CO

coreOCR 7B 050325 Preview

CoreocrGGUF by mradermacherUpdated 2025-07-11
Download on Hugging Face
Parameters7.62B
Context32K
Layers28
Architectureqwen2vl
Smallest quant1.9 GB
Quick answer

coreOCR 7B 050325 Preview needs about 5.7 GB of memory at Q4_K_M (a 4.7 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 24 quants, from 1.9 GB (IQ1_S) to 6.3 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 1.9 GB.

coreOCR 7B 050325 Preview – Vision‑language OCR model

coreOCR 7B 050325 Preview is a fine‑tuned Qwen2‑VL‑7B model for document‑level OCR and long‑context vision‑language tasks. It supports image‑to‑text conversion with LaTeX output and multi‑page document parsing.

Good at

  • Document OCR from scanned PDFs
  • Long‑context vision‑language reasoning
  • Math LaTeX generation

Limits

  • No real‑time edge inference
  • Performance drops on very low‑resolution images
  • Not optimized for high‑speed video streams

Best for

  • OCR of invoices and forms
  • Extracting structured data from research papers
  • Automated math problem solving

Who it’s for. Developers building document digitization pipelines, researchers needing OCR with math support, and teams integrating visual commands into AI agents. The model is suitable for server‑side inference where memory resources are available.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S1.9 GB 2.9 GB
Fits Get file →
IQ1_M2.0 GB 3.0 GB
Fits Get file →
IQ2_XXS2.3 GB 3.2 GB
Fits Get file →
IQ2_XS2.5 GB 3.4 GB
Fits Get file →
IQ2_S2.6 GB 3.6 GB
Fits Get file →
IQ2_M2.8 GB 3.8 GB
Fits Get file →
Q2_K_S2.8 GB 3.8 GB
Fits Get file →
Q2_K3.0 GB 4.0 GB
Fits Get file →
IQ3_XXS3.1 GB 4.1 GB
Fits Get file →
IQ3_XS3.3 GB 4.3 GB
Fits Get file →
Q3_K_S3.5 GB 4.5 GB
Fits Get file →
IQ3_S3.5 GB 4.5 GB
Fits Get file →
IQ3_M3.6 GB 4.5 GB
Fits Get file →
Q3_K_M3.8 GB 4.8 GB
Fits Get file →
Q3_K_L4.1 GB 5.1 GB
Fits Get file →
IQ4_XS4.2 GB 5.2 GB
Fits Get file →
IQ4_NL4.4 GB 5.4 GB
Fits Get file →
Q4_04.4 GB 5.4 GB
Fits Get file →
Q4_K_S4.5 GB 5.4 GB
Fits Get file →
Q4_K_M4.7 GB 5.7 GB
Fits Get file →
Q4_14.9 GB 5.8 GB
Fits Get file →
Q5_K_S5.3 GB 6.3 GB
Fits Get file →
Q5_K_M5.4 GB 6.4 GB
Fits Get file →
Q6_K6.3 GB 7.2 GB
Tight Get file →

For 8 GB VRAM, use IQ1_S (file size 1.9 GB, memory 2.9 GB) or IQ1_M (2.04 GB, 3 GB). With 12 GB VRAM, IQ2_S (2.6 GB, 3.6 GB) or Q2_K (3.02 GB, 4 GB) provide a good balance of size and performance. Larger models such as Q5_K_M (5.44 GB, 6.4 GB) require 16 GB or more.

What GPU do you need for coreOCR 7B 050325 Preview?

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 Q2_K (3.0 GB file, about 4.0 GB in use).
  • 6 GB VRAM: the best quant that fits is Q4_1 (4.9 GB file, about 5.8 GB in use).
  • 8 GB VRAM: the best quant that fits is Q6_K (6.3 GB file, about 7.2 GB in use).

Which coreOCR 7B 050325 Preview quant should you choose?

Q4_K_M is the usual starting point for coreOCR 7B 050325 Preview: it balances file size and quality well. Here it is a 4.7 GB file.

If memory is tight, the smallest file is IQ1_S at 1.9 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen2vl
Parameters7.62B
Layers28
Trained context32,768 tokens
KV cache (fp16)56 KB per token

Source

Quantized bymradermacher
FamilyCoreocr
Licenseapache-2.0
Downloads (HF)755
Last updated2025-07-11

Frequently asked questions about coreOCR 7B 050325 Preview

How much VRAM does coreOCR 7B 050325 Preview need?

About 5.7 GB at Q4_K_M with an 8K context window. That is the 4.7 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 coreOCR 7B 050325 Preview on an 8 GB GPU?

Yes, with Q6_K: the 6.3 GB file needs about 7.2 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of coreOCR 7B 050325 Preview GGUF?

It depends on the quant: IQ1_S is 1.9 GB, IQ1_M is 2.0 GB, IQ2_XXS is 2.3 GB, IQ2_XS is 2.5 GB, IQ2_S is 2.6 GB, IQ2_M is 2.8 GB and 18 more.

What context length does coreOCR 7B 050325 Preview support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 0.5 GB at 8K and 1.9 GB at 32K.

Where can I download coreOCR 7B 050325 Preview GGUF?

The files are on Hugging Face in the mradermacher/coreOCR-7B-050325-preview-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 coreOCR 7B 050325 Preview 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 coreOCR 7B 050325 Preview on 8 GB VRAM?

Yes, using the IQ1_S or IQ1_M quantization will fit within 8 GB VRAM, with estimated memory usage of 2.9 GB or 3 GB at 8 k context.

Does this model support video input?

The model can process video frames up to 20+ minutes, but it is not optimized for real‑time video inference on constrained devices.

Is the model multilingual?

It supports multiple scripts, but performance on low‑resource or rare scripts may vary.

Other GGUFs of coreOCR-7B-050325-preview

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Coreocr models

All Coreocr →

Other small models

All small models →