Raon-1-nano-gguf

Try Try

Raon-1-nano-gguf has 3.13B parameters and takes 2.07 GB on disk. See where its parameters live, layer by layer, and what hardware it needs.

At a glance

KRAFTON/Raon-1-nano-gguf
Repo createdNov 10, 2026updated Nov 17, 2026
Model type—Not shown: breakdown incomplete
InputsText
Total parameters3.13B
Active per token—Not shown: breakdown incomplete
Experts—Not shown: breakdown incomplete
Max context (from config)256K tokens
Layers2418 linear + 6 full attention
On disk2.07 GB1 file
PrecisionQ4_K (59%), Q6_K (31%), Q8_0 (7.4%), FP16 (2.3%), other (0.12%)
QuantizationQ4_K_M (GGUF)mix of Q4_K, Q6_K, Q8_0 · blocks of 256 / blocks of 32 · 99% of parameters
Fewest GPUs1× RTX 4060a single 8 GB card · weights only
FamilyQuantization of KRAFTON/Raon-1-nano
Licenseapache-2.0
GitHubNot linked