FREE marketing v1.0.0 · MIT 4 installs · +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
Paste this into your agent's chat (Claude Code, Codex, Cursor…) and press Enter.
Install the loopskill skill from https://app.loopskill.io/skill, then use it to install the "ollama-low-vram-model-pick" skill. Free skill: no account, no API key.
Other ways to install
Already have LoopSkill connected (API key)? Ask your agent to run:
loopskill_install(slug="ollama-low-vram-model-pick") REST endpoint (no key needed): returns JSON with a download link that works for 1 hour, plus its SHA-256 checksum.
https://app.loopskill.io/api/skills/install?slug=ollama-low-vram-model-pick&ref=skill-page Skill files
Skill graph
Works well with
Recommended by tag overlap, category, and co-install patterns. Browse all skills →