MegaCapybara

The fastest inference engine for Qwen3.8-27B on the NVIDIA RTX 5090: up to 500 tokens/s for one agent and up to 2,000 tokens/s for many, contexts up to 1M tokens, and a launcher that shows what every setting costs. Windows and Linux.

perkel666/MegaCapybara

View on GitHub ↗

The fastest inference engine for Qwen3.8-27B on the NVIDIA RTX 5090: up to 500 tokens/s for one agent and up to 2,000 tokens/s for many, contexts up to 1M tokens, and a launcher that shows what every setting costs. Windows and Linux.

MegaCapybara ranks 490th of 539 in Local Runtime / Inference Engine, last commit 17 days ago.

Star trajectory

18 days tracked
2026-11-0485 stars today2026-11-22
Momentum

- in 30d, below the Local Runtime / Inference Engine median of +1.9%.

Maintenance

Last commit 17 days ago, staler than the median of 6d.

How it compares in Local Runtime / Inference Engine

MegaCapybara
85
stars
- 30d
commit 17 days ago
Local Runtime / Inference Engine median
360
stars
+1.9% 30d
commit ~6d ago
Leader · ollama
187.8k
stars
+1.9% 30d
commit today

Ranked 490th of 539 by stars.

Ranked by shared tags, then keywords, then stars
  1. Alzeo is an open-source installer that turns an NVIDIA DGX Spark, or any GB10 machine (ASUS, Dell, HP, Lenovo…

    +36 (+15%) in 30d · Committed 2d ago · Python · MIT

    Shares Production Serving & Deployment, Local Runtime / Inference Engine, LLM Gateway & Routing, Inference Optimization

  2. Local proxy that learns your app's typed LLM decisions and answers them with a Laya head. Jev and OpenAI…

    +3 (+4.1%) in 30d · Committed 41d ago · Python · Apache-2.0

    Shares Local Runtime / Inference Engine, Inference Optimization, LLM Gateway & Routing, Production Serving & Deployment

  3. Run many AI agents at once on your Mac, up to 3x faster.

    +273 (+91%) in 30d · Committed today · Python · Apache-2.0

    Shares Local Runtime / Inference Engine, Production Serving & Deployment, Inference Optimization, LLM Gateway & Routing

  4. Run large AI models on your own PC: Qwen3.8-Flash-Next on Strata's engine, and GLM 5.3 Flash, DeepSeek V4…

    +962 (+243%) in 30d · Committed 3d ago · C++ · MIT

    Shares Local Runtime / Inference Engine, Inference Optimization, Production Serving & Deployment

  5. Xolotl: run DeepSeek-V4.1-Flash, all 552B, as a local coding agent on one gaming PC (RTX 4090 + 110 GB RAM)…

    +264 (+90%) in 30d · Committed today · C++ · MIT

    Shares Local Runtime / Inference Engine, Production Serving & Deployment, Inference Optimization

  6. run a 27b local ai on your gaming gpu, rtx 3060 and up, radeon rx 6600 and up in beta, 8gb or more, linux and…

    +31 (+19%) in 30d · Committed 35d ago · Python

    Shares Local Runtime / Inference Engine, Production Serving & Deployment, Inference Optimization

  7. Bonsai 2 27B: 262k context (trained max) on 12 GB, 54 to 97 tok/s decode, 2x prefill, q8_0 KV recipe, grammar…

    Committed yesterday · Python · Other license

    Shares Local Runtime / Inference Engine, Inference Optimization, Production Serving & Deployment

  8. Pure Rust + CUDA LLM inference engine — no PyTorch, OpenAI-compatible, serves Qwen3 to Kimi-K2

    +25 (+3.5%) in 30d · Committed yesterday · Rust · Apache-2.0

    Shares Production Serving & Deployment, Inference Optimization, Local Runtime / Inference Engine

  9. Inference engine for Intel devices. Serve LLMs, VLMs, Whisper, Kokoro-TTS, Embedding and Rerank models over…

    +10 (+1.8%) in 30d · Committed yesterday · Python · Apache-2.0

    Shares Local Runtime / Inference Engine, Production Serving & Deployment, Inference Optimization

  10. llama.cpp/ik_llama.cpp launcher: loads big MoE models across mismatched multi-GPU rigs by exact VRAM math.

    +2 (+0.7%) in 30d · Committed 2d ago · Go · MIT

    Shares Local Runtime / Inference Engine, Inference Optimization, Production Serving & Deployment

Language
-
License
MIT License
Contributors
1
Forks
1
Watchers
1
Open issues
6
Releases
12
Created
2026-10-03
Stars this week
+2

You've seen where MegaCapybara stands today.

Get the moves before everyone else: the 5 Local Runtime / Inference Engine repos climbing fastest, every Tuesday.

Free weekly digest. Double opt-in, unsubscribe anytime.

Maintain MegaCapybara?

Claim this page to add your own call-to-action.

Claim this page