OP

OpenCaption 4B VL SFT v1.0

OpencaptionGGUF by prithivMLmodsUpdated 2026-07-25
Download on Hugging Face
Parameters4B
Context256K
Layers36
Architectureqwen3vl
Smallest quant1.9 GB
Quick answer

OpenCaption 4B VL SFT v1.0 needs about 4.2 GB of memory at Q4_K_M (a 2.5 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 14 quants, from 1.9 GB (Q3_K_S) to 16.1 GB (F32). Longer context needs more: at 32K tokens the KV cache alone adds about 4.8 GB.

OpenCaption 4B VL SFT v1.0 – detailed vision‑language captioning

OpenCaption 4B VL SFT v1.0 is a 4B parameter vision‑language model built on Qwen3‑VL. It is fine‑tuned for dense image captioning, producing rich, long‑form descriptions that capture scene composition, object relationships, and visual context. The model is released under the Apache‑2.0 license.

Good at

  • Dense image captioning
  • Fine‑grained visual description
  • Long‑form scene analysis

Limits

  • Experimental release – output quality may vary
  • No ground‑truth detection
  • Limited to image captioning tasks

Best for

  • Research on caption quality
  • Evaluating visual grounding
  • Local inference for captioning experiments

Who it’s for. Researchers and developers who need a compact vision‑language model for dense captioning and visual reasoning. The model is suitable for local deployment and experimentation, but may produce unexpected outputs in some scenarios.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q3_K_S1.9 GB 3.6 GB
Fits Get file →
Q3_K_M2.1 GB 3.8 GB
Fits Get file →
Q3_K_L2.2 GB 3.9 GB
Fits Get file →
Q4_02.4 GB 4.1 GB
Fits Get file →
Q4_K_S2.4 GB 4.1 GB
Fits Get file →
Q4_K_M2.5 GB 4.2 GB
Fits Get file →
Q5_02.8 GB 4.5 GB
Fits Get file →
Q5_K_S2.8 GB 4.5 GB
Fits Get file →
Q5_K_M2.9 GB 4.6 GB
Fits Get file →
Q6_K3.3 GB 5.0 GB
Fits Get file →
Q8_04.3 GB 6.0 GB
Fits Get file →
BF168.1 GB 9.8 GB
Too big Get file →
F168.1 GB 9.8 GB
Too big Get file →
F3216.1 GB 17.8 GB
Too big Get file →

For 8 GB VRAM, use Q4_0 (file size 2.37 GB, estimated 4.1 GB memory). For 12 GB VRAM, Q5_0 (2.82 GB, 4.5 GB memory) or Q5_K_M (2.89 GB, 4.6 GB memory) are suitable. For 16 GB VRAM, Q6_K (3.31 GB, 5 GB memory) or Q8_0 (4.28 GB, 6 GB memory) provide higher precision.

What GPU do you need for OpenCaption 4B VL SFT v1.0?

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 Q3_K_L (2.2 GB file, about 3.9 GB in use).
  • 6 GB VRAM: the best quant that fits is Q8_0 (4.3 GB file, about 6.0 GB in use).
  • 8 GB VRAM: the best quant that fits is Q8_0 (4.3 GB file, about 6.0 GB in use).
  • 12 GB VRAM: the best quant that fits is BF16 (8.1 GB file, about 9.8 GB in use).
  • 16 GB VRAM: the best quant that fits is BF16 (8.1 GB file, about 9.8 GB in use).
  • 24 GB VRAM: the best quant that fits is F32 (16.1 GB file, about 17.8 GB in use).

Which OpenCaption 4B VL SFT v1.0 quant should you choose?

Q4_K_M is the usual starting point for OpenCaption 4B VL SFT v1.0: it balances file size and quality well. Here it is a 2.5 GB file.

The Q8_0 file is 4.3 GB, about 1.7 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

If memory is tight, the smallest file is Q3_K_S at 1.9 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen3vl
Parameters4B
Layers36
Trained context262,144 tokens
KV cache (fp16)144 KB per token

Source

Quantized byprithivMLmods
Licenseapache-2.0
Downloads (HF)985
Last updated2026-07-25

Frequently asked questions about OpenCaption 4B VL SFT v1.0

How much VRAM does OpenCaption 4B VL SFT v1.0 need?

About 4.2 GB at Q4_K_M with an 8K context window. That is the 2.5 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 OpenCaption 4B VL SFT v1.0 on an 8 GB GPU?

Yes, with Q8_0: the 4.3 GB file needs about 6.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of OpenCaption 4B VL SFT v1.0 GGUF?

It depends on the quant: Q3_K_S is 1.9 GB, Q3_K_M is 2.1 GB, Q3_K_L is 2.2 GB, Q4_0 is 2.4 GB, Q4_K_S is 2.4 GB, Q4_K_M is 2.5 GB and 8 more.

What context length does OpenCaption 4B VL SFT v1.0 support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 1.2 GB at 8K and 4.8 GB at 32K.

Where can I download OpenCaption 4B VL SFT v1.0 GGUF?

The files are on Hugging Face in the prithivMLmods/OpenCaption-4B-VL-SFT-v1.0-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 OpenCaption 4B VL SFT v1.0 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 OpenCaption 4B VL SFT v1.0 on 8 GB VRAM?

Yes, the Q4_0 quant requires about 4.1 GB memory at 8 k context, which fits within 8 GB VRAM.

Does the model support text‑only inference?

No, the model is vision‑language and requires image input for captioning.

What license applies to this model?

The model is released under the Apache‑2.0 license.

Other GGUFs of OpenCaption-4B-VL-SFT-v1.0

Similar models

Browse all →

More from prithivMLmods

All by prithivMLmods →

More Opencaption models

All Opencaption →

Other small models

All small models →