Model reference · open weights
NuMarkdown-Thinking is an open-weight language model from numind, listed in the AxForge catalogue. AxForge can bring it up on EU-owned hardware for you on request — with the licence handled where one is required.
About
🖥️ <a href="https://nuextract.ai/"API / Platform</a   |   🗣️ <a href="https://discord.gg/3tsEtJNCDe"Discord</a   |   🔗 <a href="https://github.com/numindai/NuMarkdown"GitHub</a   |   🤗 <a href="https://huggingface.co/spaces/numind/NuMarkdown-8b-Thinking"Demo</a Reasoning comes to OCR 🧠✨📄🤘 NuMarkdown-8B-Thinking is the first reasoning OCR VLM. It is specifically trained to convert documents into clean Markdown files, well suited for RAG applications. It generates thinking tokens to figure out the layout of the document before generating the Markdown file. It is particularly good at understanding documents with weird layouts and complex tables. The number of thinking tokens can vary from 20% to 500% of the final answer, depending on the task difficulty. NuMarkdown-8B-Thinking is a fine-tune of Qwen 2.5-VL-7B on synthetic Doc → Reasoning → Markdown examples, followed by an RL phase (GRPO) with a layout-centric reward. Try it out in the 🤗 space! Results NuMarkdown-8B-Thinking is outperforming generic non-reasoning models like GPT-4o and specialized OCR models like OCRFlux. It is competitive against large reasoning closed-source models like Gemini 2.5. Arena ranking against popular alternatives (using trueskill-2 ranking system, with around 500 model-anonymized votes): We plan to realease a markdown arena, similar to llmArena, for complex document-to-markdown tasks to provide a tool to evaluate different solutions. Win/Draw/Lose-rate against others models (image-only): Training 1. SFT: Single epoch supervised fine-tuning on synthetic reasoning traces generated from public PDFs. 2. RL (GRPO): RL phase using a layout-centric reward with difficult image examples. Example: Quick start: vLLM: 🤗 Transformers:
Summarised from the published model card. Read the full card on the HuggingFace links below.
Specifications
| Maker | numind |
|---|---|
| Type | Language models |
| Parameters (lead) | 8.3B |
| Context | 125k tokens |
| Variants | 1 |
| Runs with | transformers |
| Based on | Qwen/Qwen2.5-VL-7B-Instruct |
| Released | 2025-07-29 |
| Popularity | 312k downloads / month |
| Likes | 492 |
| Licence | Open weights |
How it works
Variants
Open weights ship in several sizes and precisions. One page, all the variants — pick the one that fits your GPU. VRAM figures are estimates from model size.
| Variant | Params | Precision | VRAM | Fits 16 GB | Weights |
|---|---|---|---|---|---|
| NuMarkdown-8B-Thinking | 8.3B | BF16 | ~19.1 GB | ✓ | Weights ↗ |
Using it via the API
Once AxForge deploys numarkdown-thinking for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (numarkdown-thinking below is illustrative; you get the exact model name on deployment.)
$ curl -sS https://api.axforge.ai/v1/chat/completions \
-H "Authorization: Bearer $AXFORGE_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"numarkdown-thinking","messages":[{"role":"user","content":"Hello"}]}'
Details
Tags
Licence
Open weights under mit — commercial use is permitted. Deploy it on AxForge EU hardware on request. Read the licence ↗