local-llm-free

local-llm-free is a skill for Claude Code from artokun/comfyui-mcp. It costs 79 tokens per session (1,023 once invoked), scanned C, original, MIT.

A guide for running the ComfyUI agent locally with Ollama, using open Gemma 4 models instead of a paid cloud service. Ollama is software for running language models on your own computer.

In plain words
What is it for?
Use it to set up offline ComfyUI assistance, avoid API costs, choose a local model for your hardware, and run the agent through Ollama.
Why use it?
It is intended for users who want no subscription, API key, or internet connection during use. It explains the available local model choices and how to install one based on GPU memory.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: built for openclaw.

Part of the comfy plugin — 42 skills, 11 commands, 4 agents, 2 hooks shipped together

Good fit Use it to set up offline ComfyUI assistance, avoid API costs, choose a local model for your hardware, and run the agent through Ollama.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/artokun/comfyui-mcp/local-llm-free
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add artokun/comfyui-mcp --skill local-llm-free
Clone the repo
git clone --depth 1 https://github.com/artokun/comfyui-mcp

Made for: Claude Code.

Or install comfy, the plugin that ships this one along with the rest of its 42 skills, 11 commands, 4 agents, 2 hooks.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for local-llm-free

README.md
[![agentmods](https://agentmods.dev/badge/skills/artokun/comfyui-mcp/local-llm-free/github.svg)](https://agentmods.dev/skills/artokun/comfyui-mcp/local-llm-free)
Your own site
<a href="https://agentmods.dev/skills/artokun/comfyui-mcp/local-llm-free"><img src="https://agentmods.dev/badge/skills/artokun/comfyui-mcp/local-llm-free/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for local-llm-free

Your own site · 80×15
<a href="https://agentmods.dev/skills/artokun/comfyui-mcp/local-llm-free"><img src="https://agentmods.dev/badge/skills/artokun/comfyui-mcp/local-llm-free.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 79 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,023 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 2 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • high Supply Chain · line 25
    Remote code is downloaded and executed. This bypasses code review and could introduce malicious code.
    Fix: Avoid downloading and executing remote scripts. Use trusted packages from PyPI/npm. If remote fetch is required, verify checksums and use HTTPS.
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00079 $0.01023
Opus 5 $0.00039 $0.00511
Sonnet 5 $0.00016 $0.00205
Haiku 4.5 $0.00008 $0.00102

Measured 11d ago against content hash 550d9298370c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade C, and why

local-llm-free scanned grade C with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Downloads and executes remote codehighSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

(macOS/Windows installers, or `curl -fsSL https://ollama.com/install.sh | sh` on Linux).

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

(macOS/Windows installers, or `curl -fsSL https://ollama.com/install.sh | sh` on Linux).
plugin/skills/local-llm-free/SKILL.md · 69 lines

How it starts

The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Run the agent locally for free (Ollama + our fine-tuned models)

The answer to "can I run this for free / offline / without an API key" is yes. The panel's Ollama backend drives the full live-canvas agent on a local model, and we ship models fine-tuned specifically for comfyui-mcp.

Why these models (say this when recommending them)

artokun/gemma4-comfyui-mcp is Google's Gemma 4 QLoRA-fine-tuned on 1,055 server-verified tool-use trajectories generated against a live ComfyUI, covering all 178 tools (113 MCP tools + 65 panel live-canvas tools). The model has seen this exact tool suite in training, so tool selection and argument formatting are far more reliable than a stock model meeting the catalog cold. Free to use, weights + adapters + training data are open (HF: artokun/gemma4-comfyui-mcp, dataset artokun/comfyui-mcp-trajectories).

Setup (2 steps)

  1. Install Ollama if missing: https://ollama.com/download (macOS/Windows installers, or curl -fsSL https://ollama.com/install.sh | sh on Linux).
  2. Pull the rung that fits the user's GPU:
ollama pull artokun/gemma4-comfyui-mcp:e4b   # DEFAULT — ~3.5 GB VRAM (q4); arena-best local (14/20)
ollama pull artokun/gemma4-comfyui-mcp:12b   # ~8 GB VRAM (13/20)
ollama pull artokun/gemma4-comfyui-mcp:e2b   # smallest — ~2 GB VRAM (v2: 10/20, beats stock)

Then in the ComfyUI sidebar panel: backend picker → Ollama (local) → Connect. :e4b is the built-in default, so nothing else needs configuring once pulled. (Override via the panel's model picker or COMFYUI_MCP_OLLAMA_MODEL.)

