QA

Qari OCR Merged Fp16

QariGGUF by mradermacherUpdated 2025-12-25
Download on Hugging Face
Parameters1.78B
Context32K
Layers28
Architectureqwen2vl
Smallest quant0.0 GB
Quick answer

Qari OCR Merged Fp16 needs about 1.9 GB of memory at Q4_K_M (a 1.1 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 1.5 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 0.9 GB.

Qari OCR Merged Fp16 – a 1.78B vision model for OCR tasks

Qari OCR Merged Fp16 is a 1.78B parameter vision model based on qwen2vl. It merges Qwen2-VL-2B-Instruct with the NAMAA-Space/Qari-OCR LoRA adapter. The model supports 32768 context tokens and is released under Apache‑2.0.

Good at

  • OCR on images
  • Vision‑to‑text generation
  • Multimodal instruction following

Limits

  • No vision support in non‑vision quant files
  • Requires 8k context for full performance
  • Large memory for higher quants

Best for

  • OCR in low‑resource environments
  • Document image summarization
  • Multimodal QA on scanned text

Who it’s for. Developers needing a lightweight OCR model for embedded or edge devices. Researchers working on multimodal OCR pipelines may also benefit from the merged architecture.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 0.7 GB
Fits Get file →
IQ1_S0.5 GB 1.2 GB
Fits Get file →
IQ1_M0.5 GB 1.3 GB
Fits Get file →
IQ2_XXS0.6 GB 1.3 GB
Fits Get file →
IQ2_XS0.6 GB 1.4 GB
Fits Get file →
IQ2_S0.7 GB 1.4 GB
Fits Get file →
IQ2_M0.7 GB 1.4 GB
Fits Get file →
Q2_K_S0.7 GB 1.5 GB
Fits Get file →
Q2_K0.8 GB 1.5 GB
Fits Get file →
IQ3_XXS0.8 GB 1.5 GB
Fits Get file →
IQ3_XS0.8 GB 1.6 GB
Fits Get file →
Q3_K_S0.9 GB 1.6 GB
Fits Get file →
IQ3_S0.9 GB 1.6 GB
Fits Get file →
IQ3_M0.9 GB 1.6 GB
Fits Get file →
Q3_K_M0.9 GB 1.7 GB
Fits Get file →
Q3_K_L1.0 GB 1.7 GB
Fits Get file →
IQ4_XS1.0 GB 1.8 GB
Fits Get file →
IQ4_NL1.1 GB 1.8 GB
Fits Get file →
Q4_01.1 GB 1.8 GB
Fits Get file →
Q4_K_S1.1 GB 1.8 GB
Fits Get file →
Q4_K_M1.1 GB 1.9 GB
Fits Get file →
Q4_11.2 GB 1.9 GB
Fits Get file →
Q5_K_S1.3 GB 2.0 GB
Fits Get file →
Q5_K_M1.3 GB 2.0 GB
Fits Get file →
Q6_K1.5 GB 2.2 GB
Fits Get file →

For 8 GB VRAM, use Q4_K_M (1.12 GB file, ~1.9 GB memory). For 4 GB VRAM, IQ1_S (0.51 GB file, ~1.2 GB memory) is recommended. If memory is limited to 2 GB, IQ1_M (0.54 GB file, ~1.3 GB memory) is the smallest viable option.

What GPU do you need for Qari OCR Merged Fp16?

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 (1.5 GB file, about 2.2 GB in use).

Which Qari OCR Merged Fp16 quant should you choose?

Q4_K_M is the usual starting point for Qari OCR Merged Fp16: it balances file size and quality well. Here it is a 1.1 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
Parameters1.78B
Layers28
Trained context32,768 tokens
KV cache (fp16)28 KB per token

Source

Quantized bymradermacher
FamilyQari
Licenseapache-2.0
Downloads (HF)580
Last updated2025-12-25

Frequently asked questions about Qari OCR Merged Fp16

How much VRAM does Qari OCR Merged Fp16 need?

About 1.9 GB at Q4_K_M with an 8K context window. That is the 1.1 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 Qari OCR Merged Fp16 on an 8 GB GPU?

Yes, with Q6_K: the 1.5 GB file needs about 2.2 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Qari OCR Merged Fp16 GGUF?

It depends on the quant: file is 0.0 GB, IQ1_S is 0.5 GB, IQ1_M is 0.5 GB, IQ2_XXS is 0.6 GB, IQ2_XS is 0.6 GB, IQ2_S is 0.7 GB and 19 more.

What context length does Qari OCR Merged Fp16 support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 0.2 GB at 8K and 0.9 GB at 32K.

Where can I download Qari OCR Merged Fp16 GGUF?

The files are on Hugging Face in the mradermacher/Qari-OCR-merged-fp16-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 Qari OCR Merged Fp16 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 Qari OCR Merged Fp16 on 8 GB VRAM?

Yes, the Q4_K_M quant uses about 1.9 GB memory at 8k context, fitting within 8 GB VRAM.

Does the model support vision tasks?

Yes, the model is a vision model and includes mmproj files in the static repository.

What license applies to this model?

The model is released under the Apache‑2.0 license.

Other GGUFs of Qari-OCR-merged-fp16

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Qari models

All Qari →

Other tiny models

All tiny models →