RW

rwkv7-g1k-13.3b-20260930-ctx25600.pth

RwkvGGUF by shoumenchougouUpdated 2026-09-30
Download on Hugging Face
Parameters13.3B
Context1024K
Layers61
Architecturerwkv7
Smallest quant8.5 GB
Quick answer

rwkv7-g1k-13.3b-20260930-ctx25600.pth needs about 10.0 GB of memory at Q4_K_M (a 8.5 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 5 quants, from 8.5 GB (Q4_K_M) to 26.7 GB.

RWKV-7 G1k 13.3B base model for local inference

RWKV-7 G1k 13.3B is a base language model in GGUF format. It uses a recurrent architecture with constant‑size state. The model is available in several quantizations for different memory budgets.

Good at

  • Recurrent architecture with constant state
  • Large context support up to 1,048,576 tokens
  • Efficient inference on local hardware

Limits

  • No vision support
  • Not instruction‑tuned
  • Requires 8,000 context for memory estimates

Best for

  • Local text generation
  • Fine‑tuning on custom data
  • Low‑latency inference on GPUs

Who it’s for. Developers and researchers who need a large, efficient local language model for text generation and fine‑tuning. The model is suitable for users with access to GPU or CPU inference tools such as llama.cpp or Ollama.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M8.5 GB 10.0 GB
Too big Get file →
Q5_K_M10.0 GB 11.7 GB
Too big Get file →
Q6_K11.6 GB 13.5 GB
Too big Get file →
Q8_014.7 GB 17.0 GB
Too big Get file →
—26.7 GB 30.5 GB
Too big Get file →

For 8 GB VRAM, use Q4_K_M (file size 8.46 GB, estimated 10 GB memory at 8 k context). For 12 GB VRAM, Q5_K_M (9.99 GB, 11.7 GB). For 16 GB VRAM, Q6_K (11.62 GB, 13.5 GB).

What GPU do you need for rwkv7-g1k-13.3b-20260930-ctx25600.pth?

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: 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 Q5_K_M (10.0 GB file, about 11.7 GB in use).
  • 16 GB VRAM: the best quant that fits is Q6_K (11.6 GB file, about 13.5 GB in use).
  • 24 GB VRAM: the best quant that fits is Q8_0 (14.7 GB file, about 17.0 GB in use).
  • 32 GB VRAM: the best quant that fits is the main file (26.7 GB file, about 30.5 GB in use).

Which rwkv7-g1k-13.3b-20260930-ctx25600.pth quant should you choose?

Q4_K_M is the usual starting point for rwkv7-g1k-13.3b-20260930-ctx25600.pth: it balances file size and quality well. Here it is a 8.5 GB file.

The Q8_0 file is 14.7 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
Parameters13.3B
Layers61
Trained context1,048,576 tokens

Source

Quantized byshoumenchougou
FamilyRwkv
Licenseapache-2.0
Downloads (HF)3,096
Last updated2026-09-30

Frequently asked questions about rwkv7-g1k-13.3b-20260930-ctx25600.pth

How much VRAM does rwkv7-g1k-13.3b-20260930-ctx25600.pth need?

About 10.0 GB at Q4_K_M with an 8K context window. That is the 8.5 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 rwkv7-g1k-13.3b-20260930-ctx25600.pth on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 10.0 GB, so you would need a larger GPU or CPU offloading.

What is the file size of rwkv7-g1k-13.3b-20260930-ctx25600.pth GGUF?

It depends on the quant: Q4_K_M is 8.5 GB, Q5_K_M is 10.0 GB, Q6_K is 11.6 GB, Q8_0 is 14.7 GB, file is 26.7 GB.

What context length does rwkv7-g1k-13.3b-20260930-ctx25600.pth support?

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

Where can I download rwkv7-g1k-13.3b-20260930-ctx25600.pth GGUF?

The files are on Hugging Face in the shoumenchougou/RWKV7-G1k-13.3B-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 rwkv7-g1k-13.3b-20260930-ctx25600.pth 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.

Can I run RWKV-7 G1k 13.3B on 8 GB VRAM?

Yes, using the Q4_K_M quantization which estimates 10 GB memory at 8 k context, but actual VRAM usage may vary with batch size.

Does this model support image input?

No, it is a pure text model with no vision capabilities.

Is the model instruction‑tuned?

No, it is a base language model and may not follow instructions consistently.

Other GGUFs of rwkv7-g1

Similar models

Browse all →

More from shoumenchougou

All by shoumenchougou →

More Rwkv models

All Rwkv →

Other medium models

All medium models →