KDL-Frontier-Parser-nano
A 1.2B-parameter open-weight document parsing model, packaged and orchestrated by KoreaDeep as the nano tier of the KDL Frontier Parser family.
ParseBench results
Measured 2026-06-10 with the official ParseBench harness, full set, single end-to-end pass (2,553 test cases, 0 inference failures):
| Dimension | Metric | Score |
|---|---|---|
| Overall (mean) | mean of 5 dimensions | 76.48 |
| Tables | grits_trm_composite | 84.56 |
| Visual Grounding / Layout | rule_pass_rate | 81.83 |
| Content Faithfulness | content_faithfulness | 86.63 |
| Semantic Formatting | normalized_text_score | 66.32 |
| Charts | chart_data_point | 63.08 |
Serving
vllm serve <this-repo> \
--served-model-name kdl-frontier-parser-nano \
--max-model-len 8192 \
--gpu-memory-utilization 0.85 \
--max-num-seqs 24 \
--trust-remote-code \
--limit-mm-per-prompt '{"image":1}'
Usage
This model is not a single-shot end-to-end parser. It runs as a pipeline: detect layout, crop each region, then call the model again per region with a task-specific prompt.
Prompts
Each task uses a fixed prompt (note the leading newline):
| Task | Prompt |
|---|---|
| Layout | \nLayout Detection: |
| Text | \nText Recognition: |
| Table | \nTable Recognition: |
| Formula | \nFormula Recognition: |
| Figure | \nImage Analysis: |
Table recognition returns OTSL. Other output formats are left to the caller.
Inference notes
- Serve with
--trust-remote-codeand--limit-mm-per-prompt '{"image":1}'(one image per request). - Set
enable_thinking=Falsein the chat template. - Pass
skip_special_tokens=Falsewhen decoding. - Greedy decoding (
temperature=0).
Feed page images, not PDFs. Chat UIs (e.g. open-webui) with free-form prompts will not work — use the prompts above.
Benchmark methodology
The ParseBench score is an end-to-end pipeline measurement — this model served via vLLM plus deterministic rule-based post-processing of model output — consistent with how all ParseBench providers are evaluated (every provider is a submitter-hosted endpoint). No other learned models, classifiers, or ensembles are involved: single model, single pass.
About
Built by KoreaDeep, a document-AI company. The larger KDL-Frontier-Parser-ultra is available through DEEP Agent.