RWKV
Shares rank 66 of 72 language models by recommenders
An open recurrent language model that uses recurrent blocks instead of attention, reaching near-Transformer performance at small scale with well-documented research.
An open recurrent language model that uses recurrent blocks instead of attention, reaching near-Transformer performance at small scale with well-documented research.
6 people gave an opinion
- recommend it
- 6
- criticize it
- 0
- approval share
- 100%
Recommended in 5 of 13 months
- November 2025: not recommended
- December 2025: recommended
- January 2026: not recommended
- February 2026: recommended
- March 2026: recommended
- April 2026: recommended
- May 2026: not recommended
- June 2026: not recommended
- July 2026: not recommended
- August 2026: recommended
- September 2026: not recommended
- October 2026: not recommended
- November 2026: not recommended (month in progress)
Why it doesn’t carry the badge
- 6 people recommend itNeeds 10 or more, not met.
- Nobody criticizes itNeeds 2 to 1 or better, met.
- Recommended in 5 of 13 monthsNeeds 4 or more, met.
The same three rules apply to every product, and the badge can’t be bought. How the badge works
What people say about it
The reasons people give, with the number of comments that give each one. Open a reason to read what they said.
Why people recommend it
Each mark is one comment
Recurrent design, close to Transformers
“RWKV and Mamba families LLM-s have recurrent blocks instead of attention, and they get really close to performance of Transformer on small scale.”
Comment from 3 Feb 2026 in “The Core Flaws of Modern AI Based on Large Language Models” Excellent research and diagrams
“they've done an excellent job with the accompanying research, provide plenty of reference diagrams and visualization”
Comment from 16 Mar 2026 in “LLM Architecture Gallery” Handles state-tracking that attention cannot
“It solves state-tracking problems that fixed-depth attention provably cannot.”
Comment from 23 Feb 2026 in “RWKV-7 beats Llama 3.2 with 3x fewer training tokens and formally exceeds TC^0”
Other language models people recommend
The four most recommended other language models, with the same counts for each, so you can compare like for like. The tick on each bar marks the 2 to 1 line the badge needs.
| Product | Recommend | Criticize | Approval | Months | Owned | Badge |
|---|---|---|---|---|---|---|
| Claude Opus | 3,331 | 2,746 | 55% | 13 | 4 mo156 owners | — |
| OpenAI GPT | 1,205 | 987 | 55% | 13 | 6 mo47 owners | — |
| Claude Sonnet | 854 | 586 | 59% | 13 | 6 mo46 owners | — |
| DeepSeek V4 Flash | 828 | 223 | 79% | 8 | 1 mo24 owners | Approved |
| RWKVThis page | 6 | 0 | 100% | 5 | — | — |
What people said
4 of the 6 comments that mention it, newest first. Each links to the original comment.
“Still a lot better than 2.826 bits per bytes of xz level 9.”
“they've done an excellent job with the accompanying research, provide plenty of reference diagrams and visualization”
“It solves state-tracking problems that fixed-depth attention provably cannot.”
“RWKV and Mamba families LLM-s have recurrent blocks instead of attention, and they get really close to performance of Transformer on small scale.”
Counts come from 1,795,640 Hacker News comments, November 2025 to November 2026. How we count. Report a mistake.