# Wallawalla47/Infernix

> C++/CUDA single-GPU inference engine for Qwen models on RTX 50-series cards, with offloaded experts, prefix caching and OpenAI/Anthropic-compatible APIs. Aimed at running large Qwen checkpoints locally, including agentic coding workloads.

- Magnitude: 1.2 out of 10 — Cooling
- Stars: 104 total · +1 star measured 2026-10-13, 10:07–12:38 UTC, ≈ 3 by evening
- Star trust: star growth looks organic
- Category: Language models · Language: C++ · License: Apache-2.0 · Created: 2026-10-08 · Last push: 2026-10-12
- GitHub: https://github.com/Wallawalla47/Infernix · Page: https://gitnova.dev/en/r/Wallawalla47/Infernix

## Useful for

- Serve Qwen3.8-Flash-Next locally on a single RTX 5090 with experts offloaded to RAM and NVMe.
- Plug the server into Claude Code or Codex via the OpenAI/Anthropic-compatible endpoints.
- Constrain outputs to JSON Schema or GBNF grammars for structured tool calls.

## Why it’s here

- Star-counter measurements on 2026-10-13 (UTC), 10:07–12:38: 103 → 104 stars (+1). This is the change over that interval.
- Estimated end-of-day forecast: about +3 stars, using observed gains and the previous day.
- The repository is 5 days old and already has 104 stars. With less than two weeks of history, there's no usual pace to compare the spike against yet.
- Top new repositories this week: #188.

## 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: 14
- Issues and pull requests: 24
- Watchers: 2
- Average over the last week: 18 per day
- Usual pace: too little history (under two weeks)
- Stars in the last hour (measured): 0
- Latest release: windows-2026.10.11 (2026-10-11)

## Stars per day, last 6 days (oldest → newest, today is partial)

2026-10-08 … 2026-10-13: 9, 64, 14, 8, 8, 1

## Spotted in now

- Top new repositories this week: #188

## Similar by description

1. **Neroued/ninfer** — 2.4 · Steady · Language models · C++ · +17 stars measured 2026-10-13, 00:05–12:32 UTC, ≈ 32 by evening
   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.
   Full card: https://gitnova.dev/en/r/Neroued/ninfer.md
2. **mw00/project-maya** — 5.1 · Early signal · Language models · C++ · +52 stars measured 2026-10-13, 00:02–12:26 UTC, ≈ 109 by evening
   Local engine, server and dashboard to run the 321B MoE model GLM-5.3-Flash on one or two NVIDIA GPUs, offloading experts to RAM and NVMe.
   Full card: https://gitnova.dev/en/r/mw00/project-maya.md
3. **sybil-solutions/dsv41-flash-offload** — 0.0 · Steady · Language models · Python · +0 stars measured 2026-10-13, 00:11–12:42 UTC, ≈ 0 by evening
   Serves DeepSeek-V4.1-Flash (EXL3 3.0 bpw) on a single 24 GB RTX 3090 by offloading experts to DDR4 and NVMe, exposing an OpenAI-compatible API. Aimed at running a large MoE model locally on consumer hardware.
   Full card: https://gitnova.dev/en/r/sybil-solutions/dsv41-flash-offload.md
4. **FlashML-org/FreeToken** — 2.3 · Steady · Language models · Python · +18 stars measured 2026-10-13, 00:06–12:32 UTC, ≈ 36 by evening
   A Mixture-of-Experts inference engine for running frontier-scale open-weight MoE models (290B+) on consumer hardware — GPUs, CPUs, and host memory. Aimed at users who want to run frontier models locally.
   Full card: https://gitnova.dev/en/r/FlashML-org/FreeToken.md
5. **Niko1221/Strata** — 4.8 · Steady · Language models · C++ · +663 stars measured 2026-10-13, 00:02–12:26 UTC, ≈ 1,213 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

---

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 2026-10-13 12:43 UTC, updated every 30 minutes.