# ArmBench MCP Server

> Use this tool when you need to benchmark and serve large language models (LLMs) on Arm64 cloud instances, solving problems of inefficient model deployment and inference. It provides an MCP-compatible API for serving results, taking in LLMs and KleidiAI optimizations as inputs and outputting benchmarking and inference results. Ideal for use cases requiring optimized LLM deployment on Arm64 architectures.

Canonical page: https://skillsregistry.net/skills/sirmos-armbench  
JSON: https://api.skillsregistry.net/v1/skills/sirmos-armbench

## Description

Enables benchmarking and inference of LLMs on Arm64 cloud instances with KleidiAI optimizations, providing an MCP-compatible API for serving results.

## Trust

- **Trust score (0–1):** 0.70
- **Verification tier:** verified
- **Last scanned:** 2026-09-03

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-09-03

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/twnnr99s66)
- **Repository:** <https://github.com/sirmos/arm-pulse>

## 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": "sirmos-armbench"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/sirmos-armbench` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/sirmos-armbench/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