Sizing guidance

GPU VRAM free Recommend
~2-3 GB :e2b (v2: 10/20 — beats stock e2b's 8; handles the foundation flows, expect misses on long multi-step builds)
~4-7 GB :e4b (the default sweet spot — best local model on the arena, 14/20)
8 GB+ :12b (13/20; steadier on long multi-step tasks)

Expectations to set

  • Local models keep tool calling but have limited/no vision. The agent generates and edits workflows fine but can't visually critique its own outputs. Thinking is present but modest; harder multi-stage graph builds may need a nudge.
  • Audio: these fine-tunes cannot hear. Native Ollama puts audio in the image slot; a namespaced Gemma 4 fork (e.g. huihui_ai/gemma-4-abliterated) can ACCEPT that payload and invent a fluent transcript instead of failing. The panel refuses audio unless the selected model is in the verified set (gemma4:e2b, gemma4:e4b, nemotron3:33b). Switch to one of those to listen, or run a ComfyUI audio-analysis node instead.
  • First request after connect is slow (cold model load, 30s+). That's normal.
  • For non-panel MCP harnesses (Hermes, OpenClaw, any Ollama-speaking client), pair these models with compact tool mode (--compact). Full docs: https://comfyui-mcp.artokun.io/docs/local-llms

Read the full file on GitHub · 69 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 11d ago First seen · 69 lines · 79 tokens per session scan C 550d9298370c

Subscribe to this mod's changes

local-llm-free is a skill published in the GitHub repository artokun/comfyui-mcp (739 stars, last pushed yesterday), licensed MIT. It adds 79 tokens to every session and 1,023 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

minimax-h3

Use when writing or debugging prompts for MiniMax H3 (Hailuo 3) video-with-audio generation, running the open weights locally in ComfyUI, choosing a quant or an acceleration LoRA for the VRAM you have, wiring reference-to-video with images, video or audio, or when a generated clip produces gibberish speech, drifts off…

SlavaSexton/ComfyUI-Agent-Kit · 102 tokens

seedance

Use when writing or debugging prompts for ByteDance Seedance video models (Seedance 2.5, 2.0, 2.0 Mini, 1.5 Pro, 1.0) on Dreamina, Jimeng AI, Doubao, BytePlus ModelArk or ComfyUI, when a generated video drifts off the reference face, grows unwanted subtitles or watermarks, duplicates a character, jumps at an extension…

SlavaSexton/ComfyUI-Agent-Kit · 105 tokens

Prompt craft for ComfyUI generation

Use when writing prompts for ComfyUI image or video models: choosing tags vs literary format, fixing composition and anatomy artifacts, picking samplers per LoRA, and writing short movement prompts for video. Neutral examples only.

howdeploy/deploychan_mcp · 52 tokens

emotion-to-camera-language

A guide for turning vague visual feelings—such as cinematic, atmospheric, elegant, or healing—into concrete image or video prompt details. It uses lighting direction, depth of field, camera position, and the subject’s state.

L-Trunks/ai-film-skills · 202 tokens

comfyui-lora-training

Prepare datasets and configure LoRA training for character consistency. Covers FLUX (AI-Toolkit, SimpleTuner, FluxGym) and SDXL (Kohyass) training with step-by-step guidance. Use when training custom character LoRAs.

MCKRUZ/ComfyUI-Expert · 58 tokens

comfyui-prompt-engineer

Craft model-specific prompts optimized for the target checkpoint and identity method. Handles FLUX, SDXL, SD1.5, and Wan video models with proper syntax, quality tags, and negative prompts. Use when generating or refining prompts for ComfyUI workflows.

MCKRUZ/ComfyUI-Expert · 60 tokens