ModelLLMsv6.0

RWKV-6

by RWKV Foundation · open-source · Last verified 2026-03-17

Sixth generation of the RWKV architecture combining transformer-level quality with RNN efficiency for linear-time inference. Enables constant memory usage regardless of sequence length, making it ideal for resource-constrained and streaming applications.

https://wiki.rwkv.com ↗

D—Poor

Adoption: DQuality: BFreshness: C+Citations: CEngagement: F

Specifications

License: Apache 2.0
Pricing: open-source
Capabilities: text-generation, linear-time-inference, constant-memory, streaming-generation, multilingual
Integrations: huggingface, rwkv-runner, ollama
Use Cases: edge-deployment, streaming-applications, resource-constrained-inference, real-time-generation
API Available: No
Parameters: 14B
Context Window: Unlimited (linear RNN)
Modalities: text
Training Cutoff: Mid 2024
Tags: llm, open-source, rnn-architecture, linear-attention, efficient
Added: 2026-03-17
Completeness: 85%

Index Score

34.8

Adoption

Quality

Freshness

Citations

Engagement

Explore the full AI ecosystem on Agents as a Service