---
title: "Inspect and benchmark"
description: "Read the released container directly and measure decode performance on the active machine."
canonical: "https://www.fermionresearch.com/docs/inspect-bench/"
source: "Fermion Research"
---

Docs / Guides

# Inspect and benchmark

Read the released container directly and measure decode performance on the active machine.

## Inspect a model artifact

```text
fermion inspect
fermion inspect --layer 0 --projection q
fermion inspect --sha256 --json
```

`inspect` reports geometry, parameters by tensor class, projection weight-state occupancy, byte use, per-layer occupancy spread, and KV-cache cost. `--json` makes the result machine-readable.

| Flag | Effect |
| --- | --- |
| `--layer N` | Restrict inspection to one layer and skip the rest of the file. |
| `--projection TYPE` | Select q, k, v, o, gate, up, or down. |
| `--sha256` | Add a full-file digest. |
| `--json` | Return structured output. |

## Benchmark the current machine

```text
fermion bench
fermion bench --tokens 128 --warmup 2
fermion bench --draft auto
```

The benchmark prints detected hardware, model size, load time, wall throughput, and steady-state decode throughput separately. With a draft, it adds a drafted row and an output-identity check.

| Flag | Default | Purpose |
| --- | --- | --- |
| `--tokens` | 32 | Greedy generation window. |
| `--prompt` | fixed prompt | Replace the benchmark prompt. |
| `--warmup` | 1 | Warm-up generations before measurement. |
| `--draft` | none | Measure speculative decoding too. |

Source: [https://www.fermionresearch.com/docs/inspect-bench/](https://www.fermionresearch.com/docs/inspect-bench/)