# argonautlabsai/deltafin

> A Rust fork of the Deltafin engine that runs the full 2.8T-parameter Kimi K3 MoE on Apple Silicon by streaming expert weights from four SSDs, with a benchmark package and ARGODRIVE tooling.

- Magnitude: 0.3 out of 10 — Quiet
- Stars: 95 total · +0 stars on 2026-09-25 (UTC), ≈ 0 by evening
- Star trust: star growth looks organic
- Category: Language models · Language: Rust · Created: 2026-09-08 · Last push: 2026-09-10
- GitHub: https://github.com/argonautlabsai/deltafin · Page: https://gitnova.dev/en/r/argonautlabsai/deltafin

## Useful for

- Run Kimi K3 locally on a 128 GB MacBook and measure decode throughput
- Reproduce the k3-public-bench benchmark and compare results across your drives
- Assess how the number of SSDs affects expert-streaming throughput

## Why it’s here

- The repository is 17 days old and already has 95 stars.
- Hacker News: “Kimi K3 (2.8T) at 1 token/s on a MacBook Pro, streamed from four SSDs” — 277 points, 17 days ago.

## 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: 0
- Issues and pull requests: 0
- Watchers: 0
- Average over the last week: 0 per day
- Usual pace: 4 per day

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

2026-09-30 … 2026-10-29: None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None

## Magnitude by day, last 13 days

09-13 1.0, 09-14 1.2, 09-15 1.2, 09-16 0.9, 09-17 0.4, 09-18 0.4, 09-19 0.5, 09-20 0.6, 09-21 0.2, 09-22 0.2, 09-23 0.4, 09-24 0.5, 09-25 0.5

## Hacker News

- Kimi K3 (2.8T) at 1 token/s on a MacBook Pro, streamed from four SSDs — 277 points, 155 comments: https://news.ycombinator.com/item?id=49616257

---

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 2026-09-25 20:10 UTC, updated every 30 minutes.