# drumih/turbo-fieldfare

> A custom Swift + Metal runtime for running Gemma 4 26B-A4B on Apple Silicon Macs: keeps ~2 GB in memory and streams experts from SSD, so it works even on 8 GB RAM machines.

- Magnitude: 1.1 out of 10 — Steady
- Stars: 7,079 total · +0 stars measured 2026-10-29, 00:10–08:39 UTC, ≈ 3 by evening
- Star trust: star growth looks organic
- Category: Language models · Language: Swift · License: Apache-2.0 · Created: 2026-07-17 · Last push: 2026-10-26
- GitHub: https://github.com/drumih/turbo-fieldfare · Page: https://gitnova.dev/en/r/drumih/turbo-fieldfare

## Useful for

- Run a local Gemma chat on an 8 GB MacBook Air without the cloud
- Start a loopback OpenAI-compatible server to call the model from your scripts
- Install the model via the streaming repacker without storing the full checkpoint

## Why it’s here

- Star-counter measurements on 2026-10-29 (UTC), 00:10–08:39: 7079 → 7079 stars (+0). This is the change over that interval.
- Estimated end-of-day forecast: about +3 stars, using observed gains and the previous day.
- Top new repositories in the last 4 months: #99.

## 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: 458
- Issues and pull requests: 195
- Watchers: 36
- Average over the last week: 13 per day
- Usual pace: 10 per day
- Stars in the last hour (measured): 0
- Latest release: 0.9.4 (2026-10-26)

## Stars per day, last 30 days (oldest → newest, today is partial)

2026-09-30 … 2026-10-29: 8, 4, 2, 6, 5, 3, 7, 3, 4, 4, 6, 3, 10, 37, 9, 6, 3, 3, 6, 1, 33, 15, 9, 22, 16, 17, 9, 20, 7, 0

## Magnitude by day, last 14 days

10-16 1.7, 10-17 1.3, 10-18 1.5, 10-19 1.4, 10-20 1.9, 10-21 2.4, 10-22 2.0, 10-23 1.9, 10-24 2.3, 10-25 2.1, 10-26 2.1, 10-27 1.8, 10-28 2.1, 10-29 1.1

## Spotted in now

- Top new repositories in the last 4 months: #99

## Similar by description

1. **trymirai/uzu** — 3.4 · Breakout · Language models · Rust · +16 stars measured 2026-10-29, 00:03–08:32 UTC, ≈ 63 by evening
   A high-performance AI model inference engine written in Rust with APIs for Rust, Python, Swift, and TypeScript. It lets you run LLMs locally inside your app with zero latency and no inference costs.
   Full card: https://gitnova.dev/en/r/trymirai/uzu.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 2026-10-29 08:42 UTC, updated every 30 minutes.