What are the hardware requirements for RWKV7 Goose World3 1.5B HF?

RWKV7 Goose World3 1.5B HF requires approximately 3 GB of VRAM and supports a context window of 2K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed RWKV7 Goose World3 1.5B HF and how large is it?

RWKV7 Goose World3 1.5B HF is developed by RWKV, a model with 1.5b 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 Goose World3 1.5B HF?

RWKV7 Goose World3 1.5B HF is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

RWKV7 Goose World3 1.5B HF by RWKV — VRAM 3GB, 2K context

Name: RWKV7 Goose World3 1.5B HF
Author: RWKV

RWKV7 Goose World3 1.5B HF is an open-source language model by RWKV. Features: 1.5b LLM, VRAM: 3GB, Context: 2K, License: apache-2.0, LLM Explorer Score: 0.18.

Arxiv:2503.14456 Ar Base model:blinkdl/rwkv-7-worl... Base model:finetune:blinkdl/rw... Conversational Custom code En Es Fr Ja Ko Pt Region:us Rwkv7 Safetensors Zh

Model Card on HF 🤗: https://huggingface.co/RWKV/RWKV7-Goose-World3-1.5B-HF

RWKV7 Goose World3 1.5B HF Parameters and Internals

LLM Name	RWKV7 Goose World3 1.5B HF
Repository 🤗	https://huggingface.co/RWKV/RWKV7-Goose-World3-1.5B-HF
Base Model(s)	BlinkDL/rwkv-7-world BlinkDL/rwkv-7-world
Model Size	1.5b
Required VRAM	3 GB
Updated	2026-06-29
Maintainer	RWKV
Model Type	rwkv7
Model Files	3.0 GB
Supported Languages	en zh ja ko fr ar es pt
Model Architecture	RWKV7ForCausalLM
License	apache-2.0
Context Length	2048
Model Max Length	2048
Transformers Version	4.48.1
Tokenizer Class	RwkvTokenizer
Padding Token	<\|rwkv_tokenizer_end_of_text\|>
Vocabulary Size	65536
Torch Data Type	float32

Rank the RWKV7 Goose World3 1.5B HF 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

Best Alternatives to RWKV7 Goose World3 1.5B HF

Best Alternatives	Context / RAM	Downloads	Likes
Rwkv7 1.5B World	2K / 3 GB	1186	9