RWKV Seed OSS 36B Hybrid needs about 27.3 GB of memory at Q4_K_M (a 24.6 GB file) with an 8K context window, so it fits on a 32 GB GPU. This repository has 4 quants, from 16.9 GB (IQ3_XXS) to 28.4 GB (Q5_K_M). Longer context needs more: at 32K tokens the KV cache alone adds about 8.6 GB.
RWKV Seed OSS 36B Hybrid is a 37.2B-parameter Rwkv model in GGUF format, quantized by OpenMOSE. Its trained context length is 512K tokens. The repository has 4 quant files, from 16.9 GB (IQ3_XXS) to 28.4 GB (Q5_K_M).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ3_XXS | 16.9 GB | 19.6 GB | Too big | Get file → | |
| IQ4_XS | 22.3 GB | 25.0 GB | Too big | Get file → | |
| Q4_K_M | 24.6 GB | 27.3 GB | Too big | Get file → | |
| Q5_K_M | 28.4 GB | 31.1 GB | Too big | Get file → |
What GPU do you need for RWKV Seed OSS 36B Hybrid?
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: no quant fits at an 8K context.
- 8 GB VRAM: no quant fits at an 8K context.
- 12 GB VRAM: no quant fits at an 8K context.
- 16 GB VRAM: no quant fits at an 8K context.
- 24 GB VRAM: the best quant that fits is IQ3_XXS (16.9 GB file, about 19.6 GB in use).
- 32 GB VRAM: the best quant that fits is Q5_K_M (28.4 GB file, about 31.1 GB in use).
Which RWKV Seed OSS 36B Hybrid quant should you choose?
Q4_K_M is the usual starting point for RWKV Seed OSS 36B Hybrid: it balances file size and quality well. Here it is a 24.6 GB file.
If memory is tight, the smallest file is IQ3_XXS at 16.9 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
Source
Frequently asked questions about RWKV Seed OSS 36B Hybrid
How much VRAM does RWKV Seed OSS 36B Hybrid need?
About 27.3 GB at Q4_K_M with an 8K context window. That is the 24.6 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 RWKV Seed OSS 36B Hybrid on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 19.6 GB, so you would need a larger GPU or CPU offloading.
What is the file size of RWKV Seed OSS 36B Hybrid GGUF?
It depends on the quant: IQ3_XXS is 16.9 GB, IQ4_XS is 22.3 GB, Q4_K_M is 24.6 GB, Q5_K_M is 28.4 GB.
What context length does RWKV Seed OSS 36B Hybrid support?
The GGUF header lists a trained context length of 524,288 tokens (512K). 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 RWKV Seed OSS 36B Hybrid GGUF?
The files are on Hugging Face in the OpenMOSE/RWKV-Seed-OSS-36B-Hybrid-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 RWKV Seed OSS 36B Hybrid 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.