MI

MinerU2.5 Pro 2604 1.2B

MineruGGUF by mradermacherUpdated 2026-04-21
Download on Hugging Face
Parameters494M
Context8K
Layers24
Architectureqwen2vl
Smallest quant0.0 GB
Quick answer

MinerU2.5 Pro 2604 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 25 quants, from 0.0 GB to 0.5 GB (Q6_K).

MinerU2.5 Pro 2604 1.2B – 0.494B parameter Qwen2VL document parsing model

MinerU2.5 Pro 2604 1.2B is a 0.494B parameter Qwen2VL model trained for PDF‑to‑Markdown conversion. It supports 8192 context tokens and is released under the apache‑2.0 license. The model is available in multiple GGUF quantizations.

Good at

  • PDF‑to‑Markdown conversion
  • Table and formula parsing
  • Cross‑page table merging

Limits

  • No mmproj vision support
  • Requires 8192 context tokens
  • License is apache‑2.0

Best for

  • Document digitization
  • Automated form extraction
  • Batch PDF processing

Who it’s for. Developers building document‑centric applications who need accurate table and formula extraction. The model is suitable for teams that can run GGUF files locally with llama.cpp.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 0.6 GB
Fits Get file →
IQ1_S0.3 GB 0.9 GB
Fits Get file →
IQ1_M0.3 GB 0.9 GB
Fits Get file →
IQ2_XXS0.3 GB 0.9 GB
Fits Get file →
IQ2_XS0.3 GB 0.9 GB
Fits Get file →
IQ2_S0.3 GB 0.9 GB
Fits Get file →
IQ2_M0.3 GB 0.9 GB
Fits Get file →
Q2_K_S0.3 GB 0.9 GB
Fits Get file →
IQ3_XXS0.3 GB 0.9 GB
Fits Get file →
Q3_K_S0.3 GB 0.9 GB
Fits Get file →
IQ3_S0.3 GB 0.9 GB
Fits Get file →
IQ3_XS0.3 GB 0.9 GB
Fits Get file →
Q2_K0.3 GB 0.9 GB
Fits Get file →
IQ3_M0.3 GB 0.9 GB
Fits Get file →
IQ4_XS0.3 GB 1.0 GB
Fits Get file →
IQ4_NL0.4 GB 1.0 GB
Fits Get file →
Q4_00.4 GB 1.0 GB
Fits Get file →
Q3_K_M0.4 GB 1.0 GB
Fits Get file →
Q3_K_L0.4 GB 1.0 GB
Fits Get file →
Q4_10.4 GB 1.0 GB
Fits Get file →
Q4_K_S0.4 GB 1.0 GB
Fits Get file →
Q4_K_M0.4 GB 1.0 GB
Fits Get file →
Q5_K_S0.4 GB 1.0 GB
Fits Get file →
Q5_K_M0.4 GB 1.0 GB
Fits Get file →
Q6_K0.5 GB 1.1 GB
Fits Get file →

For 8 GB VRAM, use IQ1_S, IQ1_M, IQ2_XXS, IQ2_XS, or IQ2_S – each file is 0.32–0.33 GB and needs about 0.9 GB memory at 8 k context. For 12 GB VRAM, choose Q4_K_S or Q4_K_M (0.39–0.40 GB, ~1 GB memory). For 16 GB VRAM, Q5_K_S or Q5_K_M (0.41–0.42 GB, ~1 GB memory) provide higher quality.

What GPU do you need for MinerU2.5 Pro 2604 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 Q6_K (0.5 GB file, about 1.1 GB in use).

Which MinerU2.5 Pro 2604 1.2B quant should you choose?

Q4_K_M is the usual starting point for MinerU2.5 Pro 2604 1.2B: it balances file size and quality well. Here it is a 0.4 GB file.

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 context8,192 tokens
KV cache (fp16)12 KB per token

Source

Quantized bymradermacher
FamilyMineru
Licenseapache-2.0
Downloads (HF)647
Last updated2026-04-21

Frequently asked questions about MinerU2.5 Pro 2604 1.2B

How much VRAM does MinerU2.5 Pro 2604 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 Pro 2604 1.2B on an 8 GB GPU?

Yes, with Q6_K: the 0.5 GB file needs about 1.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of MinerU2.5 Pro 2604 1.2B GGUF?

It depends on the quant: file is 0.0 GB, IQ1_S is 0.3 GB, IQ1_M is 0.3 GB, IQ2_XXS is 0.3 GB, IQ2_XS is 0.3 GB, IQ2_S is 0.3 GB and 19 more.

What context length does MinerU2.5 Pro 2604 1.2B support?

The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 0.1 GB at 8K and 0.1 GB at 8K.

Where can I download MinerU2.5 Pro 2604 1.2B GGUF?

The files are on Hugging Face in the mradermacher/MinerU2.5-Pro-2604-1.2B-i1-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 Pro 2604 1.2B use?

Hugging Face lists the license as apache-2.0. 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 Pro 2604 1.2B on 8 GB VRAM?

Yes, use IQ1_S, IQ1_M, IQ2_XXS, IQ2_XS, or IQ2_S quantizations. Each requires about 0.9 GB memory at 8192 context.

Does this model support image input?

No, the model does not include mmproj files and does not support image or vision inputs.

What license applies to this model?

The model is released under the apache‑2.0 license.

Other GGUFs of MinerU2.5-Pro-2604-1.2B

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Mineru models

All Mineru →

Other tiny models

All tiny models →