# sqliteai/warp

> An embeddable dependency-free C inference engine that runs huge MoE models (Kimi K3, DeepSeek-V4.1-Flash, GLM-5.3-Flash) on consumer hardware by streaming activated experts from NVMe and using spare RAM as a bounded expert cache.

- Magnitude: 0.6 out of 10 — Quiet
- Stars: 2,467 total · +1 star on 2026-10-02 (UTC), ≈ 2 by evening
- Star trust: star growth looks organic
- Category: Language models · Language: C · License: Apache-2.0 · Created: 2026-07-28 · Last push: 2026-09-18
- GitHub: https://github.com/sqliteai/warp · Homepage: https://sqlite.ai · Page: https://gitnova.dev/en/r/sqliteai/warp

## Useful for

- Run Kimi K3 on a 64 GB MacBook Pro with weights on SSD and experts cached in RAM
- Serve DeepSeek-V4.1-Flash or GLM-5.3-Flash locally without cloud on a low-memory machine
- Tune num_experts_per_token in the container manifest to trade quality for decode speed

## Why it’s here

- 1 star so far today, about 2 expected by the end of the day.
- Hacker News: “Show HN: Warp – Run DeepSeek v4.1 Flash with 5 GB of RAM at 3.77 tok/s” — 16 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: 187
- Issues and pull requests: 74
- Watchers: 9
- Average over the last week: 3 per day
- Usual pace: 6 per day
- Latest release: v0.8.1 (2026-09-18)

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

2026-10-04 … 2026-11-02: 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 14 days

09-19 1.4, 09-20 1.0, 09-21 1.1, 09-22 1.4, 09-23 0.7, 09-24 1.1, 09-25 0.8, 09-26 1.0, 09-27 0.8, 09-28 0.9, 09-29 0.9, 09-30 0.9, 10-01 0.8, 10-02 0.7

## Hacker News

- Show HN: Warp – Run DeepSeek v4.1 Flash with 5 GB of RAM at 3.77 tok/s — 16 points, 6 comments: https://news.ycombinator.com/item?id=49714036

---

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 2026-10-02 15:53 UTC, updated every 30 minutes.