# inferbench

> Use this tool when you need to benchmark and optimize local large language models (LLMs) on your own hardware, solving problems of model performance and efficiency. It takes in local LLMs and hardware specifications as input and outputs optimal quantization settings and real-time token processing speeds. Ideal for use cases where cloud-based solutions are not feasible or desired, such as on-demand model serving and local development environments.

Canonical page: https://skillsregistry.net/skills/jonimartin27-inferbench  
JSON: https://api.skillsregistry.net/v1/skills/jonimartin27-inferbench

## Description

InferBench's MCP server lets coding agents run, serve and benchmark local LLMs (text + image, llama.cpp + Stable Diffusion) on your own hardware on demand — measuring real tokens/sec and picking the optimal quant for your GPU from a 124-model catalog. Local-first, no cloud required.

## Trust

- **Trust score (0–1):** 0.29
- **Verification tier:** scanned
- **Last scanned:** 2026-08-31

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** iot-hardware
- **Updated:** 2026-08-31

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/bk5jmj7i05)
- **Repository:** <https://github.com/JoniMartin27/inferbench>

## 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": "jonimartin27-inferbench"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/jonimartin27-inferbench` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/jonimartin27-inferbench/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