SeedVR2 needs about 2.7 GB of memory at Q4_K_M (a 2.0 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 15 quants, from 1.6 GB (Q3_K_M) to 8.8 GB (Q8_0).
SeedVR2 – a 3.39B parameter video upscaler in GGUF format
SeedVR2 is a 3.39 billion‑parameter model designed for high‑quality video and image upscaling. It is available as a GGUF quantization and can run on multiple GPUs via llama.cpp. The model is released under the Apache‑2.0 license.
Good at
- Video upscaling
- Image upscaling
- Multi‑GPU deployment
Limits
- No vision support beyond upscaling
- Requires 8 k context for full performance
- Large VRAM needed for higher quants
Best for
- Enhancing low‑resolution videos
- Restoring archival footage
- Batch upscaling in pipelines
Who it’s for. Developers and content creators who need efficient, open‑source upscaling. The model is suitable for integration into ComfyUI workflows or standalone CLI usage on systems with sufficient GPU memory.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q3_K_M | 1.6 GB | 2.2 GB | Fits | Get file → | |
| Q4_K_M | 2.0 GB | 2.7 GB | Fits | Get file → | |
| Q5_K_M | 2.4 GB | 3.2 GB | Fits | Get file → | |
| Q6_K | 2.9 GB | 3.7 GB | Fits | Get file → | |
| Q8_0 | 3.7 GB | 4.6 GB | Fits | Get file → | |
| Q3_K_M | 3.7 GB | 4.6 GB | Fits | Get file → | |
| Q3_K_M | 3.7 GB | 4.6 GB | Fits | Get file → | |
| Q4_K_M | 4.8 GB | 5.8 GB | Fits | Get file → | |
| Q4_K_M | 4.8 GB | 5.8 GB | Fits | Get file → | |
| Q5_K_M | 5.8 GB | 7.0 GB | Fits | Get file → | |
| Q5_K_M | 5.8 GB | 7.0 GB | Fits | Get file → | |
| Q6_K | 6.9 GB | 8.2 GB | Too big | Get file → | |
| Q6_K | 6.9 GB | 8.2 GB | Too big | Get file → | |
| Q8_0 | 8.8 GB | 10.4 GB | Too big | Get file → | |
| Q8_0 | 8.8 GB | 10.4 GB | Too big | Get file → |
For 8 GB VRAM, use Q4_K_M (file size 2 GB, estimated 2.7 GB memory). If 12 GB is available, Q5_K_M (2.41 GB, 3.2 GB memory) is a good balance. For 16 GB or more, Q6_K (2.85 GB, 3.7 GB memory) or Q8_0 (3.66 GB, 4.6 GB memory) provide higher quality.
What GPU do you need for SeedVR2?
These figures add the file size, an fp16 KV cache at an 8K context window 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 (2.9 GB file, about 3.7 GB in use).
- 6 GB VRAM: the best quant that fits is Q4_K_M (4.8 GB file, about 5.8 GB in use).
- 8 GB VRAM: the best quant that fits is Q5_K_M (5.8 GB file, about 7.0 GB in use).
- 12 GB VRAM: the best quant that fits is Q8_0 (8.8 GB file, about 10.4 GB in use).
Which SeedVR2 quant should you choose?
Q4_K_M is the usual starting point for SeedVR2: it balances file size and quality well. Here it is a 2.0 GB file.
The Q8_0 file is 3.7 GB, about 1.8 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_M at 1.6 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
Source
Frequently asked questions about SeedVR2
How much VRAM does SeedVR2 need?
About 2.7 GB at Q4_K_M with an 8K context window. That is the 2.0 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 SeedVR2 on an 8 GB GPU?
Yes, with Q5_K_M: the 5.8 GB file needs about 7.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of SeedVR2 GGUF?
It depends on the quant: Q3_K_M is 1.6 GB, Q4_K_M is 2.0 GB, Q5_K_M is 2.4 GB, Q6_K is 2.9 GB, Q8_0 is 3.7 GB, Q3_K_M is 3.7 GB and 9 more.
Where can I download SeedVR2 GGUF?
The files are on Hugging Face in the cmeka/SeedVR2-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 SeedVR2 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 SeedVR2 on 8 GB VRAM?
Yes, the Q4_K_M quant uses about 2.7 GB of VRAM at 8 k context, which fits within an 8 GB GPU.
Does SeedVR2 support multi‑GPU setups?
Yes, it can run as a multi‑GPU standalone CLI via llama.cpp, suitable for larger batch processing.