VI

Video SALMONN 2 Pro 32B

VideoGGUF by mradermacherUpdated 2026-09-03
Download on Hugging Face
Parameters32.8B
Context256K
Layers64
Architectureqwen3vl
Smallest quant0.0 GB
Quick answer

Video SALMONN 2 Pro 32B needs about 22.4 GB of memory at Q4_K_M (a 19.8 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 24 quants, from 0.0 GB to 26.9 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 8.6 GB.

Video SALMONN 2 Pro 32B – 32.8B parameter vision‑audio model

Video SALMONN 2 Pro 32B is a 32.8B parameter model built on the Qwen3VL backbone. It supports joint video and audio understanding, detailed video captioning, and audio‑visual question answering. The model is released under the apache‑2.0 license.

Good at

  • Video captioning
  • Audio‑visual question answering
  • Multimodal instruction following

Limits

  • Large VRAM requirement – 29.5 GB at 8 k context for Q6_K
  • No vision support in non‑vision quant files
  • Requires CUDA‑compatible GPU for inference

Best for

  • Developers building multimodal assistants
  • Researchers benchmarking audio‑visual QA
  • Content creators generating video captions

Who it’s for. The model is intended for developers and researchers who need a high‑capacity multimodal foundation model. It is suitable for projects that require detailed video understanding and audio‑visual interaction.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 2.7 GB
Fits Get file →
IQ1_S7.3 GB 10.0 GB
Too big Get file →
IQ1_M8.0 GB 10.6 GB
Too big Get file →
IQ2_XXS9.0 GB 11.7 GB
Too big Get file →
IQ2_XS10.0 GB 12.6 GB
Too big Get file →
IQ2_S10.5 GB 13.2 GB
Too big Get file →
IQ2_M11.4 GB 14.0 GB
Too big Get file →
Q2_K_S11.5 GB 14.1 GB
Too big Get file →
Q2_K12.3 GB 15.0 GB
Too big Get file →
IQ3_XXS12.8 GB 15.5 GB
Too big Get file →
IQ3_XS13.7 GB 16.4 GB
Too big Get file →
Q3_K_S14.4 GB 17.0 GB
Too big Get file →
IQ3_S14.4 GB 17.1 GB
Too big Get file →
IQ3_M14.9 GB 17.6 GB
Too big Get file →
Q3_K_M16.0 GB 18.6 GB
Too big Get file →
Q3_K_L17.3 GB 20.0 GB
Too big Get file →
IQ4_XS17.7 GB 20.3 GB
Too big Get file →
Q4_018.7 GB 21.4 GB
Too big Get file →
Q4_K_S18.8 GB 21.4 GB
Too big Get file →
Q4_K_M19.8 GB 22.4 GB
Too big Get file →
Q4_120.6 GB 23.3 GB
Too big Get file →
Q5_K_S22.6 GB 25.3 GB
Too big Get file →
Q5_K_M23.2 GB 25.9 GB
Too big Get file →
Q6_K26.9 GB 29.5 GB
Too big Get file →

For 8 GB VRAM use IQ1_S (7.32 GB file, 10 GB memory). For 16 GB VRAM use Q3_K_M (15.97 GB file, 18.6 GB memory). For 32 GB VRAM use Q6_K (26.88 GB file, 29.5 GB memory). Estimates are approximate.

What GPU do you need for Video SALMONN 2 Pro 32B?

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 the main file (0.0 GB file, about 2.7 GB in use).
  • 6 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 2.7 GB in use).
  • 8 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 2.7 GB in use).
  • 12 GB VRAM: the best quant that fits is IQ2_XXS (9.0 GB file, about 11.7 GB in use).
  • 16 GB VRAM: the best quant that fits is IQ3_XXS (12.8 GB file, about 15.5 GB in use).
  • 24 GB VRAM: the best quant that fits is Q4_1 (20.6 GB file, about 23.3 GB in use).
  • 32 GB VRAM: the best quant that fits is Q6_K (26.9 GB file, about 29.5 GB in use).

Which Video SALMONN 2 Pro 32B quant should you choose?

Q4_K_M is the usual starting point for Video SALMONN 2 Pro 32B: it balances file size and quality well. Here it is a 19.8 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

Architectureqwen3vl
Parameters32.8B
Layers64
Trained context262,144 tokens
KV cache (fp16)256 KB per token

Source

Quantized bymradermacher
FamilyVideo
Licenseapache-2.0
Downloads (HF)1,234
Last updated2026-09-03

Frequently asked questions about Video SALMONN 2 Pro 32B

How much VRAM does Video SALMONN 2 Pro 32B need?

About 22.4 GB at Q4_K_M with an 8K context window. That is the 19.8 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 Video SALMONN 2 Pro 32B on an 8 GB GPU?

Yes, with the smaller files: the 0.0 GB file needs about 2.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Video SALMONN 2 Pro 32B GGUF?

It depends on the quant: file is 0.0 GB, IQ1_S is 7.3 GB, IQ1_M is 8.0 GB, IQ2_XXS is 9.0 GB, IQ2_XS is 10.0 GB, IQ2_S is 10.5 GB and 18 more.

What context length does Video SALMONN 2 Pro 32B support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 2.1 GB at 8K and 8.6 GB at 32K.

Where can I download Video SALMONN 2 Pro 32B GGUF?

The files are on Hugging Face in the mradermacher/video-SALMONN-2-Pro-32B-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 Video SALMONN 2 Pro 32B 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 Video SALMONN 2 Pro 32B on 8 GB VRAM?

No. The smallest quant requires 10 GB memory at 8 k context, so 8 GB VRAM is insufficient.

Does the model support audio input?

Yes, audio‑visual alignment is part of the training pipeline and can be enabled with the --no-audio flag to ignore audio.

Is the model available for commercial use?

It is licensed under apache‑2.0, which permits commercial use with attribution.

Other GGUFs of video-SALMONN-2-Pro-32B

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Video models

All Video →

Other medium models

All medium models →