VI

VideoScore2

VideoscoreGGUF by mradermacherUpdated 2025-12-04
Download on Hugging Face
Parameters7.62B
Context125K
Layers28
Architectureqwen2vl
Smallest quant0.0 GB
Quick answer

VideoScore2 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 25 quants, from 0.0 GB to 6.3 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 1.9 GB.

VideoScore2 – a vision‑language model for video quality and alignment scoring

VideoScore2 is a 7.62‑billion‑parameter model built on the qwen2vl architecture. It evaluates visual quality, text‑to‑video alignment, and physical consistency, producing chain‑of‑thought rationales. The model is trained on 27,168 human‑annotated videos from the VideoFeedback2 dataset.

Good at

  • Video quality assessment
  • Text‑to‑video alignment scoring
  • Chain‑of‑thought reasoning

Limits

  • No vision support in the base GGUF files
  • Large VRAM requirement for higher‑quality quants
  • License is Apache‑2.0

Best for

  • Evaluating video content quality
  • Assessing alignment between video and text prompts
  • Generating detailed video analysis rationales

Who it’s for. Researchers and developers needing a detailed, interpretable video scoring system. The model is suitable for academic studies and production pipelines that require robust video evaluation metrics.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 1.0 GB
Fits Get file →
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 (1.9 GB, 2.9 GB memory) or IQ1_M (2.04 GB, 3 GB memory). With 12 GB VRAM, Q2_XS (2.47 GB, 3.4 GB memory) or Q3_K_M (3.81 GB, 4.8 GB memory) are recommended. Higher‑quality quants like Q4_K_M (4.68 GB, 5.7 GB memory) need 16 GB or more.

What GPU do you need for VideoScore2?

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 VideoScore2 quant should you choose?

Q4_K_M is the usual starting point for VideoScore2: it balances file size and quality well. Here it is a 4.7 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
Parameters7.62B
Layers28
Trained context128,000 tokens
KV cache (fp16)56 KB per token

Source

Quantized bymradermacher
Licenseapache-2.0
Downloads (HF)360
Last updated2025-12-04

Frequently asked questions about VideoScore2

How much VRAM does VideoScore2 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 VideoScore2 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 VideoScore2 GGUF?

It depends on the quant: file is 0.0 GB, 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 and 19 more.

What context length does VideoScore2 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 VideoScore2 GGUF?

The files are on Hugging Face in the mradermacher/VideoScore2-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 VideoScore2 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 VideoScore2 on 8 GB VRAM?

Yes, use IQ1_S or IQ1_M quant files; they require about 2.9–3 GB memory at 8 k context.

Does VideoScore2 support vision tasks?

Yes, it is a vision‑language model; the GGUF files include the necessary vision components.

What license applies to VideoScore2?

The model is released under the Apache‑2.0 license.

Other GGUFs of VideoScore2

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Videoscore models

All Videoscore →

Other small models

All small models →