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.

TinySmallMediumLarge
Most downloadedNewestLargestLongest contextSmallest
RW
Rwkv 6 World 7b
Rwkv · latestissue
Params7.64B
Context1024K
Smallest3.0 GB
GGUF
RW
rwkv 6 world 3b
Rwkv · latestissue
Params3.1B
Context1024K
Smallest1.2 GB
GGUF
RW
Rwkv 6 World 7b
Rwkv · bartowski
Params7.64B
Context1024K
Q4_K_M4.8 GB
GGUF
RW
rwkv7 g1h 1.5b i1
Rwkv · RemySkye
Params1.53B
Context1024K
Q4_K_M1.1 GB
GGUF
RW
rwkv7-g1k-13.3b-20260930-ctx25600.pth
Rwkv · shoumenchougou
Params13.3B
Context1024K
Q4_K_M8.5 GB
GGUF
RW
rwkv 6 finch 14b
Rwkv · latestissue
Params14.1B
Context1024K
Smallest5.4 GB
GGUF
RW
rwkv 6 world 1b6
Rwkv · latestissue
Params1.6B
Context1024K
Smallest0.7 GB
GGUF
RW
rwkv 6 finch 1b6
Rwkv · latestissue
Params1.6B
Context1024K
Smallest0.7 GB
GGUF
RW
rwkv7 g1h 2.9b i1
Rwkv · RemySkye
Params2.95B
Context1024K
Q4_K_M2.1 GB
GGUF
RW
rwkv7-g1k-7.2b-20260930-ctx25600.pth
Rwkv · shoumenchougou
Params7.2B
Context1024K
Q4_K_M4.6 GB
GGUF
RW
RWKV 5.2 3B NSFW Role 16k
Rwkv · mzwing
Params3.1B
Context1024K
Q4_K_M1.9 GB
GGUF
RW
rwkv7-g1c-13.3b-20251231-ctx8192.pth
Rwkv · NaomiBTW
Params13.3B
Context1024K
Q4_K_M8.4 GB
GGUF
RW
Rwkv7 2.9B G1
Rwkv · Mungert
Params2.95B
Context1024K
Q4_K_M2.0 GB
Reasoning
RW
Rwkv7 G1 1.5b Instruct Preview
Rwkv · mzwing
Params1.53B
Context1024K
Q4_K_M1.0 GB
GGUF
RW
RWKV6 3B Chn UnlimitedRP mini chat
Rwkv · btaskel
Params3.1B
Context1024K
Smallest1.9 GB
GGUF
RW
RWKV7 2.9B v3 UnlimitedRP Mini Novel Chat Preview
Rwkv · mzwing
Params2.95B
Context1024K
Q4_K_M1.9 GB
GGUF
RW
RWKV6 3B Chn UnlimitedRP Mini Chat HF
Rwkv · mzwing
Params3.1B
Context1024K
Q4_K_M1.9 GB
GGUF
RW
RWKV7-Goose-World3-2.9B-HF
Rwkv · Mungert
Params2.95B
Context1024K
Q4_K_M1.9 GB
GGUF
RW
Rwkv7 G1 1.5b Lonely Neko
Rwkv · mzwing
Params1.53B
Context1024K
Q4_K_M1.0 GB
GGUF
RW
rwkv7-g1h-2.9b-20260710-ctx10240.pth
Rwkv · RemySkye
Params2.95B
Context1024K
Q4_K_M2.1 GB
Reasoning
RW
Rwkv 6 World 7b
Rwkv · mradermacher
Params7.64B
Context1024K
Q4_K_M4.8 GB
GGUF
RW
RWKV6 7B v3 Porn Chat Pro
Rwkv · mzwing
Params7.64B
Context1024K
Q4_K_M4.8 GB
GGUF
RW
rwkv7 g1h 7.2b i1
Rwkv · RemySkye
Params7.2B
Context1024K
Q4_K_M4.9 GB
Reasoning
RW
rwkv7-g1h-7.2b-20260710-ctx10240.pth
Rwkv · RemySkye
Params7.2B
Context1024K
Q4_K_M4.9 GB
Reasoning
RW
RWKV v7 0.1B G1
Rwkv · LuRenJiasWorld
Params191M
Context1024K
Q4_K_M0.1 GB
Reasoning
RW
rwkv7-2.9B-world
Rwkv · Mungert
Params2.95B
Context1024K
Q4_K_M1.9 GB
GGUF
RW
rwkv7-g1k-2.9b-20260930-ctx25600.pth
Rwkv · shoumenchougou
Params2.95B
Context1024K
Q4_K_M1.9 GB
Reasoning
RW
rwkv7-g1l-13.3b-20261031-ctx34304.pth
Rwkv · shoumenchougou
Params13.3B
Context1024K
Q4_K_M8.5 GB
Reasoning
RW
rwkv7 g1g 7.2b i1
Rwkv · RemySkye
Params7.2B
Context1024K
Q4_K_M4.5 GB
Reasoning
RW
RWKV6 7B v3 Porn Chat
Rwkv · mzwing
Params7.64B
Context1024K
Q4_K_M4.8 GB
GGUF

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.

Keep browsing