# Surogate (Invergent): rune

> Invergent's decision model for text and images. A fine-tune of Gemma-4-26B-A4B (about 4B parameters active per token) that answers Choice, Noul and Score questions, with an optional thinking mode for harder questions.

- Page: https://systemonemodels.tech/surogate/rune
- API: https://api.systemonemodels.tech/v1/models/surogate/rune
- Download: `pip install systemonemodels && systemone pull surogate/rune`

## Facts

| | |
|---|---|
| Maker | Surogate (Invergent) (https://systemonemodels.tech/surogate) |
| Decides | choice, score, noul, classify, route |
| Architecture | rune |
| Base model | google/gemma-4-26b-a4b-it |
| Parameters | 26B |
| Context | 262K tokens |
| Licence | apache-2.0 |
| Availability | Open weights + hosted API |
| Released | 2026-09-21 |
| Latest version | 2026.09 |

## Hosted API

- Provider: Invergent (https://invergent.ai/blog/rune/)

- Input: — · Output: —

## Model card

<!-- generated by scripts/seed_catalog.py; edit content/models/catalog.yaml -->

# Rune 26B-A4B

Invergent's decision model for text and images. A fine-tune of Gemma-4-26B-A4B (about 4B parameters active per token) that answers Choice, Noul and Score questions, with an optional thinking mode for harder questions.

The Hugging Face repository is gated (access must be requested) and, despite its name, holds BF16 safetensors shards; a hosted API is also offered. Invergent reports a Decision Index 0.2.1 score of 57.44 against Jev 1.13's 57.91, ahead of Jev in three of the five areas, and 90 to 180 ms per decision on an RTX PRO 6000 (0.18 s with an image, 4.9 s with thinking). On the public Decision Index board it was first among open models on 28 September. Context 262,000 tokens. Weights Apache-2.0, but check the gate's terms before mirroring.

## What it decides

- **choice** — picks one option from a set
- **score** — places the input on an ordered scale
- **noul** — answers a yes/no question with one calibrated probability
- **classify** — assigns a category from a fixed taxonomy
- **route** — sends the input to one of several destinations

## At a glance

| | |
|---|---|
| Parameters | 26B |
| Base model | `google/gemma-4-26b-a4b-it` |
| Maker | Surogate (Invergent) |
| Released | 2026-09-21 |
| License | apache-2.0 |
| Reported latency | 90–180 ms per decision on an RTX PRO 6000; 0.18 s with an image; 4.9 s with thinking |

## Hosted API

Served by **Invergent**. [Get access](https://invergent.ai/blog/rune/).

## Get the weights

```bash
pip install systemonemodels
systemone pull surogate/rune
```

The files are served from the maker's Hugging Face repository, [`surogate/rune-26b-a4b-GGUF`](https://huggingface.co/surogate/rune-26b-a4b-GGUF), and verified against the checksums recorded here.

## Read more

- [Launch post](https://invergent.ai/blog/rune/)
- [Weights on Hugging Face (gated)](https://huggingface.co/surogate/rune-26b-a4b-GGUF)
- [Decision Index](https://huggingface.co/spaces/multimodalart/jev-decision-index)

---

*This page was opened by System One for Surogate (Invergent), who can claim the organisation and take it over at any time.*

---

From System One Models — https://systemonemodels.tech/ · every System One model: https://systemonemodels.tech/system-one-models