RW

RWKV v7 2.9B World v3

RwkvGGUF by zhiyuan8Updated 2025-06-06
Download on Hugging Face
Parameters2.95B
Context1024K
Layers32
Architecturerwkv7
Smallest quant1.9 GB
Quick answer

RWKV v7 2.9B World v3 needs about 2.6 GB of memory at Q4_K_M (a 1.9 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 4 quants, from 1.9 GB (Q4_K_M) to 5.9 GB (F16).

RWKV v7 2.9B World v3 is a 2.95B-parameter Rwkv model in GGUF format, quantized by zhiyuan8. Its trained context length is 1024K tokens. The repository has 4 quant files, from 1.9 GB (Q4_K_M) to 5.9 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M1.9 GB 2.6 GB
Fits Get file →
Q5_K_M2.2 GB 3.0 GB
Fits Get file →
Q8_03.3 GB 4.1 GB
Fits Get file →
F165.9 GB 7.1 GB
Fits Get file →

What GPU do you need for RWKV v7 2.9B World v3?

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 Q5_K_M (2.2 GB file, about 3.0 GB in use).
  • 6 GB VRAM: the best quant that fits is Q8_0 (3.3 GB file, about 4.1 GB in use).
  • 8 GB VRAM: the best quant that fits is F16 (5.9 GB file, about 7.1 GB in use).

Which RWKV v7 2.9B World v3 quant should you choose?

Q4_K_M is the usual starting point for RWKV v7 2.9B World v3: it balances file size and quality well. Here it is a 1.9 GB file.

The Q8_0 file is 3.3 GB, about 1.7 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.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturerwkv7
Parameters2.95B
Layers32
Trained context1,048,576 tokens

Source

Quantized byzhiyuan8
FamilyRwkv
Licenseapache-2.0
Downloads (HF)80
Last updated2025-06-06

Frequently asked questions about RWKV v7 2.9B World v3

How much VRAM does RWKV v7 2.9B World v3 need?

About 2.6 GB at Q4_K_M with an 8K context window. That is the 1.9 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 v7 2.9B World v3 on an 8 GB GPU?

Yes, with F16: the 5.9 GB file needs about 7.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of RWKV v7 2.9B World v3 GGUF?

It depends on the quant: Q4_K_M is 1.9 GB, Q5_K_M is 2.2 GB, Q8_0 is 3.3 GB, F16 is 5.9 GB.

What context length does RWKV v7 2.9B World v3 support?

The GGUF header lists a trained context length of 1,048,576 tokens (1024K).

Where can I download RWKV v7 2.9B World v3 GGUF?

The files are on Hugging Face in the zhiyuan8/RWKV-v7-2.9B-World-v3-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 v7 2.9B World v3 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.

Other GGUFs of rwkv-7-world

Similar models

Browse all →

More from zhiyuan8

All by zhiyuan8 →

More Rwkv models

All Rwkv →

Other tiny models

All tiny models →