MI

MinerU2.5-2509-1.2B

MineruGGUF by MungertUpdated 2025-10-20
Download on Hugging Face
Parameters494M
Context16K
Layers24
Architectureqwen2vl
Smallest quant0.0 GB
Quick answer

MinerU2.5-2509-1.2B needs about 1.0 GB of memory at Q4_K_M (a 0.4 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 19 quants, from 0.0 GB to 1.0 GB (BF16).

MinerU2.5-2509-1.2B: 1.2B‑parameter vision‑language model for document parsing

MinerU2.5-2509-1.2B is a 1.2B‑parameter vision‑language model designed for efficient high‑resolution document parsing. It uses a two‑stage strategy: global layout analysis on downsampled images followed by fine‑grained content recognition on native‑resolution crops.

Good at

  • Global layout analysis
  • Fine‑grained content recognition
  • High‑resolution document parsing

Limits

  • No vision support beyond document images
  • Requires 8‑k context for full functionality
  • AGPL‑3.0 license

Best for

  • Document OCR
  • Table extraction
  • Formula parsing

Who it’s for. Developers building document processing pipelines or researchers needing a lightweight vision‑language model for structured document analysis. The model is suitable for applications that require accurate layout, text, formula, and table extraction.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 0.6 GB
Fits Get file →
IQ4_NL0.3 GB 0.9 GB
Fits Get file →
IQ3_XS0.3 GB 0.9 GB
Fits Get file →
IQ3_XXS0.3 GB 0.9 GB
Fits Get file →
IQ4_XS0.3 GB 0.9 GB
Fits Get file →
Q3_K_S0.3 GB 0.9 GB
Fits Get file →
IQ3_M0.3 GB 0.9 GB
Fits Get file →
Q3_K_M0.3 GB 0.9 GB
Fits Get file →
Q4_10.3 GB 0.9 GB
Fits Get file →
Q4_K_S0.3 GB 0.9 GB
Fits Get file →
Q4_00.4 GB 1.0 GB
Fits Get file →
Q4_K_M0.4 GB 1.0 GB
Fits Get file →
Q5_00.4 GB 1.0 GB
Fits Get file →
Q5_10.4 GB 1.0 GB
Fits Get file →
Q5_K_M0.4 GB 1.0 GB
Fits Get file →
Q6_K_M0.5 GB 1.1 GB
Fits Get file →
Q8_00.5 GB 1.1 GB
Fits Get file →
F160.8 GB 1.4 GB
Fits Get file →
BF161.0 GB 1.6 GB
Fits Get file →

For 8‑GB VRAM, use IQ4_NL (0.28 GB) or Q4_0 (0.35 GB). For 12‑GB VRAM, Q4_K_M (0.39 GB) or Q5_0 (0.4 GB) provide higher precision. For 16‑GB VRAM, Q6_K_M (0.51 GB) or Q8_0 (0.53 GB) offer the best trade‑off between size and performance. Estimates are approximate.

What GPU do you need for MinerU2.5-2509-1.2B?

These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.

  • 4 GB VRAM: the best quant that fits is BF16 (1.0 GB file, about 1.6 GB in use).

Which MinerU2.5-2509-1.2B quant should you choose?

Q4_K_M is the usual starting point for MinerU2.5-2509-1.2B: it balances file size and quality well. Here it is a 0.4 GB file.

The Q8_0 file is 0.5 GB, about 1.3 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

If memory is tight, the smallest file is the first one in the table at 0.0 GB, with the quality trade-offs that come with fewer bits.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen2vl
Parameters494M
Layers24
Trained context16,384 tokens
KV cache (fp16)12 KB per token

Source

Quantized byMungert
FamilyMineru
Licenseagpl-3.0
Downloads (HF)1,362
Last updated2025-10-20

Frequently asked questions about MinerU2.5-2509-1.2B

How much VRAM does MinerU2.5-2509-1.2B need?

About 1.0 GB at Q4_K_M with an 8K context window. That is the 0.4 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.

Can I run MinerU2.5-2509-1.2B on an 8 GB GPU?

Yes, with BF16: the 1.0 GB file needs about 1.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of MinerU2.5-2509-1.2B GGUF?

It depends on the quant: file is 0.0 GB, IQ4_NL is 0.3 GB, IQ3_XS is 0.3 GB, IQ3_XXS is 0.3 GB, IQ4_XS is 0.3 GB, Q3_K_S is 0.3 GB and 13 more.

What context length does MinerU2.5-2509-1.2B support?

The GGUF header lists a trained context length of 16,384 tokens (16K). The KV cache grows with the context you use: about 0.1 GB at 8K and 0.2 GB at 16K.

Where can I download MinerU2.5-2509-1.2B GGUF?

The files are on Hugging Face in the Mungert/MinerU2.5-2509-1.2B-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does MinerU2.5-2509-1.2B use?

Hugging Face lists the license as agpl-3.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Can I run MinerU2.5-2509-1.2B on 8 GB VRAM?

Yes, use a quantized file such as IQ4_NL or Q4_0, which are under 0.4 GB and require less than 1 GB of VRAM at 8‑k context.

What context length does the model support?

The model was trained with 16384 tokens and supports up to that context length.

Does the model support image input?

Yes, it is a vision‑language model and can process document images for layout and content extraction.

Similar models

Browse all →

More from Mungert

All by Mungert →

More Mineru models

All Mineru →

Other tiny models

All tiny models →