QuixiAI Open-Sources embeddinggemma.c: A Blazing Fast Cross-Platform Embedding Inference Engine
QuixiAI · x · 2026-07-21
QuixiAI has released embeddinggemma.c, a cross-platform embedding inference engine written in pure C, emphasizing extreme speed and the ability to run anywhere.
Key Features:
- Hardware Acceleration: Provides optimized kernels for CPU, Metal, CUDA, ROCm, and SYCL.
- Model Support: Currently supports the embeddinggemma-300M-qat-q40-GGUF model (2k context).
- Flexible Dimensions: Supports Matryoshka embeddings at 768, 512, 256, and 128 dims.
- Usability: Offers a standard HTTP API.
Related event: QuixiAI Open-Sources Cross-Platform C Language Embedding Engine(2 posts)→
More from Infra
- AI Infra Meme: While Countries Need TW-Scale Power for Datacenters, People Argue About Lightbulbs — mgostIH · 2026-10-27
- Legora runs 2,000 parallel agent evals on Modal Sandboxes for legal AI — blelbach · 2026-10-27
- Cloud release velocity scores: AWS 95, Azure 90, Google Cloud 82 — DavidLinthicum · 2026-10-27
- Selling a 5090 to scale local inference: one business weighs 5 hardware paths — Anarchaotic · 2026-10-27
- AWS tutorial: fleet-wide edge CV model lifecycle with SageMaker SDK v3, ~$0.07 per run — AWS ML Blog · 2026-10-27
- Qwen3.8-27B hits 40 tok/s on Jetson Thor with INT4 + MTP, accuracy beats FP16 — No-Dragonfly6246 · 2026-10-27