Rwkv GGUF models
171 GGUF models in the Rwkv family, quantized by 25 uploaders. Sizes run from 191M to 37.2B parameters. The longest trained context is 1024K tokens.
About the Rwkv GGUF models
Rwkv is represented on ggufmodels.com by 171 GGUF models, quantized by 25 uploaders on Hugging Face. The most downloaded are Rwkv 6 World 7b, rwkv 6 world 3b and Rwkv 6 World 7b. Parameter counts run from 191M to 37.2B, and the longest trained context window is 1024K tokens.
A Q4_K_M file of a Rwkv model is between 0.0 to 24.6 GB, which is the quant most people start with. Most files come from shoumenchougou (56), mradermacher (25) and RemySkye (16). The quants you will meet most often are Q4_K_M (135), Q8_0 (132), Q5_K_M (129) and Q6_K (127), where the number is how many models offer that quant.
Frequently asked questions
Which Rwkv GGUF should I download?
The most downloaded Rwkv GGUF here is Rwkv 6 World 7b. Pick the size that fits your GPU first, then choose a quant: Q4_K_M is the usual starting point, and Q5_K_M or Q6_K give more quality if you have memory to spare. The VRAM pages below list what fits each GPU.
How much VRAM does a Rwkv model need?
Q4_K_M files of Rwkv models on this site range from 0.0 to 24.6 GB. Add the KV cache for your context length and about 0.5 GB for the runtime, which usually means 1.5 to 3 GB on top of the file at an 8K context.
Where do Rwkv GGUF files come from?
The most common quantizers here are shoumenchougou, mradermacher and RemySkye. They convert the original model and publish quantized files on Hugging Face. ggufmodels.com does not host files; every download button opens Hugging Face.