agbalu/Jugurtha-4B

Text Generation • 5B • Updated 1 day ago • 851 • 4

Note Base BF16 weights for Transformers and vLLM.

agbalu/Jugurtha-4B-GGUF

Text Generation • 4B • Updated 16 days ago • 450 • 2

Note GGUF quantizations for Ollama, llama.cpp, and LM Studio.

agbalu/Jugurtha-4B-MLX-4bit

Text Generation • 4B • Updated 16 days ago • 365 • 2

Note 4-bit MLX quantization for Apple Silicon.

Note Classical world literature and oral poetry in Kabyle.

Note Official interactive chat interface (GGUF Q4_K_M)

agbalu/Jugurtha-2-9B

Text Generation • 10B • Updated 1 day ago • 770 • 1

Note Second-generation sovereign Kabyle reasoning foundation model (8.95B). 80.81% SIB-200, 49.45 chrF++ kab→eng, native chain-of-thought.

agbalu/Jugurtha-2-9B-GGUF

Text Generation • 9B • Updated 5 days ago • 363

Note GGUF quantizations (Q4_K_M, Q5_K_M, Q6_K, Q8_0) for Ollama, LM Studio, and llama.cpp.