RWKV
RNN-based language model with transformer-level performance and linear scaling.
About
RWKV is a language model architecture that blends the training parallelism of transformers with the linear-time, constant-memory inference of recurrent networks, using no key-value cache. The RWKV-7 generation is attention-free and updates its state in context at every token, suiting long-context and multimodal use, and models range from small to 14B parameters. It is a Linux Foundation AI project. Released under the Apache 2.0 license.
Reviews (0)
Leave a Review
No reviews yet. Be the first to review!
Details
- Category
- Large Language Models (LLMs)
- Price
- Free
- Platform
- Local/Desktop
- Difficulty
- Intermediate (3/5)
- License
- Apache-2.0
- Minimum VRAM
- 4 GB
- Added
- Apr 3, 2026
Related Tools
Open-source code LLM family by IBM for enterprise code generation.
High-performance open-weight MoE LLM with 671B total parameters.
Hybrid SSM-Transformer model by AI21 Labs combining Mamba with attention layers.
State-space model for language with linear-time sequence modeling.
Family of small language models by Hugging Face for on-device use.
Open-weight LLM by Meta in 8B and 70B sizes with strong general capabilities.