# Neroued/ninfer

> NInfer is a from-scratch C++/CUDA inference engine for Qwen3.5 Dense and MoE models on a single NVIDIA RTX 5090. It serves text, image, and video prompts via a local CLI or OpenAI-/Anthropic-compatible HTTP APIs.

- Magnitude: 1.8 out of 10 — Steady
- Stars: 3,041 total · +7 stars measured 2026-10-16, 00:11–11:28 UTC, ≈ 17 by evening
- Star trust: star growth looks organic
- Category: Language models · Language: C++ · License: Apache-2.0 · Created: 2026-06-26 · Last push: 2026-10-16
- GitHub: https://github.com/Neroued/ninfer · Page: https://gitnova.dev/en/r/Neroued/ninfer

## Useful for

- Start a local Qwen3.8-27B inference server with two concurrent requests and a 240,000-token context.
- Send an OpenAI-compatible request to the local model via curl for text generation.
- Run a one-shot CLI request with an image or video using the --vision flag.

## Why it’s here

- Star-counter measurements on 2026-10-16 (UTC), 00:11–11:28: 3034 → 3041 stars (+7). This is the change over that interval.
- Estimated end-of-day forecast: about +17 stars, using observed gains and the previous day.

## 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: 600
- Issues and pull requests: 398
- Watchers: 26
- Average over the last week: 27 per day
- Usual pace: 38 per day

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

2026-10-04 … 2026-11-02: 37, 34, 39, 36, 38, 27, 27, 40, 31, 23, 29, 24, 0, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None

## Magnitude by day, last 14 days

09-29 2.0, 10-04 0.0, 10-05 2.1, 10-06 2.5, 10-07 2.6, 10-08 2.7, 10-09 2.5, 10-10 2.4, 10-11 2.3, 10-12 2.6, 10-13 2.4, 10-14 2.3, 10-15 2.0, 10-16 1.9

---

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 2026-10-16 11:35 UTC, updated every 30 minutes.