LiteParse Tops Document Parsing Benchmarks At 3ms Per Page

Original post

LiteParse is unreasonably good for document parsing

✅ It is the fastest document parsing tool out there - average parse time per page is 3ms ⚡️⚡️ ✅ Now that we support markdown, it tops opendataloader-bench, OlmOCR-bench, and ParseBench in terms of accuracy ✅ It supports 50+ other document formats ✅ It even gives you basic bounding boxes that your coding agent can stitch together

Even if you need deeper VLM-enabled parsing (e.g. LlamaParse), there's no reason you shouldn't be using this as a first pass for everything.

https://github.com/run-llama/liteparse

LlamaIndex 🦙@llama_index

We built LiteParse, the fastest document parsing solution on the planet and made it open source.

And it just hit 10k github stars. 🦙 Fast to run. Fast to love.

Thanks for building with us. If you haven't tried it already, repo at: https://github.com/run-llama/liteparse?utm_medium=socials&utm_source=twitter_li&utm_campaign=2026-06

9:22 AM · Jun 27, 2026 · 5.2K Views

VIEWS184RETWEETS2

Afiz ⚡️@itsafiz

It really isn't an exaggeration!

LiteParse clocks in at an average of 3ms per page for a reason: it skips the heavy AI processing and cloud overhead entirely.

Here is exactly how it pulls off that kind of speed:

- Purely Local & Lightweight: It runs completely on your machine (built on a Rust core with a native PDFium C library) rather than sending files over the network to a distant cloud server.

- No Heavy VLMs/GPUs: Instead of using an expensive, slow Vision-Language Model to "read" the page layout, it relies on fast, deterministic layout heuristics and projects text onto a spatial grid.

- Selective OCR: It only activates OCR (using lightweight engines like Tesseract) when it encounters scanned pages or embedded images; otherwise, it extracts native text layers directly.

Because it reconstructs headings, tables, and lists into structured Markdown almost instantly, it's a massive win for real-time RAG pipelines and coding agents that need a quick first pass over documents.

Quick demo 🧵👇

Jerry Liu@jerryjliu0

LiteParse is unreasonably good for document parsing

Even if you need deeper VLM-enabled parsing (e.g. LlamaParse), there's no reason you shouldn't be using this as a first pass for everything.

https://github.com/run-llama/liteparse

3h1.7K85

Afiz ⚡️@itsafiz

Here is the demo:

https://x.com/i/broadcasts/1DGLddArpbQGm

3h37

Hira@Hiraweb3

@jerryjliu0 Speed demon with brains this changes everything.

3h29

Sebastian Sosa@Sebasti54919704

@jerryjliu0 your note that olmOCR-bench's rule checks sometimes disagree with each other is the part i keep thinking about. when the benchmark itself is noisy, how do you tell a parser is genuinely better vs just better at fitting the benchmark's quirks?

3h16

tsunami_crypto@ls_brd

@jerryjliu0 3ms per page is actually insane for production pipelines

how are you doing the image chunking that fast?

3h16

Strata@ChainZenit

@jerryjliu0 3ms per page is actually insane, how did you get it there?

3h10

V0LYX@0xV0LYX

@jerryjliu0 the 3ms per page is actually wild. docs at scale just changed completely

3h10