RWKV

RNN-based language model with transformer-level performance and linear scaling.

Open SourceSelf HostedOffline CapableGPU Required (4GB+ VRAM)
0.0 (0)

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

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.

Open SourceSelf HostedOfflineGPU 8GB+
Intermediate
0.0 (0)
Featured

High-performance open-weight MoE LLM with 671B total parameters.

Open SourceSelf HostedOfflineGPU 24GB+
Advanced
0.0 (0)

Hybrid SSM-Transformer model by AI21 Labs combining Mamba with attention layers.

Open SourceSelf HostedOfflineGPU 12GB+
Intermediate
0.0 (0)

State-space model for language with linear-time sequence modeling.

Open SourceSelf HostedOfflineGPU 8GB+
Advanced
0.0 (0)

Family of small language models by Hugging Face for on-device use.

Open SourceSelf HostedOffline
Beginner
0.0 (0)

Open-weight LLM by Meta in 8B and 70B sizes with strong general capabilities.

Open SourceSelf HostedOfflineGPU 8GB+
Intermediate
0.0 (0)
Browse all Large Language Models (LLMs) tools