LLM Reference

RWKV Project

Researched today
Flagship Q/$
Quality
$/M out

8 models across 2 families · Latest: RWKV-7 Goose 2.9B (2025-03)

Linear complexity language models combining the efficiency of RNNs with the parallelism of Transformers

Long context

RWKV Project's portfolio covers 8 active models across 2 non-obsolete families, with task labels spanning long context. Open a model detail page to compare provider routes and sourced benchmarks.

Portfolio context: 1 decision-task tag, 8 active tracked models, latest research stamp 2026-05-25.

Use this portfolio page for

  • Teams evaluating long context across this lab's releases
  • Readers comparing families before locking a flagship SKU
  • 8 tracked SKUs for migration and pricing follow-ups

Do not stop here for

  • Choosing a hosting provider without opening a model page for price ladders

Active models

8

Non-deprecated SKUs linked to this researcher

Active families

2

Non-obsolete families in coverage

Open catalog

0 OSS

0 open-weight (text match)

Decision task tags

1

Mapped to the site-wide task taxonomy

Latest dated release

2025-03-18

RWKV-7 Goose 2.9B

Freshness

2026-05-25

Researched today

fresh

Release cadence

Showing 5 recent dated ships (full timeline below). Latest spotlight: RWKV-7 Goose 2.9B (2025-03-18).

Where this lab wins

  • Long-context: 8 tracked models with context-token or InfiniteBench-class signal.

Flagship quality / price signal

Anchor SKU: RWKV-6 Finch 14B (best sourced coding Q/$ in this portfolio).

Quality / dollar unavailable for this anchor — missing benchmark coverage and/or output token price on the cheapest ladder route (open the model detail after pricing lands).

RWKV Project is an AI research organization. Linear complexity language models combining the efficiency of RNNs with the parallelism of Transformers. RWKV Project ships 2 model families totaling 8 models, with the most recent release RWKV-7 Goose 2.9B in 2025-03. Notable families include RWKV-7 Goose and RWKV-6 Finch. Use it as a stable reference for lab background, release coverage, and follow-up model pages as they are added.

About

The RWKV Project, maintained under the Linux Foundation AI & Data Foundation and led by Bo Peng, develops the RWKV (Receptance Weighted Key Value) family of language models. RWKV is a pure recurrent architecture that achieves linear O(n) time complexity during training and O(1) constant-memory inference — unlike Transformers which require quadratic attention and growing KV caches. The architecture has progressed through major versions: RWKV-4 (Dove, 2023), RWKV-5 (Eagle), RWKV-6 (Finch, 2024), RWKV-7 (Goose, 2025), and experimental RWKV-8 (Heron). All production models are released under Apache 2.0. The World series models are trained on multilingual corpora covering 100+ languages.

Featured models

ModelReleasedContextInput price ($/1M)Output price ($/1M)License
RWKV-7 Goose 2.9B2025-03-18Infinite--Apache 2.0
RWKV-7 Goose 1.5B2025-03-18Infinite--Apache 2.0
RWKV-7 Goose 0.4B2025-03-18Infinite--Apache 2.0

Model families

Recent releases

  1. RWKV-7 Goose 2.9B- 2025-03-18
  2. RWKV-7 Goose 1.5B- 2025-03-18
  3. RWKV-7 Goose 0.4B- 2025-03-18
  4. RWKV-7 Goose 0.1B- 2025-03-18
  5. RWKV-6 Finch 14B- 2024-09-03

FAQ

What models has RWKV Project released?

RWKV Project ships 8 models across 2 families: RWKV-7 Goose and RWKV-6 Finch.

Is RWKV Project's technology open source?

All tracked models are released under Apache 2.0.

Where is RWKV Project headquartered?

RWKV Project is headquartered in Global / Linux Foundation AI & Data.

What is RWKV Project known for?

Linear complexity language models combining the efficiency of RNNs with the parallelism of Transformers. Its most prominent tracked family is RWKV-7 Goose.

How can I access RWKV Project's models?

RWKV Project's provider availability is tracked on model pages as API and hosting data is verified.

Explore related pages

Last reviewed: 2026-05-25. Data sourced from public lab announcements and provider documentation.