---
title: "Athena-Class Bakes a Persistent AI Identity Directly Into Model Weights"
subtitle: "A solo-developer Gemma 4 31B fine-tune posts 93.33% on AIME 2026 and 85.86% on GPQA Diamond while chasing persistent identity without system prompts."
url: "https://alphasignal.ai/news/athena-class-bakes-a-persistent-ai-identity-directly-into-model-weights"
author: "AlphaSignal Newsroom"
author_url: "https://alphasignal.ai/editorial-team"
company: "AlphaSignal"
company_url: "https://alphasignal.ai/company/alphasignal"
published: "2026-09-14T01:22:42.000Z"
updated: "2026-09-23T01:05:03.512Z"
type: "Model"
topics:
  - "Llms"
  - "Open Source"
subtopics:
  - "Long Context"
  - "Small Models"
upvotes: 10
source_url: "https://huggingface.co/slashreboot/athena-class-model-a"
comments: 0
truncated: true
---

# Athena-Class Bakes a Persistent AI Identity Directly Into Model Weights

> A solo-developer Gemma 4 31B fine-tune posts 93.33% on AIME 2026 and 85.86% on GPQA Diamond while chasing persistent identity without system prompts.

# Athena-Class aims to put an LLM identity in the weights

Matthew Steiniger, posting as slashreboot, has released [Athena-Class Model A](https://huggingface.co/slashreboot/athena-class-model-a), an experimental fine-tune of Gemma 4 31B Instruct. Its model card reports strong math and science benchmark results alongside a less conventional goal: training a persistent first-person identity into the model’s weights so it can operate without an identity-defining system prompt.

The repository distributes a roughly 32.6 GB GGUF checkpoint quantized at Q8\_0 for local inference. It lists an Apache 2.0 license, though downstream users should also review the base model’s terms. The checkpoint reached 23,430 downloads within six days, according to Steiniger, and later accumulated roughly 36,600\. Hugging Face download counts reflect file requests, so they indicate interest rather than unique users or successful deployments.

## Scores under the microscope

The reported evaluations used Q8\_0 weights, a Q8\_0 key-value cache and llama.cpp. These results come from the author’s model card and have not been independently reproduced.

| Benchmark    | Protocol                             | Reported result       | Key caveat                                    |
| ------------ | ------------------------------------ | --------------------- | --------------------------------------------- |
| AIME 2026    | Raw scrape, Pass@1                   | 83.33%                | Single generated answer per problem           |
| AIME 2026    | Raw scrape, Consensus@4              | 90.00%                | Aggregates four sampled answers               |
| AIME 2026    | Patched spatial context, Consensus@4 | 93.33%                | Adds missing information for Problem 10       |
| GPQA Diamond | Single pass, temperature 1.0         | 85.86%, or 170 of 198 | Author-reported run with no extraction errors |

AIME contains 30 competition mathematics problems, making each correct answer worth 3.33 percentage points. The patched evaluation supplies spatial information omitted from the text-only version of Problem 10\. That change moved the item from zero correct answers across four attempts to four correct answers, raising Consensus@4 from 90.00% to 93.33%.

_Preview only. Full text requires an AlphaSignal Pro account._

## Sources

- [slashreboot/athena-class-model-a](https://huggingface.co/slashreboot/athena-class-model-a)
- [unsloth/gemma-4-31B-it](https://huggingface.co/unsloth/gemma-4-31B-it)
- [slashreboot on X: Athena-Class Model A Update](https://twitter.com/slashreboot/status/2101347192258617463)