KI

Kiel 2 VQA

KielGGUF by kiel2Updated 2026-09-27
Download on Hugging Face
Parameters7.6B
Context125K
Layers28
Architectureqwen2vl
Smallest quant4.7 GB
Quick answer

Kiel 2 VQA 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 2 quants, from 4.7 GB (Q4_K_M) to 15.2 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 1.9 GB.

Kiel 2 VQA – multimodal vision‑language model for visual question answering

Kiel 2 VQA is a 7.6 billion‑parameter multimodal model based on Qwen2VL. It is fine‑tuned for visual question answering, document and chart parsing, OCR, and spatial localization. The model is released under Apache‑2.0.

Good at

  • Visual question answering
  • Document and chart parsing
  • OCR and spatial localization

Limits

  • No vision support beyond images
  • Requires 8 k context for full functionality
  • Large memory footprint for higher precision

Best for

  • Answering image‑based questions
  • Extracting structured data from invoices
  • Analyzing complex charts

Who it’s for. Developers building multimodal chatbots or document‑analysis tools that need accurate visual understanding. The model is suitable for applications requiring high‑precision image interpretation and structured data extraction.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M4.7 GB 5.7 GB
Fits Get file →
F1615.2 GB 16.2 GB
Too big Get file →

For 8 GB VRAM, use the Q4_K_M quantized file (4.68 GB, ~5.7 GB memory at 8k context). If more memory is available, the F16 quantized file (15.24 GB, ~16.2 GB memory at 8k context) provides higher precision.

What GPU do you need for Kiel 2 VQA?

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: the best quant that fits is Q4_K_M (4.7 GB file, about 5.7 GB in use).
  • 8 GB VRAM: the best quant that fits is Q4_K_M (4.7 GB file, about 5.7 GB in use).
  • 12 GB VRAM: the best quant that fits is Q4_K_M (4.7 GB file, about 5.7 GB in use).
  • 16 GB VRAM: the best quant that fits is Q4_K_M (4.7 GB file, about 5.7 GB in use).
  • 24 GB VRAM: the best quant that fits is F16 (15.2 GB file, about 16.2 GB in use).

Which Kiel 2 VQA quant should you choose?

Q4_K_M is the usual starting point for Kiel 2 VQA: it balances file size and quality well. Here it is a 4.7 GB file.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen2vl
Parameters7.6B
Layers28
Trained context128,000 tokens
KV cache (fp16)56 KB per token

Source

Quantized bykiel2
FamilyKiel
Licenseapache-2.0
Downloads (HF)2,231
Last updated2026-09-27

Frequently asked questions about Kiel 2 VQA

How much VRAM does Kiel 2 VQA 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 Kiel 2 VQA on an 8 GB GPU?

Yes, with Q4_K_M: the 4.7 GB file needs about 5.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Kiel 2 VQA GGUF?

It depends on the quant: Q4_K_M is 4.7 GB, F16 is 15.2 GB.

What context length does Kiel 2 VQA support?

The GGUF header lists a trained context length of 128,000 tokens (125K). 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 Kiel 2 VQA GGUF?

The files are on Hugging Face in the kiel2/Kiel-2-VQA repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does Kiel 2 VQA 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 Kiel 2 VQA on 8 GB VRAM?

Yes, the Q4_K_M quantized model requires about 5.7 GB of VRAM at 8k context, fitting within an 8 GB budget.

Does the model support vision tasks beyond image classification?

Yes, it is designed for visual question answering, document parsing, OCR, and spatial localization.

Similar models

Browse all →

More from kiel2

All by kiel2 →

More Kiel models

All Kiel →

Other small models

All small models →