded 16-bit + GGUF) ships in finetune/train/reexport.py.

Repo layout

12b/ e4b/ e2b/        model-q4_k_m.gguf (+q5/q8 where built), LoRA adapter,
                      chat_template.jinja, tokenizer/trainer configs
finetune/             the COMPLETE pipeline: datagen (task synth + tool-surface
                      export), train (QLoRA + dataset prep + re-export),
                      arena (server-verified eval harness), package (Modelfile)
finetune/data/        train/val JSONL (1,055 trajectories) + the 178-tool surface

Limits

Tool calling is the trained strength. Vision is limited at these sizes — the agent generates but can't visually critique its own outputs — and hard multi-stage graph composition (multi-output pipelines built in one shot) remains frontier-model territory (see the measured arena table below; the harness is in finetune/arena/).

Arena results (measured, server-verified)

Scores on the comfyui-mcp LLM Arena — a 10-scenario ladder (health → generation → break/fix → multi-stage pipelines) where every result is verified against a live ComfyUI server, not the model's claims. Best of 3 full runs per model, RTX 4090, PASS=2/PARTIAL=1/FAIL=0:

Model	Score	vs. stock base
`:e4b`	14/20 (13–14) — best local model we've tested	stock gemma4:e4b: 12/20
`:12b`	13/20 (12–13)	stock 12b unbenchmarked
`:e2b` v2	10/20 (7–10)	stock gemma4:e2b: 8/20

Every rung beats its stock base. For calibration, the same ladder scores frontier hosted models 19–20/20 and the best small hosted models 17–19/20 — these are honest local-tier numbers, not marketing.

e2b v2 note: the initial e2b release regressed below stock (4/20) — the smallest rung couldn't bridge between the direct-call training format and the deployed 6-tool router envelope, dropping call_tool's name field. v2 retrains on a dual-view mix (direct calls + the exact runtime router format + fresh server-verified arena trajectories) — zero malformed envelopes across all verdict runs. Details: comfyui-mcp#183.

Credits & license

Bases by p-e-w (Heretic) and coder3101; Gemma 4 by Google DeepMind (Gemma license). Fine-tune, data, and pipeline by @artokun — part of the comfyui-mcp project.

Downloads last month: 157

GGUF

Model size

12B params

Architecture

gemma4

Hardware compatibility

4-bit

5-bit

8-bit

Model tree for artokun/gemma4-comfyui-mcp

Base model

google/gemma-4-12B

Finetuned

google/gemma-4-12B-it

Finetuned

coder3101/gemma-4-12B-it-heretic

Quantized

(6)

this model