RWKV 24B A2B wakaba 2601 needs about 16.0 GB of memory at Q4_K_M (a 14.7 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 6 quants, from 9.6 GB (IQ3_XXS) to 14.7 GB (Q4_K_M). Longer context needs more: at 32K tokens the KV cache alone adds about 3.2 GB.
RWKV 24B A2B wakaba 2601 is a 23.5B-parameter Rwkv model in GGUF format, quantized by OpenMOSE. Its trained context length is 256K tokens. The repository has 6 quant files, from 9.6 GB (IQ3_XXS) to 14.7 GB (Q4_K_M).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ3_XXS | 9.6 GB | 10.9 GB | Too big | Get file → | |
| IQ3_XXS | 9.6 GB | 10.9 GB | Too big | Get file → | |
| IQ4_XS | 13.0 GB | 14.3 GB | Too big | Get file → | |
| IQ4_XS | 13.0 GB | 14.3 GB | Too big | Get file → | |
| Q4_K_M | 14.7 GB | 16.0 GB | Too big | Get file → | |
| Q4_K_M | 14.7 GB | 16.0 GB | Too big | Get file → |
What GPU do you need for RWKV 24B A2B wakaba 2601?
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: the best quant that fits is IQ3_XXS (9.6 GB file, about 10.9 GB in use).
- 16 GB VRAM: the best quant that fits is Q4_K_M (14.7 GB file, about 16.0 GB in use).
Which RWKV 24B A2B wakaba 2601 quant should you choose?
Q4_K_M is the usual starting point for RWKV 24B A2B wakaba 2601: it balances file size and quality well. Here it is a 14.7 GB file.
If memory is tight, the smallest file is IQ3_XXS at 9.6 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 RWKV 24B A2B wakaba 2601
How much VRAM does RWKV 24B A2B wakaba 2601 need?
About 16.0 GB at Q4_K_M with an 8K context window. That is the 14.7 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 RWKV 24B A2B wakaba 2601 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 10.9 GB, so you would need a larger GPU or CPU offloading.
What is the file size of RWKV 24B A2B wakaba 2601 GGUF?
It depends on the quant: IQ3_XXS is 9.6 GB, IQ3_XXS is 9.6 GB, IQ4_XS is 13.0 GB, IQ4_XS is 13.0 GB, Q4_K_M is 14.7 GB, Q4_K_M is 14.7 GB.
What context length does RWKV 24B A2B wakaba 2601 support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 0.8 GB at 8K and 3.2 GB at 32K.
Where can I download RWKV 24B A2B wakaba 2601 GGUF?
The files are on Hugging Face in the OpenMOSE/RWKV-24B-A2B-wakaba-2601-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 24B A2B wakaba 2601 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.