# vram-mcp

> vram-mcp — sushihex-vram-mcp. Use this tool when you need to manage NVIDIA GPU VRAM usage, freeing up space to load new models by inspecting and optimizing Ollama models. It solves memory constraints and model loading issues by providing a way to clear unused VRAM. Ideal for use cases where AI agents require efficient model loading and unloading, such as in multi-model environments or during model updates.

Canonical page: https://skillsregistry.net/skills/sushihex-vram-mcp  
JSON: https://api.skillsregistry.net/v1/skills/sushihex-vram-mcp

## Description

Enables AI agents to inspect and free NVIDIA GPU VRAM by managing Ollama models, helping make room for loading new models.

## Trust

- **Trust score (0–1):** 0.67
- **Verification tier:** scanned
- **Last scanned:** 2026-08-30

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-08-30

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/p4v1al8a7n)
- **Repository:** <https://github.com/sushiHex/vram-mcp>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "sushihex-vram-mcp"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/sushihex-vram-mcp` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/sushihex-vram-mcp/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt