Filters

-
-
-
Reset

Open-Weight LLM Models — Live Ranking, Benchmarks & Specs

Explore, filter and compare open-weight language models with live specs, benchmarks and license data

Raon-1 nano

KRAFTON AI

Open Weights

Parameters

3.1B

Released

29.10.26

hybrid dense Transformer decoder with Raon Delta Attention (18 linear attention layers) and Gated MLA (6 full-attention layers), Raon-mHC residual connections (4 streams), per-layer embeddings (256), tied LM head, NoPE
Raon
Apache License 2.0
Openness Score 1.0

Raon-1 mini

KRAFTON AI

Open Weights

Parameters

28.8B total / 4.3B active

Released

21.10.26

hybrid Mixture-of-Experts (MoE) Transformer decoder with Raon Delta Attention (18 linear attention layers) and Gated MLA (7 full-attention layers), Raon-mHC residual connections, NoPE
Raon
Apache License 2.0
Openness Score 1.0