# ninjahawk/livenerf

> A benchmark for tracking whether a frontier model quietly degrades after release: it runs a frozen question panel daily and statistically measures drift in accuracy and token counts against the launch-week baseline.

- Magnitude: 3.3 out of 10 — Early signal
- Stars: 88 total · +0 stars today, ≈ 31 by evening
- Star trust: star growth looks organic
- Category: Language models · Language: Python · Created: 2026-09-22 · Last push: 2026-09-27
- GitHub: https://github.com/ninjahawk/livenerf · Page: https://gitnova.dev/en/r/ninjahawk/livenerf

## Useful for

- Run the daily question panel through headless Claude Code to collect a baseline
- Check whether model accuracy dropped over a 10-day window after release
- Track falling output token counts as an early sign of reduced model effort

## Why it’s here

- 0 stars so far today, about 31 expected by the end of the day.
- The spike has held for 3 days in a row — not a one-off blip.
- The repository is 6 days old and already has 88 stars. With less than two weeks of history, there's no usual pace to compare the spike against yet.
- Top new repositories this week: #152.

## Star trust

Star growth looks organic.

Star-trust labels are heuristics based on the repository’s behavior, not a check of every stargazer.

## Numbers

- Forks: 4
- Issues and pull requests: 5
- Watchers: 5
- Average over the last week: 17 per day
- Usual pace: too little history (under two weeks)
- Stars in the last hour (measured): 4

## Stars per day, last 9 days (oldest → newest, today is partial)

2026-09-20 … 2026-09-28: 0, 0, 16, 14, 2, 3, 10, 43, 0

## Spotted in now

- Top new repositories this week: #152

## More in this category

1. **Niko1221/Strata** — 7.0 · Early signal · Language models · C++ · +0 stars today, ≈ 218 by evening
   A C++ local inference engine that runs the 125B MoE model Qwen3.8-Flash-Next on a regular PC with one NVIDIA GPU (12-24 GB) and 64 GB RAM, exposing an OpenAI/Anthropic-compatible API on localhost.
   Full card: https://gitnova.dev/en/r/Niko1221/Strata.md
2. **ollaya-dev/ollaya** — 6.5 · Early signal · Language models · Rust · +0 stars today, ≈ 158 by evening
   A local runtime for decision models: pulls and serves classification and routing models behind a TypeSafe-compatible API. Like Ollama, but for models that return probabilities instead of text.
   Full card: https://gitnova.dev/en/r/ollaya-dev/ollaya.md
3. **deepfates/imp** — 6.3 · Early signal · Language models · Elixir · +0 stars today, ≈ 101 by evening
   A port of DSPy to the BEAM: declarative LM programs in Elixir with signatures, optimizers and agents running as OTP processes.
   Full card: https://gitnova.dev/en/r/deepfates/imp.md
4. **Mapika/decider** — 4.7 · Breakout · Language models · Python · +0 stars today, ≈ 218 by evening
   A language model that does not generate text: from a single forward pass it returns calibrated probabilities for typed questions (Choice, Score, Noul) about a given state. An open reproduction of the "System One" model class built on…
   Full card: https://gitnova.dev/en/r/Mapika/decider.md
5. **NVIDIA/Model-Optimizer** — 4.5 · Breakout · Language models · Python · +0 stars today, ≈ 91 by evening
   NVIDIA library for compressing and accelerating models: quantization, pruning, distillation, NAS and speculative decoding with export to TensorRT-LLM, vLLM, SGLang. For ML engineers preparing models for deployment.
   Full card: https://gitnova.dev/en/r/NVIDIA/Model-Optimizer.md

---

Magnitude (0–10) measures how fast and how unusually interest in a repository is growing right now. It is not a quality score.
Days are UTC. “So far today” is a fact; “expected by the end of the day” is a forecast.
Summaries and use cases are written by an LLM (DeepSeek V4.1 Flash) from the README and may be inaccurate: verify specific claims (benchmarks, speed, hardware) in the repository itself.
Data as of 2026-09-28 03:37 UTC, updated every 30 minutes.