DA

datalab-to/chandra-ocr-2

DatalabGGUF by kietnt0603Updated 2026-04-10
Download on Hugging Face
Parameters4.84B
Context256K
Layers32
Architectureqwen35
Smallest quant9.7 GB
Quick answer

datalab-to/chandra-ocr-2 needs about 11.3 GB of memory at BF16 (a 9.7 GB file) with an 8K context window, so it fits on a 12 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

datalab-to/chandra-ocr-2 is a 4.84B-parameter Datalab model in GGUF format, quantized by kietnt0603. Its trained context length is 256K tokens. The repository has 1 quant file, from 9.7 GB (BF16) to 9.7 GB (BF16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
BF169.7 GB 11.3 GB
Too big Get file →

What GPU do you need for datalab-to/chandra-ocr-2?

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: no quant fits at an 8K context.
  • 6 GB VRAM: no quant fits at an 8K context.
  • 8 GB VRAM: no quant fits at an 8K context.
  • 12 GB VRAM: the best quant that fits is BF16 (9.7 GB file, about 11.3 GB in use).

Which datalab-to/chandra-ocr-2 quant should you choose?

BF16 (9.7 GB) is the middle option in this repository. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen35
Parameters4.84B
Layers32
Trained context262,144 tokens
KV cache (fp16)128 KB per token

Source

Quantized bykietnt0603
FamilyDatalab
Licenseopenrail
Downloads (HF)12
Last updated2026-04-10

Frequently asked questions about datalab-to/chandra-ocr-2

How much VRAM does datalab-to/chandra-ocr-2 need?

About 11.3 GB at BF16 with an 8K context window. That is the 9.7 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 datalab-to/chandra-ocr-2 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 11.3 GB, so you would need a larger GPU or CPU offloading.

What is the file size of datalab-to/chandra-ocr-2 GGUF?

It depends on the quant: BF16 is 9.7 GB.

What context length does datalab-to/chandra-ocr-2 support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.3 GB at 32K.

Where can I download datalab-to/chandra-ocr-2 GGUF?

The files are on Hugging Face in the kietnt0603/chandra-ocr-2-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 datalab-to/chandra-ocr-2 use?

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

Similar models

Browse all →

More from kietnt0603

All by kietnt0603 →

Other small models

All small models →