What are the hardware requirements for RWKV7 13.3B 20260805?

RWKV7 13.3B 20260805 requires approximately 26.6 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed RWKV7 13.3B 20260805 and how large is it?

RWKV7 13.3B 20260805 is developed by RWKV, a model with 13.3b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

Where can I download or evaluate RWKV7 13.3B 20260805?

RWKV7 13.3B 20260805 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

RWKV7 13.3B 20260805 by RWKV — VRAM 26.6GB

Name: RWKV7 13.3B 20260805
Author: RWKV

RWKV7 13.3B 20260805 is an open-source language model by RWKV. Features: 13.3b LLM, VRAM: 26.6GB, License: apache-2.0, LLM Explorer Score: 0.3.

Arxiv:2503.14456 Ar Conversational Dataset:bigcode/starcoderdata Dataset:cerebras/slimpajama-62... Dataset:eleutherai/pile Dataset:huggingfacefw/fineweb-... Dataset:mlfoundations/dclm-bas... Dataset:oscar-corpus/oscar-230... De En Endpoints compatible Es Fr It Ja Ko Pt Recurrent Region:us Ru Rwkv Rwkv7 Safetensors Sharded Tensorflow Vi Zh

Model Card on HF 🤗: https://huggingface.co/RWKV/RWKV7-13.3B-20260805

RWKV7 13.3B 20260805 Parameters and Internals

LLM Name	RWKV7 13.3B 20260805
Repository 🤗	https://huggingface.co/RWKV/RWKV7-13.3B-20260805
Model Size	13.3b
Required VRAM	26.6 GB
Updated	2026-08-08
Maintainer	RWKV
Model Type	rwkv7
Model Files	5.0 GB: 1-of-6 4.9 GB: 2-of-6 5.0 GB: 3-of-6 5.0 GB: 4-of-6 5.0 GB: 5-of-6 1.7 GB: 6-of-6
Supported Languages	en zh fr es de pt ru it ja ko vi ar
Model Architecture	Rwkv7ForCausalLM
License	apache-2.0
Tokenizer Class	PreTrainedTokenizerFast
Padding Token	<\|endoftext\|>
Vocabulary Size	65536

Rank the RWKV7 13.3B 20260805 capabilities

Have you tried this model? Rate its performance — this feedback helps the ML community find the right model for their needs.

Instruction Following and Task Automation
Factuality and Completeness of Knowledge
Censorship and Alignment
Data Analysis and Insight Generation
Text Generation
Text Summarization and Feature Extraction
Code Generation
Multi-Language Support and Translation