GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
Carlosian
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Run this model inference with full control and performance in your environment.
Model Details
Model Provider
Carlosian
Model Tree
Qwen/Qwen3-VL-4B-Instruct
Input Modalities
Output Modalities
Supported Functionality
Training used OCR labels generated or adjudicated by Qwen3-VL-235B-A22B-Instruct as a teacher for the 4B student. In the project's page-level OCR comparison, the resulting 4B Trithemius model matched the 235B teacher on 86% of evaluated pages.
This is a project-specific OCR agreement rate—not character error rate, not a claim of general vision-language parity, and not evidence that the 4B model matches the 235B teacher outside this historical-OCR task.
The model weights are split across two safetensors shards and mapped by model.safetensors.index.json. The repository also includes the model configuration, processor configuration, tokenizer, chat template, and generation configuration required for inference.
This is an OCR/transcription model, not an English translation model. Supply one page image at a time and request transcription rather than commentary, modernization, or reconstruction.
Example instruction:
text
Transcribe this historical printed page faithfully. Preserve line and paragraphstructure, headings, names, dates, abbreviations, and visible marginal ortabular material. Do not translate or silently repair uncertain text. Mark textthat cannot be read reliably as [unclear]. Return only the transcription.
For dense pages, splitting the image into overlapping regions is safer than simply increasing the generation limit. A larger token cap can extend a repetition loop instead of recovering missing text.
The model supplied the Latin OCR witness for 27 Trithemius 4B editions published in the Trithemius Corpus. Those are the project's recommended English reading editions where available. Their English was produced separately through a translation, assessment, and full-work remediation pipeline.
The model card deliberately separates OCR quality from downstream translation quality. Direct inspection of 3,902 pages from eight difficult works found body-page OCR to be generally clean, with total degenerate-page rates of approximately 0.2–3.3% per audited work. The larger historical failure cluster came from an unguarded downstream translation run that could drift to neighboring pages; that translation failure is not a benchmark for this OCR model.
See the corpus Methodology for the complete OCR, translation, grading, and remediation record.
[unclear] when promptedTraining examples were derived from public-domain institutional page scans and transcription pairs assembled during the Trithemius Corpus project. Source code, methodology, work metadata, provenance records, and published OCR witnesses are available in the Trithemius Corpus repository.
The released model should not be taken to imply that libraries or scan providers endorsed the fine-tune. Source institutions retain attribution for their digitized holdings; the underlying historical works are public domain.
Released under the Apache License 2.0, consistent with the Qwen base model. Users remain responsible for complying with licenses or terms attached to images they process.
text
Fabin, Ian Carlos (2026). Qwen3-VL-4B Trithemius OCR. Hugging Face model repository.https://huggingface.co/Carlosian/Qwen3-VL-4B-Trithemius
Developed and assembled by Ian Carlos Fabin (Carlosian).