All tasks / Models

Infinity-Parser2-Flash

infly's small open-weights document-parsing VLM, the 2B sibling of Infinity-Parser2-Pro.

  • infly
  • Open weights
  • Released 27 Feb 2026

Official page

Where it ranks

  • –
    Documents & OCR
    Models · Local · no result on this task’s benchmarks yet

Facts

Vendor
infly
Family
Infinity-Parser Flash
Released
27 Feb 2026
Weights
Open: download and run it yourself
License
Apache-2.0
Parameters
2.21B
GPU memory to run locally
~6 GB (Estimate, no official figure: BF16 weights ≈ 2.21 B × 2 GB + ~1.5 GB runtime overhead. Size is the Hugging Face safetensors total.)
Access
Free (open weights)
Last verified
19 Oct 2026

Price from huggingface.co, 19 Oct 2026.

Benchmark results

BenchmarkResultEntry on the leaderboardAs ofSource
ParseBench (models)73.3%Infinity-Parser2-Flash
Overall (mean of tables, charts, content faithfulness, semantic formatting, visual grounding) from leaderboard.csv in the ParseBench repo (last leaderboard commit 2026-10-09).
9 Oct 2026github.com

Where you can use it

No tracked tool lists this model yet; as open weights it runs in local runtimes.

Sources