FREE marketing v1.0.0 · MIT 1 install · +1/wk
Ollama Low-VRAM Model Picker
by LoopSkill community
Pick the right Ollama model for a low-VRAM GPU (≤4 GB) when offloading LLM work from a paid API (Z.AI, OpenAI) to local. Avoids the 'I'll just use the latest Gemma' trap — the newest models often DON'T fit on small consumer GPUs even at Q4. Validated 2026-04-27 on a GTX 1650 Ti (4 GB) for Cognee LLM
5 KB
Install in your agent
→ First time? Tell your agent: "install the loopskill skill from app.loopskill.io/skill" — then the lines below add this skill.
Quick install ollama-low-vram-model-pick
In your agent (MCP)
loopskill_install(slug="ollama-low-vram-model-pick") Signed install URL (curl-able with your API key)
https://app.loopskill.io/api/skills/install?slug=ollama-low-vram-model-pick&ref=skill-page Works in any MCP-capable agent — Claude Code, Cursor, Cline, OpenClaw, Hermes, Windsurf.
Your install command
Sign in to get your API key and the personalized install command.
Sign in to install →This skill requires Pro. Upgrade to install.
See plans →Copy and paste into your agent's environment:
export RECIPES_API_KEY=rec_live_… Get key → loopskill install ollama-low-vram-model-pick First time? Generate your API key on the Library page.
Checking…
Skill files